Compare commits

...

1166 Commits

Author SHA1 Message Date
github-actions[bot] 7384e4d273 Release @llamaindex/anthropic@0.3.9 (#1972)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-05-23 13:04:47 +07:00
Peter Goldstein ae75966721 Update Gemini model keys to reflect Google changes (#1968) 2025-05-23 11:22:55 +07:00
Peter Goldstein 5cdab12791 Add Claude Sonnet 4 and Claude Opus 4 models (#1969) 2025-05-23 11:10:50 +07:00
github-actions[bot] eaf2cb11a5 Release 0.11.3 (#1966)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-05-22 16:58:59 +07:00
Marcus Schiesser 3ae01a227e chore: remove repin (#1967) 2025-05-22 16:53:44 +07:00
Marcus Schiesser 76ff23dc48 fix: pRetry not working with CommonJS 2025-05-22 15:14:00 +07:00
github-actions[bot] ed497727b1 Release 0.11.2 (#1964)
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-05-22 14:34:37 +07:00
Marcus Schiesser 59601dd3ab feat: Add support for builtin image generation tool 2025-05-22 13:12:23 +07:00
github-actions[bot] 8474ca970e Release 0.11.1 (#1961)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-05-20 22:18:57 -07:00
Alex Yang 3703f907d9 fix(parse): upload API (#1960) 2025-05-20 17:39:39 -07:00
github-actions[bot] f63b702bec Release 0.11.0 (#1950)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-05-19 12:23:04 +07:00
Marcus Schiesser ccde88fe0b docs: update azure docs (#1958) 2025-05-19 11:49:18 +07:00
ANKIT VARSHNEY b0cd5301bb remove openai from llamaindex package and remove default setting for llm and embedModel (#1809)
Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-05-19 11:12:57 +07:00
Marcus Schiesser 3e66ddc10d chore: Move Azure models to azure package (#1888) 2025-05-16 15:50:12 +07:00
Marcus Schiesser c719b968f3 Fix: broken links in docs (#1956)
Co-authored-by: Andrew Kostka <apkostka@gmail.com>
2025-05-15 16:49:05 +07:00
Anubhav Rana c73c659c6d chore: qdrant version updates (#1913)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-05-15 12:30:24 +07:00
Marcus Schiesser 361a685012 chore: remove old workflows (#1951) 2025-05-15 10:29:47 +07:00
Marcus Schiesser 680b529e94 chore: remove requireContext from tools (#1949) 2025-05-14 16:38:44 +07:00
github-actions[bot] 389acbd307 Release 0.10.6 (#1942)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-05-13 17:16:55 +07:00
Marcus Schiesser 2e181be160 feat: add xai tools (#1948) 2025-05-13 17:10:57 +07:00
Marcus Schiesser 7a7ca604c5 feat: add xai support (#1947) 2025-05-13 16:48:53 +07:00
Marcus Schiesser c2fd4f9fc1 docs: add docs for concept (#1946) 2025-05-13 16:02:21 +07:00
GiftMungmeeprued 40f5f410c0 fix: enhance loadJson in LlamaParseReader to handle URL inputs correctly (#1936) 2025-05-13 10:10:04 +07:00
Anubhav Rana d671ed6d25 feat: qdrant search params (#1911) 2025-05-13 09:50:23 +07:00
Marcus Schiesser 76c9a80057 chore: make core peer dep (#1941) 2025-05-12 18:08:55 +07:00
operagxsasha 46a416517c docs: added a badge to the social network Twitter (#1943) 2025-05-12 18:05:08 +07:00
Tomer Igal 168d11fe51 feat: update agent input interface to support files (#1938)
Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>
2025-05-12 17:21:46 +07:00
operagxsasha 3dfa5eb9ff docs: edited the link to the license badge (#1939) 2025-05-12 17:10:17 +07:00
Marcus Schiesser 9b20859dc5 docs: reorder examples (#1937) 2025-05-12 14:16:47 +07:00
Thuc Pham 93691793c5 feat: add E2E test for installing packages with npm (#1930) 2025-05-12 11:02:44 +07:00
Marcus Schiesser 3b231cf11c readd old sentence splitter for testing (#1926) 2025-05-10 09:01:22 +07:00
Marcus Schiesser 7073fca171 docs: LlamaParseReader how to use EU (#1931) 2025-05-09 16:45:20 +07:00
Marcus Schiesser 9145577bf5 docs: move live examples (#1928) 2025-05-09 15:02:33 +07:00
github-actions[bot] 4a18a2eb3d Release 0.10.5 (#1922)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-05-09 14:30:39 +07:00
ANKIT VARSHNEY 206b491724 feat: Support for google live api (#1905) 2025-05-09 14:20:40 +07:00
Marcus Schiesser 9b2e25a184 fix: Use Uint8Array instead of Buffer for file type messages (works w… (#1921) 2025-05-08 13:19:59 +07:00
github-actions[bot] b29521bf6c Release @llamaindex/google@0.2.6 (#1918)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-05-07 16:31:58 +07:00
Marcus Schiesser 73e25787e7 feat: add gemini-2.5-pro-preview-05-06 (#1917) 2025-05-07 16:18:21 +07:00
Marcus Schiesser 3ce80540fe docs: add workflows documentation and update installation instruction… (#1916) 2025-05-07 15:22:08 +07:00
Marcus Schiesser dbc1ee3089 docs: update installation instructions for LlamaIndex to include Work… (#1915) 2025-05-07 12:31:48 +07:00
github-actions[bot] 3b45191228 Release 0.10.4 (#1901)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-05-07 11:11:11 +07:00
Marcus Schiesser aaf2f8b2db docs: fix docs for agents (#1914) 2025-05-07 11:03:08 +07:00
Marcus Schiesser 6ddf1c1b1f chore: fixes for workflows before release (#1908) 2025-05-07 09:29:09 +07:00
Marcus Schiesser a8717d5ece chore: ensure pinning workflow version (#1907) 2025-05-06 12:51:13 +07:00
Huu Le 7e8e4549f2 chore: update @llama-flow/core to version 0.4.1 and export stream api (#1906)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-05-05 16:06:44 +07:00
Alex Yang cc3fe92a22 docs: update llama-flow 2025-05-04 02:28:04 -07:00
Alex Yang 63ab0dba4e chore: drop node.js 18 support (#1904) 2025-05-02 11:51:18 -07:00
Alex Yang 2225ffd1d4 feat: bump llama cloud sdk (#1903) 2025-05-01 13:30:52 -07:00
Marcus Schiesser bc5334249b chore: migrate agentworkflows to llama-flow (#1895)
Co-authored-by: leehuwuj <leehuwuj@gmail.com>
2025-04-30 18:14:17 +07:00
Thuc Pham 41953a3ef9 fix: node10 module resolution fail in sub llamaindex packages (#1900) 2025-04-29 17:47:50 +07:00
github-actions[bot] fa66c9ca8e Release 0.10.3 (#1898)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-29 13:05:36 +07:00
Thuc Pham 3ee8c83200 feat: support file content type in message content (#1894) 2025-04-29 12:57:35 +07:00
Peter Goldstein e919bab568 Update Gemini Flash and Gemini Flash Lite model keys to exclude patch version (#1897) 2025-04-29 11:25:01 +07:00
Thuc Pham d28b6b7c4f chore: move server package code to create-llama (#1893) 2025-04-28 14:39:47 +07:00
Marcus Schiesser 1c7a262ff7 chore: stop workflow update (#1892) 2025-04-28 11:46:06 +07:00
Alex Yang 5a1838cc91 fix: remove workflow streaming demo (#1891) 2025-04-24 15:44:55 -07:00
Alex Yang b9805f4899 fix: migrate to llamaflow (#1889) 2025-04-24 15:17:02 -07:00
github-actions[bot] 109ec63779 Release @llamaindex/server@0.1.6 (#1886)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-24 19:40:11 +07:00
Thuc Pham 82d4b46fe4 feat: re-add supports for artifacts (#1869) 2025-04-24 19:28:15 +07:00
Logan f8c2d0b8ad Cleanup remaining workflows docs (#1881) 2025-04-23 16:15:49 -07:00
github-actions[bot] 6d7bc4ccbb Release (#1883)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-23 17:24:54 +07:00
Huu Le 294f502441 feat: support SSE for MCP tools adapter (#1882) 2025-04-23 15:54:37 +07:00
github-actions[bot] 056594452c Release @llamaindex/readers@3.1.0 (#1880)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-22 19:14:09 +07:00
Huu Le 1e59695cef Restructure reader packages (#1877)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-04-22 17:20:08 +07:00
Marcus Schiesser f463efd8a5 docs: fix agentic rag tutorial 2025-04-22 12:13:06 +02:00
Alex Yang cf95af40d9 make docs great again - 2nd time (#1876) 2025-04-21 15:07:16 -07:00
Alex Yang ddc910dc73 docs: no validate links 2025-04-21 12:50:10 -07:00
Alex Yang f12af27760 docs: fix turbo.json 2025-04-21 12:35:31 -07:00
Alex Yang ffdbc8f5e8 docs: disable typedoc 2025-04-21 12:27:08 -07:00
Alex Yang ea8817f7e4 fix(docs): search page id (#1875) 2025-04-21 12:10:42 -07:00
Alex Yang 359698d04b docs: remove links on docs detail page 2025-04-21 09:53:26 -07:00
Huu Le b49fb24948 docs: fix search function on the documentation site is not working. (#1872) 2025-04-21 09:49:48 -07:00
Alex Yang 78841495aa docs: fix meta.json 2025-04-21 09:43:28 -07:00
Alex Yang c81dd21472 chore: bump llama-flow docs 2025-04-21 09:38:14 -07:00
Alex Yang 52868ea0f9 docs: remove llamacloud section (#1851) 2025-04-21 09:37:40 -07:00
Logan e0a730e44e docs: replace with llama-flow docs (#1874)
Co-authored-by: Alex Yang <himself65@outlook.com>
2025-04-21 09:37:27 -07:00
Alex Yang eda486bb52 chore: bump pnpm (#1871) 2025-04-21 09:25:48 -07:00
Alex Yang 10d9c708db ci: enable turbo cache (#1873) 2025-04-21 09:25:38 -07:00
Alex Yang 556027705e chore(docs): fix inputs 2025-04-21 04:13:46 -07:00
github-actions[bot] 588cd0f0b9 Release 0.10.2 (#1861)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-18 17:14:21 +07:00
Huu Le 7ca9ddff86 feat: Add generate UI workflow to server (#1862)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
Co-authored-by: Thuc Pham <51660321+thucpn@users.noreply.github.com>
2025-04-18 16:59:44 +07:00
Thuc Pham 3310eaae29 chore: bump chat-ui 0.4.0 (#1868) 2025-04-18 15:33:08 +07:00
Peter Goldstein 96dac4ddfd feat: Add Gemini 2.5 Flash Preview (#1866) 2025-04-18 15:30:06 +07:00
Logan f9ee683593 docs: remove fake chat (#1867) 2025-04-17 17:14:38 -07:00
Peter Goldstein e5c3f95c6e Update o4-mini to allow reasoning parameters and exclude temperature (#1859) 2025-04-17 13:51:27 +07:00
Thuc Pham b155c8cf2c chore: make llamaindex as peer deps of server (#1860) 2025-04-17 13:50:28 +07:00
github-actions[bot] be6fead71a Release 0.10.1 (#1858)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <14026360+himself65@users.noreply.github.com>
2025-04-16 19:15:34 -07:00
Peter Goldstein 96dd79853a Add o3 and o4-mini models (#1857) 2025-04-16 13:28:39 -07:00
Fuma Nama f49366c9af make docs great again (#1855)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
Co-authored-by: Alex Yang <himself65@outlook.com>
2025-04-16 11:19:25 -07:00
github-actions[bot] cde403be58 Release 0.10.0 (#1854)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-16 17:02:34 +07:00
Parham Saidi e9bf4424e2 fix: update the tool call schema for nova (#1850)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-04-16 16:52:29 +07:00
Thuc Pham edb8b87d86 fix: shadcn components cannot be used in next server (#1853) 2025-04-16 15:57:25 +07:00
Thuc Pham 6cf928f390 chore: use bunchee for llamaindex (#1821) 2025-04-16 15:47:30 +07:00
Alex Yang 8e27fd2009 fix(docs): sha on edit page (#1852) 2025-04-15 23:51:38 -07:00
Alex Yang c84036bbdd fix(doc): use install shortcut (#1849) 2025-04-15 09:08:32 -07:00
github-actions[bot] f43406fc9b Release @llamaindex/community@0.0.95 (#1848)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-04-15 16:00:59 +07:00
Peter Goldstein 411dceaa41 Add Nova Premier model. Add EU endpoints for Nova models (#1841) 2025-04-15 15:48:11 +07:00
Alex Yang 2447384f31 chore: bump fumadocs & next & react (#1845) 2025-04-15 01:20:29 -07:00
github-actions[bot] 5f3eb457e6 Release 0.9.19 (#1844)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-15 00:31:31 -07:00
Peter Goldstein d365eb2e54 Add GPT-4.1 models to OpenAI (#1842) 2025-04-15 09:07:38 +02:00
Thuc Pham bb34ade6d4 feat: support cn utils for server UI (#1843) 2025-04-15 09:06:39 +02:00
github-actions[bot] c540df5069 Release 0.9.18 (#1836)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-14 20:52:09 +07:00
Marcus Schiesser 400b3b54bf feat: use full-source code with import statements for custom comps (#1838)
Co-authored-by: thucpn <thucsh2@gmail.com>
Co-authored-by: Thuc Pham <51660321+thucpn@users.noreply.github.com>
2025-04-14 13:48:21 +02:00
Marcus Schiesser 88b7046c68 chore: Move zod to peer deps (#1837) 2025-04-10 18:17:26 +07:00
Zhanghao 2ffdb274f2 docs: correct the CondenseQuestionChatEngine path (#1834) 2025-04-10 16:07:07 +07:00
github-actions[bot] 139eb050f9 Release @llamaindex/server@0.1.0 (#1835)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-04-10 15:38:40 +07:00
Thuc Pham 3ffee26b77 feat: enhance config params for LlamaIndexServer (#1833) 2025-04-10 15:21:51 +07:00
Marcus Schiesser dc6e774d78 chore: remove deepresearch events (#1831) 2025-04-09 20:45:49 +07:00
github-actions[bot] 6716188e10 Release @llamaindex/server@0.0.9 (#1830)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-04-09 17:44:13 +07:00
Thuc Pham 0b75bd6d92 feat: component dir in llamaindex server (#1828) 2025-04-09 17:25:21 +07:00
github-actions[bot] 045b267d1b Release 0.9.17 (#1823)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <14026360+himself65@users.noreply.github.com>
2025-04-08 17:35:55 -07:00
Alex Yang 41191d074a fix(parse): file input (#1829) 2025-04-08 14:15:07 -07:00
Marcus Schiesser 8b2914c8b7 docs: reorganize modules structure in docs (#1827) 2025-04-08 22:42:00 +07:00
Marcus Schiesser 4c24dfcbce docs: Move framework docs to installation directory and simplify gett… (#1826) 2025-04-07 22:54:12 +07:00
r3rer3 0dfa371fc9 Add "thinking" and "thinking_signature" to chat response, and "thinking_signature" to chat stream (#1825) 2025-04-07 21:57:55 +07:00
Peter Goldstein 0d852d6fdc Add the Gemini 2.5 Pro Preview model (#1822) 2025-04-07 16:08:40 +07:00
ANKIT VARSHNEY 2410527e64 feat: reader for postgres (#1813)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-04-07 15:57:14 +07:00
Marcus Schiesser 7d2be8c640 fix: mcp test 2025-04-07 10:44:54 +02:00
Thuc Pham 3534c373f2 feat: support multi-resolution compatibility (#1816) 2025-04-05 18:41:39 +07:00
github-actions[bot] 2cbdf71669 Release 0.9.16 (#1811)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-04 11:12:27 +02:00
Huu Le ead657aedd feat: add MCP tools integration and example usage (#1819) 2025-04-04 11:03:10 +02:00
Marcus Schiesser f5e4d098b0 chore: remove gpt-tokenizer (#1815) 2025-04-03 14:23:31 +02:00
dependabot[bot] 4d97226e50 chore(deps): bump next from 15.2.3 to 15.2.4 (#1812)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-04-03 13:57:39 +07:00
Marcus Schiesser 4999df18cc chore: bump nextjs to "^15.2.3" (#1810) 2025-04-02 21:24:57 +07:00
github-actions[bot] 9a27b6d94a Release 0.9.15 (#1807)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-02 17:08:47 +07:00
Thuc Pham 8c02684f0f fix: handle error when streaming workflow (#1808) 2025-04-02 16:26:01 +07:00
ANKIT VARSHNEY 9c63f3f94e feat: openai responses api (#1801) 2025-04-02 16:21:43 +07:00
Thuc Pham c515a324f6 feat: return raw output for agent toolcall result (#1806) 2025-04-01 22:20:06 +07:00
github-actions[bot] c70d7b9930 Release 0.9.14 (#1799)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-04-01 12:59:10 +02:00
Marcus Schiesser 1b6f368a3f feat: Support loading from URLs for all readers extending FileReader (#1805) 2025-04-01 17:39:59 +07:00
Thuc Pham 9d951b288f feat: support llamacloud in @llamaindex/server (#1796) 2025-04-01 17:39:39 +07:00
dependabot[bot] 5fe16697a2 chore(deps-dev): bump vite from 5.4.15 to 5.4.16 (#1804)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-04-01 16:49:36 +07:00
Marcus Schiesser 189d8a83ac chore: use node 20 for examples (#1803) 2025-03-31 17:21:19 +07:00
ANKIT VARSHNEY 648cfb5cb5 feat: supbase vector store (#1790) 2025-03-29 15:14:28 +07:00
Marcus Schiesser eaf326ee90 fix: passing right llm setting from SimpleChatEngine to ChatMemoryBuffer (#1798) 2025-03-28 18:20:52 +07:00
github-actions[bot] fc1bedf438 Release (#1794)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-03-28 15:22:44 +07:00
Thuc Pham 164cf7a6df fix: custom next server start fail (#1795) 2025-03-28 15:09:57 +07:00
Zhanghao e98033e2cc docs: correct the number of indexes (#1793) 2025-03-27 16:33:52 +02:00
dependabot[bot] c0ffc7b434 chore(deps-dev): bump vite from 5.4.14 to 5.4.15 (#1787)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-03-26 20:43:49 +07:00
github-actions[bot] 9cf88e9f3f Release 0.9.13 (#1783)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2025-03-26 10:31:29 +02:00
Thuc Pham 75d6e29187 feat: response source nodes in query tool output (#1784) 2025-03-26 15:24:53 +07:00
Parham Saidi 132517877e fix: stringify all tool results for anthropic on bedrock (#1786) 2025-03-25 21:16:44 +07:00
Thuc Pham 299008b34f feat: copy create-llama to @llamaindex/servers (#1780) 2025-03-25 11:55:44 +02:00
Thuc Pham 482ed67690 fix: document deployment fail due to static generation timed out (#1779) 2025-03-24 11:12:09 +02:00
github-actions[bot] 9aeec9089b Release 0.9.12 (#1744)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-03-24 14:34:45 +07:00
Daniel Bank f1db9b3d48 feat: vercel tool response fields options (#1765) 2025-03-24 14:25:26 +07:00
ANKIT VARSHNEY 25093531cf feat: elastic search vector store (#1777) 2025-03-24 14:18:42 +07:00
Thuc Pham f8a86e4eff feat: @llamaindex/server (#1759) 2025-03-21 19:14:19 +07:00
ANKIT VARSHNEY 04f8c96caa feat: add support for mongodb document store (#1771) 2025-03-21 16:16:49 +07:00
Jorge Luis Middleton 43053f9e16 Update qdrant.mdx documentation (#1770) 2025-03-21 10:06:25 +02:00
Parham Saidi 93bc0ffd21 fix: context engine additional options not being passed (#1772) 2025-03-21 01:49:43 +07:00
Huu Le 58a9446220 Fix wrong multi-agent setup (#1767) 2025-03-20 14:55:25 +03:00
Parham Saidi da06e4550b fix: include inline data check for GoogleStudio (#1769) 2025-03-20 14:50:47 +03:00
Parham Saidi 3fd4cc383e feat: google multimodal output using their new gen ai library (#1762) 2025-03-19 21:43:39 +02:00
ANKIT VARSHNEY 2b39ceffa6 docs: doc for structured output (#1761) 2025-03-19 14:15:11 +07:00
Thuc Pham 77e24cec65 fix: crypto is not defined when running on node18 (#1763) 2025-03-19 08:38:16 +02:00
ANKIT VARSHNEY 2a0a899d66 chore: added saftey setting as parameter for gemini (#1760) 2025-03-18 23:05:47 +07:00
ANKIT VARSHNEY 050cd53450 fix: delete by id in pinecone vector store (#1758) 2025-03-18 23:03:42 +07:00
George He 5189b446f4 fix: add retry handling logic to parser reader and fix lint issues (#1757)
Co-authored-by: Alex Yang <himself65@outlook.com>
2025-03-17 14:50:38 -07:00
Thuc Pham c7ff3233fe feat: @llamaindex/tools (#1755) 2025-03-17 21:20:24 +07:00
Jack Qian 21bebfcaa6 docs: add missing links (#1754) 2025-03-16 13:32:19 +07:00
ANKIT VARSHNEY 91a18e7057 feat: add support for structured output with zod schema. (#1749) 2025-03-16 11:58:28 +08:00
ANKIT VARSHNEY d1c1f99e06 feat: function calling support in mistral provider (#1756) 2025-03-15 12:18:36 +07:00
Marcus Schiesser 8be84aeb5e chore: add gemini streaming example (#782) 2025-03-14 09:25:09 +07:00
Thuc Pham 5b7b314b25 fix: unhandled server error when accessing not found pages (#1753) 2025-03-13 18:31:55 +07:00
Marcus Schiesser 4a51c9b48e docs: add link checker and fix links (#1750) 2025-03-13 15:46:05 +07:00
Alex Yang bf56fc08ad chore(cloud): update openapi.json (#1746) 2025-03-12 15:19:40 +00:00
Marcus Schiesser fa40b36516 docs: cleanup (#1745) 2025-03-12 17:54:20 +07:00
yangqiao da8068e9e0 fix: Add fromConnectionString method for Azure vCore storages (#1743)
Co-authored-by: yangqiao <yangqiao@microsoft.com>
2025-03-12 15:58:30 +07:00
github-actions[bot] 37dcf37625 Release 0.9.11 (#1734)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-03-12 12:44:55 +07:00
Stefan Edberg a8c0637d11 feat: make it possible to provide base URL to OpenAI (#1740)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-03-12 12:17:38 +07:00
Marcus Schiesser 387a19284d fix: Update mistral package for mistral API 1.5.1 (#1741) 2025-03-12 11:23:42 +07:00
ANKIT VARSHNEY a654f580cf docs: add doc for perplexity (#1738) 2025-03-12 11:17:23 +07:00
Thuc Pham 68ea7ec6a5 chore: use agent workflow for examples (#1726) 2025-03-11 19:05:00 +07:00
Marcus Schiesser 2d11ffbaea docs: update contrib (#1736) 2025-03-11 18:06:06 +07:00
ANKIT VARSHNEY 1587e48a14 Feat/perplexity (#1719) 2025-03-11 17:21:57 +07:00
Marcus Schiesser bd239aaf2d docs: update main agent docs (#1735) 2025-03-11 17:18:38 +07:00
Jack Qian 98eebf7277 feat: add request options for gemini (#1733) 2025-03-11 15:56:10 +07:00
github-actions[bot] 5478ba88b1 Release 0.9.10 (#1728)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-03-11 13:47:43 +07:00
Marcus Schiesser aea550aff4 feat: Add factory convenience factory for each LLM provider, e.g. you… (#1731) 2025-03-11 13:42:09 +07:00
Marcus Schiesser e66c6e25fb feat: add tool factory method (#1730) 2025-03-11 12:57:13 +07:00
Marcus Schiesser 40ee7610b2 feat: add asQueryTool to index and add factory methods for simplifying agent usage (#1715) 2025-03-11 11:06:21 +07:00
yangqiao c14a21bc0b fix: Add user agent for AzureCosmosDBMongoDBVectorStore (#1729)
Co-authored-by: yangqiao <yangqiao@microsoft.com>
2025-03-10 18:08:28 +07:00
Thomas Vanier 33f98565ab fix: google start chat tools params (#1716)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-03-10 18:07:36 +07:00
Huu Le b5cb35a732 chore: add unit test for agent workflow (#1704) 2025-03-10 16:44:49 +07:00
Thuc Pham c1b5be5182 feat: make AgentWorkflow llm param optional (#1727) 2025-03-10 11:48:51 +07:00
Alex Yang 6f8b68ac5f chore: fix turbo.json (#1724) 2025-03-09 01:45:28 -08:00
Alex Yang e075643b50 chore: bump bunchee (#1725) 2025-03-09 01:33:33 -08:00
Alex Yang f71b143ceb chore: add tailwindcss prettier (#1723) 2025-03-09 01:11:27 -08:00
Alex Yang ead4a80a3a feat(docs): improve misc (#1722) 2025-03-09 00:57:47 -08:00
Alex Yang da78689e24 fix(docs): use docs.toFumadocsSource (#1721) 2025-03-09 00:34:49 -08:00
Alex Yang f24a9dfe00 fix(docs): openapi generation & twoslash fix (#1720) 2025-03-09 00:02:30 -08:00
Alex Yang e31d6ba472 fix(docs): development error 2025-03-08 21:51:43 -08:00
Alex Yang d212240d64 feat: use fumadoc 15 + tailwind 4 (#1690)
Co-authored-by: thucpn <thucsh2@gmail.com>
2025-03-07 23:30:54 -08:00
github-actions[bot] cb73f77bb8 Release 0.9.9 (#1713)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-03-07 16:28:36 +07:00
Huu Le 8bf1ca1701 Support chat stream with tools for Anthropic LLM (#1710)
Co-authored-by: thucpn <thucsh2@gmail.com>
Co-authored-by: Thuc Pham <51660321+thucpn@users.noreply.github.com>
2025-03-07 15:41:15 +07:00
Alexander Tigselema 58b3ee52e0 Add Gemini 2.0 Flas Lite, Fix tools error with LLM Agent (#1712) 2025-03-07 11:15:51 +07:00
Thomas Vanier 4bac71d6a2 feat: additional tool argument (#1693) 2025-03-07 11:15:10 +07:00
github-actions[bot] a3cbcb31a2 Release 0.9.8 (#1711)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-03-06 16:33:19 +07:00
Thuc Pham bbc8c8787d fix: prefer using embedding model from vector store (#1708) 2025-03-06 16:24:05 +07:00
Huu Le 4b49428f57 fix agent workflow tool call for Ollama (#1706)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-03-06 11:13:42 +07:00
Peter Goldstein 7ee4968b06 Add Gemini 2.0 Pro Experimental (#1707) 2025-03-06 11:04:56 +07:00
github-actions[bot] 0111f5c8b0 Release 0.9.7 (#1703)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-03-05 16:59:05 +07:00
Thuc Pham beb922b743 fix: build fail in edge runtime (#1705)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-03-05 16:35:00 +07:00
patryktop e28c29d1f5 feat: add Llama 3.3 70B Instruct to community package (#1702) 2025-03-04 17:27:35 -08:00
github-actions[bot] 008cccd9f1 Release 0.9.6 (#1698) 2025-03-04 17:33:18 +07:00
Huu Le 081698d68c chore: simplify imports of agent workflow (#1700) 2025-03-04 17:01:29 +07:00
Huu Le ab5fe5d7a0 chore: remove core import in document (#1699) 2025-03-04 16:14:31 +07:00
Huu Le 56689707d3 feat: Support AgentWorkflow (#1685)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-03-04 16:05:25 +07:00
Brian Lange fd74ba4bf1 fix: Voyage typescript configs + docs (#1696) 2025-03-04 11:00:05 +07:00
github-actions[bot] b2634e47ca Release 0.9.5 (#1694)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-02-28 18:18:14 +07:00
Thuc Pham ad3c7f1ec1 fix: streaming issues with LLMAgent (#1692) 2025-02-28 18:13:36 +07:00
Alex Yang 335f2df626 chore: fix lock file 2025-02-27 12:31:11 -08:00
github-actions[bot] ee963644bf Release 0.9.4 (#1689)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-02-27 12:28:48 -08:00
Alex Yang cb256f24ae feat: support gpt-4.5 (#1688) 2025-02-27 12:24:33 -08:00
Alex Yang 1ccc04ecb5 chore: fix changeset 2025-02-27 12:17:12 -08:00
Brian Lange 034639153b feat: Voyage embeddings (#1574)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-02-27 10:22:33 +07:00
patryktop 1914b52708 feat: add Claude 3.7 Sonnet model to community package (#1683) 2025-02-26 14:38:14 -08:00
Alex Yang cb021e7196 feat(node-parser): support async function (#1682) 2025-02-26 08:59:51 -08:00
ratacat c2aa836b35 docs: upgrade remote ollama embeddings (#1680) 2025-02-25 11:39:16 -08:00
github-actions[bot] 3b0f55f1ea Release 0.9.3 (#1676)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-02-25 16:53:30 +07:00
Marcus Schiesser a9c6144eec feat: stream thinking tokens for claude 3.7 (#1679) 2025-02-25 16:48:12 +07:00
Marcus Schiesser 3564244ced chore: add claude 3.7 support (#1678) 2025-02-25 15:18:45 +07:00
Gunnar Holwerda d952e68ec4 Fix refine synthesizer empty source nodes behavior (#1677) 2025-02-24 10:56:21 +07:00
Tushar Sonawane 5c026e839f feat(vectorstore): adds firestore vector store support (#1600) 2025-02-21 16:23:50 +07:00
github-actions[bot] 9c1c5b4d50 Release 0.9.2 (#1673)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-02-21 10:57:11 +07:00
Thuc Pham c902fcbc33 chore: bump llamacloud openapi (#1674) 2025-02-20 17:47:41 +07:00
Thuc Pham 88d776f392 fix: enhance error message in llamacloud (#1672) 2025-02-20 16:33:34 +07:00
github-actions[bot] 6fcc6bcb84 Release @llamaindex/anthropic@0.1.2 (#1671)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-02-20 12:56:33 +07:00
Thuc Pham be74207945 fix: dont add empty text block to tool call (#1670) 2025-02-20 12:47:43 +07:00
Alex Yang 6be223dfad chore: bump version (#1668) 2025-02-19 19:28:12 +08:00
Alex Yang 4cbfdb5f5c ci: only run in pull request (#1669) 2025-02-19 19:11:53 +08:00
github-actions[bot] 9767d1c004 Release 0.9.1 (#1664)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <14026360+himself65@users.noreply.github.com>
2025-02-19 18:15:41 +08:00
Alex Yang e831b28627 ci: add size limit check (#1667) 2025-02-19 18:05:28 +08:00
Alex Yang cc50c9c2d4 chore: trigger env package release 2025-02-19 17:59:38 +08:00
Thuc Pham 954140776e fix: missing document entrypoints (#1663)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-02-14 17:06:23 +07:00
Savas Ziplies 6d37d440a6 refactor(agent): changed regex for tool use extraction to look for optional "Input:" prefix to comply with Cohere command-r models (#1654) 2025-02-14 15:17:03 +07:00
Alex Yang e724f7e9f2 fix: cjs module resolve esm module unexpectedly (#1662) 2025-02-14 15:52:37 +08:00
Alex Yang 1b029ae525 test: add cjs smoke test (#1660) 2025-02-14 14:28:09 +08:00
Marcus Schiesser d1db2189c9 docs: update starter to ask for api key (#1661) 2025-02-14 12:14:51 +07:00
Alex Yang 2c5b4030c9 chore: bump bunchee (#1645) 2025-02-14 09:41:32 +08:00
Alex Yang 96eb597059 fix: bundler issue default in default (#1653) 2025-02-14 09:20:39 +08:00
Marcus Schiesser 04098d55ff chore: fix pnpm lock (#1658) 2025-02-13 17:49:21 +07:00
Marcus Schiesser 335a6b9e88 chore: add pathe to examples (#1657) 2025-02-13 17:44:30 +07:00
github-actions[bot] c2a345ebb1 Release 0.9.0 (#1643)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-02-13 17:34:06 +07:00
Marcus Schiesser d3fa729a30 Cleanups before 0.9 release (#1656) 2025-02-13 17:26:22 +07:00
Thuc Pham c7c08005ec fix: fumadoc build fail (#1655) 2025-02-13 16:24:28 +07:00
Alex Yang bb0ae5e321 chore: fix pkg.pr.new issue (#1651) 2025-02-12 21:19:29 +08:00
Marcus Schiesser f4588bc770 chore: Remove readers package from llamaindex (#1649) 2025-02-12 17:16:41 +07:00
Marcus Schiesser b49037612d remove service context (#1618)
Co-authored-by: thucpn <thucsh2@gmail.com>
2025-02-12 15:10:11 +07:00
Thuc Pham a87efb91a4 docs: update chat engine docs (#1648) 2025-02-12 12:45:26 +07:00
Thuc Pham 6a4a73760b chore: remove re-exporting packages in llamaindex (#1624)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-02-12 12:44:52 +07:00
Alex Yang 1564831158 ci: fix pkg-pr-new release (#1646) 2025-02-11 22:42:42 +08:00
Alex Yang 4d94f6e50d test: smoke test with cjs/esm dual package (#1644) 2025-02-11 15:02:06 +08:00
Thuc Pham 7bd5d9340c docs: update workflow doc (#1637)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-02-11 13:41:11 +07:00
Thuc Pham d924c63162 feat: asChatEngine function for index (#1640) 2025-02-11 12:57:15 +07:00
github-actions[bot] 83cff1277c Release 0.8.37 (#1642)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-02-11 12:48:58 +07:00
Marcus Schiesser 1c908fd852 Revert "fix: bundle output incorrect (#1638)" (#1641) 2025-02-11 12:27:11 +07:00
github-actions[bot] 56f367f08d Release 0.8.36 (#1639)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <14026360+himself65@users.noreply.github.com>
2025-02-10 21:49:19 +08:00
Alex Yang cb608b5d01 fix: bundle output incorrect (#1638) 2025-02-10 21:30:36 +08:00
github-actions[bot] bd55bcffff Release 0.8.35 (#1633)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-02-10 16:45:42 +07:00
Thuc Pham 6d4d96f8fe chore: update import to workspace pages for examples and docs (#1626)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-02-10 15:43:29 +07:00
Thuc Pham b6ea2bf964 fix(gemini): use function role for message contains tool-result (#1634) 2025-02-10 12:57:45 +07:00
Parham Saidi 15563a0f70 fix: delete temp competely from params when calling openai o3 (#1629) 2025-02-10 11:07:21 +07:00
github-actions[bot] bd940d1d43 Release 0.8.34 (#1630)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-02-07 16:02:27 +07:00
Thuc Pham 9f8ad37b79 fix: missing peer deps in llamaindex (#1631) 2025-02-07 15:06:41 +07:00
Peter Goldstein 7265f74c24 Add reasoning_effort for o1 and o3 (#1628) 2025-02-07 12:01:48 +07:00
github-actions[bot] e3f1b85846 Release 0.8.33 (#1619)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-02-06 15:53:47 +07:00
Peter Goldstein e38e474f86 Add Gemini 2.0 models (#1625) 2025-02-06 15:41:20 +07:00
Parham Saidi 2019a041f7 fix: o3 calls do not support temperature param (#1622) 2025-02-06 10:23:23 +07:00
Thuc Pham 067a4894fe fix: missing condition to stringify tool input (#1620) 2025-02-05 17:25:37 +07:00
clean99 21769c8ad9 Fix: update deprecated response property in examples (#1614)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-02-05 11:28:32 +07:00
github-actions[bot] 89ea1e1d31 Release 0.8.32 (#1595)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <17126+marcusschiesser@users.noreply.github.com>
2025-02-04 12:23:47 +07:00
siquick d9bbaf95f3 chore: updated docs and examples to use correct PGVectorStore imports (#1611)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-02-04 11:18:39 +07:00
Marcus Schiesser 8744796c06 update the versioon of chromadb client (#1616)
Co-authored-by: my8bit <mail@my8bit.name>
2025-02-04 10:58:04 +07:00
Ihor Pavlenko f02621e379 fix: doc links (#1610) 2025-02-04 10:46:04 +07:00
Peter Goldstein 1892e1ce1d Add O3 mini model (#1612) 2025-02-04 10:34:22 +07:00
dependabot[bot] d90d8959a5 chore(deps-dev): bump vite from 5.4.11 to 5.4.12 (#1604)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-02-04 10:33:18 +07:00
Thuc Pham 4df1fe6cca chore: migrate llamaindex llms and embeddings to their own packages (#1615) 2025-02-03 17:32:19 +07:00
Thuc Pham 34faf4821a chore: move vector stores to their own packages (#1605) 2025-01-24 12:45:13 +07:00
Marcus Schiesser b24ffc6174 fix: pinecone import (#1603) 2025-01-21 12:32:05 +07:00
Thuc Pham 82e25c924c fix: remove ignore package from changeset (#1602) 2025-01-21 12:28:39 +07:00
Thuc Pham 1931bbca74 chore: move azure code to own @llamaindex/azure package (#1601) 2025-01-21 12:14:17 +07:00
Thuc Pham 94566169fb chore: move postgres storage classes to @llamaindex/postgres (#1597) 2025-01-20 12:24:44 +07:00
Alex Yang d6c270ec7a feat(cloud): support pass project and org id to llama parse reader (#1594) 2025-01-08 11:23:48 -08:00
github-actions[bot] e3a77044d5 Release 0.8.31 (#1579)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2025-01-08 10:42:19 -08:00
Alex Yang fd9c8294e1 chore: bump llamacloud openapi (#1592) 2025-01-06 23:12:41 -08:00
Thuc Pham 0ebbfc1031 fix: clean up docstore when generating embedding fail (#1588)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2025-01-07 11:58:09 +07:00
Alex Yang 5dec9f912a chore: bump sdk deps (#1591) 2025-01-06 17:03:15 -08:00
Alex Yang 1f53819b64 chore: bump version (#1583) 2025-01-02 07:43:17 -08:00
Erik d211b7ab13 add tool call history support in chat messages (#1565) 2024-12-22 19:09:38 -08:00
Thuc Pham 057ee146bd fix: add start command for stackblitz (#1577) 2024-12-20 23:55:33 -08:00
Thuc Pham 4a831b192c fix: docs migration issues (#1576) 2024-12-20 16:42:54 +07:00
Thuc Pham cf29ca1bf8 [WIP] feat: remove legacy docs (#1571) 2024-12-20 15:12:01 +07:00
Wassim Chegham 09b933f8da feat: add Azure AI Vector Search (#1485) 2024-12-18 11:26:53 -06:00
Thuc Pham 44c0734106 feat: migrate legacy docs (#1568) 2024-12-18 02:18:47 -08:00
github-actions[bot] a7023b4a93 Release 0.8.30 (#1570)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-12-16 11:40:25 -08:00
Alex Yang 012495b5ba chore: bump llamacloud sdk (#1569) 2024-12-16 11:10:09 -08:00
github-actions[bot] a8afb9a7a7 Release 0.8.29 (#1566)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-12-13 19:19:03 -08:00
Peter Goldstein dd596a0cf2 Add Gemini Flash 2.0 Experimental (#1563) 2024-12-13 12:10:46 -08:00
Alex Yang 9e648a0b4f chore: bump version (#1562) 2024-12-11 12:56:38 -08:00
github-actions[bot] bbb87f42ed Release 0.8.28 (#1559)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-12-11 12:09:46 -08:00
Parham Saidi 24caf93efe fix: added inference profile mapping for nova models (#1560) 2024-12-11 11:17:40 -08:00
Thuc Pham a9b5b993fa feat: build api reference pages for new documentation site (#1551) 2024-12-11 09:21:21 -08:00
github-actions[bot] f369d3de4f Release 0.8.27 (#1545)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-12-11 12:18:21 +07:00
Parham Saidi c1850ee370 feat: Amazon Nova support via Bedrock (#1548) 2024-12-10 18:56:35 -08:00
Marcus Schiesser 086a65141d Add adapter to use Vercel model providers (#1558)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-12-09 21:02:57 -08:00
Qwertic d99d598491 Update typescript.mdx (#1557) 2024-12-09 19:52:15 -08:00
Gunnar Holwerda a0e6f57d9b Pass options through to userWebpack in withLlamaIndex (#1550) 2024-12-09 19:51:52 -08:00
Gunnar Holwerda e0f6cc3be1 fix: return actual source nodes with compact and refine response synt… (#1554) 2024-12-09 11:00:12 -08:00
Jingyi Zhao 8386510d86 chore: add e2e working example for ingestion (#1543) 2024-12-04 17:36:00 -08:00
Marcus Schiesser b504303c66 fix: allow Node 18 again to make Stackblitz work (#1544) 2024-12-03 20:57:20 -08:00
Marcus Schiesser cf9a9356e0 fix: discord link (#1542) 2024-12-03 11:16:02 +07:00
github-actions[bot] 335020e242 Release 0.8.26 (#1541)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-12-02 12:23:57 -08:00
Alex Yang 3d1808b5d2 chore: bump version (#1540) 2024-12-02 12:18:51 -08:00
Alex Yang a19cbc7fe0 ci: fix (#1539) 2024-12-02 10:33:44 -08:00
github-actions[bot] b8f0cbc4e0 Release 0.8.25 (#1536)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <marcusschiesser@users.noreply.github.com>
2024-12-02 03:02:36 -08:00
Marcus Schiesser 7e8230b056 fix: release missing readers package (#1537) 2024-12-02 17:54:22 +07:00
Alex Yang 8be45899a7 chore: bump version 2024-12-02 02:21:13 -08:00
github-actions[bot] c4800bcf82 Release @llamaindex/vercel@0.0.2 (#1535) 2024-12-02 14:19:40 +07:00
Thuc Pham fd38a253b7 feat: add vercel chat example (#1532)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-12-02 13:56:28 +07:00
github-actions[bot] 510191cb5d Release 0.8.24 (#1531)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-30 06:05:47 -08:00
Jingyi Zhao 7934ade092 fix: add obsidian reader to index (#1533) 2024-11-30 01:29:45 -08:00
Jingyi Zhao a6c1eab762 feat: data connector for obsidian note taking app (#1529) 2024-11-29 22:39:59 -08:00
crisjy 515f2c1e3d feat: add AzureCosmosDBMongoVectorStore (#1528) 2024-11-28 17:53:09 -08:00
github-actions[bot] dc85649ead Release 0.8.23 (#1526)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-26 17:41:29 -08:00
Alex Yang d2b2722a30 fix: switch tokenizer in cloudflare (#1525) 2024-11-26 15:42:20 -08:00
github-actions[bot] a2bbd62399 Release 0.8.22 (#1520)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-21 23:17:45 -08:00
Alex Yang 969365ca0a feat: add cloudflare worker full example (#1521) 2024-11-21 23:05:40 -08:00
fatmelon 819af453d6 feat: add Azure CosmosDB Mongo vCore Chat store (#1516)
Co-authored-by: root <root@CPC-yangq-FRSGK>
2024-11-21 21:25:41 -08:00
github-actions[bot] 9db36f7384 Release 0.8.21 (#1513)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-19 18:18:35 -08:00
fatmelon efa221116f feat: integrate with azure cosmos db mongo vCore (#1500)
Co-authored-by: root <root@CPC-yangq-FRSGK>
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-19 17:58:25 -08:00
Alex Yang 83c3897539 fix: pinecone vector store (#1512) 2024-11-19 17:51:45 -08:00
github-actions[bot] e1cbce1f80 Release 0.8.20 (#1511)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-19 10:01:18 -08:00
Madarco 02b22da384 fix: supports vercel bundling (#1509)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-19 09:52:56 -08:00
github-actions[bot] 0aa61db547 Release 0.8.19 (#1507)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-19 00:01:48 -08:00
Alex Yang 90d265cf47 chore: bump version (#1505) 2024-11-18 18:39:13 -08:00
github-actions[bot] fc2d5ea1cd Release 0.8.18 (#1506)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-18 13:08:32 -08:00
Thuc Pham ef4f63d9f4 refactor: move mockLLM to core (#1493)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-18 11:39:46 -08:00
Thuc Pham d17450fdfb fix: next.js 15 compatibility (#1474)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-18 11:34:05 -08:00
github-actions[bot] 805d2b0d55 Release 0.8.17 (#1504)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-18 10:28:15 -08:00
Marcus Schiesser 6d22fa2a50 feat: Get PromptTemplate template variables at run-time (#1502) 2024-11-18 09:34:26 -08:00
Aman Rao 16f0068175 chore: update azure cosmos db no sql vector store (#1503) 2024-11-18 09:33:20 -08:00
github-actions[bot] 1054c3382a Release 0.8.16 (#1499)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-17 22:28:02 -08:00
Alex Yang e60328b086 fix: import error in cjs (#1498) 2024-11-17 22:24:09 -08:00
Laurie Voss 3371dfb89f Syncing footer to match main site (#1496) 2024-11-16 00:43:44 -08:00
github-actions[bot] 2065a16a07 Release 0.8.15 (#1494)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-15 11:27:52 -08:00
Wassim Chegham 5dae534f8d fix: propagate queryStr to concrete vectorStore (#1495)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-15 11:16:32 -08:00
Aman Rao 3d503cb810 chore: update azure cosmos db (#1484)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-15 00:55:32 -08:00
Thuc Pham daf8522bec feat: use mock llm (#1492) 2024-11-15 14:50:49 +08:00
github-actions[bot] 223f3136b4 Release 0.8.14 (#1491)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-14 21:49:37 -08:00
Thuc Pham c6bad7d951 docs(next): chat UI with rsc example (#1481)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-11-14 21:33:30 -08:00
Aman Rao 630b425545 feat: add Azure CosmosDB NoSql Chat store (#1490)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-14 21:30:55 -08:00
github-actions[bot] 4c7b891446 Release 0.8.13 (#1480)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-11-14 18:25:19 -08:00
Alex Yang a9c5b4899b docs: update docusaurus.config.js (#1489) 2024-11-14 17:36:52 -08:00
Alex Yang a7b0ac3cb7 feat(anthropic): support prompt caching (#1488) 2024-11-14 17:35:21 -08:00
Alex Yang a7540ff47b docs: update (#1486) 2024-11-14 15:46:48 -08:00
Aman Rao c69605f406 feat: add async support to BaseChatStore and BaseChatStoreMemory (#1483)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-14 13:45:50 -08:00
Alex Yang ee20c44d9b feat(workflow): allow send event with no output (#1479) 2024-11-14 00:17:53 -08:00
Alex Yang 1d470363df docs: add banner for legacy (#1478) 2024-11-13 18:16:13 -08:00
github-actions[bot] b39f40dbd8 Release (#1477)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-11-13 01:25:40 -08:00
Alex Yang fadc8b8ea0 feat: recoverable data with error handling (#1476) 2024-11-13 01:15:50 -08:00
Alex Yang ea92b6986d chore: update changeset 2024-11-13 01:15:28 -08:00
Alex Yang 17f9022d22 fix: output event check (#1475) 2024-11-13 00:46:35 -08:00
github-actions[bot] 14792cd8b4 Release 0.8.12 (#1473)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-12 16:20:25 -08:00
Alex Yang 7ae6eaa0a2 chore: update changeset 2024-11-12 12:49:17 -08:00
Alex Yang dbb5bd9f23 feat: allow tool_choice for OpenAIAgent (#1472) 2024-11-12 12:46:57 -08:00
github-actions[bot] aacd606204 Release 0.8.11 (#1471)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-12 11:49:22 -08:00
Alex Yang f865c984d3 feat: async get message on chat store (#1470) 2024-11-12 10:59:44 -08:00
github-actions[bot] 7b10882d06 Release 0.8.10 (#1466)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-11-11 14:19:46 -08:00
Alex Yang f066e50482 feat: vllm support (#1468) 2024-11-11 13:14:08 -08:00
Alex Yang fd8c882792 refactor: migrate example to new workflow API (#1467) 2024-11-11 12:03:38 -08:00
Alex Yang d89ebe0261 chore: update changeset 2024-11-11 10:11:04 -08:00
Alex Yang 968feb32cd feat: better input type for function tool with zod (#1464) 2024-11-11 10:10:03 -08:00
Alex Yang 43f6f56c5b docs(next): fix turbo.json (#1465) 2024-11-11 10:07:12 -08:00
github-actions[bot] b2364dc5ba Release 0.8.9 (#1460)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-10 23:32:41 -08:00
Alex Yang 67f4db8501 fix: steaming chat in ollama (#1463) 2024-11-10 23:27:09 -08:00
Alex Yang e4151a8b02 feat: support ollama agent (#1462) 2024-11-10 22:38:40 -08:00
Alex Yang 4d4cd8ac6b feat: support ollama tool call (#1461) 2024-11-10 20:46:46 -08:00
Alex Yang 4fc001c8de chore: bump @huggingface/transformers (#1459) 2024-11-10 20:14:44 -08:00
Alex Yang cf675bdc7a chore: bump version (#1458) 2024-11-10 16:43:45 -08:00
github-actions[bot] 660b831b9e Release 0.8.8 (#1457)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-11-08 23:56:46 -08:00
Alex Yang ad85bd0b46 fix: agent streaming final message & async local storage (#1456) 2024-11-08 22:54:13 -08:00
Alex Yang 18ec1f2f61 chore: separate tokenizers (#1454) 2024-11-08 18:53:05 -08:00
Alex Yang b0fbd8b5c8 docs: update CONTRIBUTING.md (#1455) 2024-11-08 18:38:26 -08:00
github-actions[bot] c0dfc8c641 Release 0.8.7 (#1453)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-08 17:57:02 -08:00
Alex Yang a8d3fa68a1 fix: exports in package.json (#1452) 2024-11-08 16:51:21 -08:00
github-actions[bot] f9470c470a Release 0.8.6 (#1450)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-08 14:57:13 -08:00
Alex Yang 95a5cc6ee1 refactor: move storage into core (#1451) 2024-11-08 14:29:08 -08:00
Peter Goldstein 487782cd98 fix: add missing inference endpoints for the Haiku 3.5 models (#1448) 2024-11-07 20:12:34 -08:00
Alex Yang 58e65d399e refactor: move e2e top level (#1449) 2024-11-07 20:11:15 -08:00
github-actions[bot] fdad3d66ac Release 0.8.5 (#1446)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-07 15:57:54 -08:00
Rozstone a6db5dd29b feat: add baseUrl and timeout option in cohere rerank (#1445)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-07 15:13:13 -08:00
Laurie Voss 7b684c4480 docs: home page tweaks (#1447) 2024-11-07 15:12:54 -08:00
Alex Yang c66868a98a chore: fix turbo cache 2024-11-07 15:05:41 -08:00
Alex Yang 14cc9ebe59 chore: move multi-model into single sub module (#1443) 2024-11-07 15:01:17 -08:00
Aman Rao 396b1e1474 feat: integrate with azure cosmos db (#1444)
Co-authored-by: Wassim Chegham <github@wassim.dev>
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-07 14:43:19 -08:00
github-actions[bot] 69f3095424 Release (#1438)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-07 14:30:26 -08:00
Alex Yang dc8bd5ea92 chore: delete .changeset/fresh-dancers-refuse.md 2024-11-07 09:49:54 -08:00
Marcus Schiesser 4af9a77d8b feat: add example using chat-ui components to docs (#1436)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-07 09:44:47 -08:00
Alex Yang 9c1d094455 docs: fix upload llamacloud script 2024-11-07 09:35:30 -08:00
Alex Yang 0a8e3fdbcd docs(next): fix build (#1441) 2024-11-06 15:23:42 -08:00
Alex Yang 1c0e0e1e1d chore: bump version (#1439) 2024-11-06 10:16:18 -08:00
Parham Saidi 47a7c3ea15 feat: added Haiku 3.5 support via Bedrock (#1437) 2024-11-05 13:03:10 -08:00
Alex Yang 898cff0d6a chore: bump pnpm (#1435) 2024-11-04 20:50:15 -08:00
Alex Yang 9df37edef4 fix: remove usage of pnpx (#1434) 2024-11-04 20:38:08 -08:00
github-actions[bot] f86a7a4fa3 Release 0.8.4 (#1432)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-04 14:51:57 -08:00
Aman Rao 35430d3609 feat: add AzureCosmosDBNoSqlVectorStore and SimpleCosmosDBReader (#1331)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-11-04 13:39:39 -08:00
Alex Yang 3c162b2b4a docs: direct to legacy docs (#1431) 2024-11-04 09:54:54 -08:00
github-actions[bot] 5bb4531245 Release 0.8.3 (#1427)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-11-02 19:05:28 -07:00
Alex Yang 2ff0a89891 fix: expose @llamaindex/node-parser (#1426) 2024-11-02 18:57:05 -07:00
Alex Yang d57917d782 feat: add code splitter and html node parser (#1425) 2024-11-02 15:14:03 -07:00
github-actions[bot] f231e0739f Release (#1424)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-11-01 16:50:36 -07:00
Alex Yang 0765742ef3 feat: revamped workflow (#1422) 2024-11-01 15:59:19 -07:00
github-actions[bot] ec7fd6be5c Release 0.8.2 (#1421)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-31 23:54:40 -07:00
Thuc Pham c7a918c3f5 fix: export postprocessors in core (#1419) 2024-10-31 23:40:37 -07:00
Marcus Schiesser 00e681d43b ci: run type-check for reader examples 2024-11-01 12:52:06 +07:00
Alex Yang c01502fb84 docs: update document (#1418) 2024-10-31 14:02:31 -07:00
github-actions[bot] 075f88dbc3 Release 0.8.1 (#1415)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-31 11:57:26 -07:00
Alex Yang cc47ee0602 docs: update README.md (#1416) 2024-10-31 11:56:54 -07:00
Alex Yang 5e6ef55a5a chore: drop nodejs 18 support (#1414) 2024-10-31 11:23:29 -07:00
Alex Yang 9c73f0a530 fix(core): async local storage in Setting.with API (#1413) 2024-10-31 11:06:14 -07:00
Alex Yang 52a4d2b83d chore: bump to eslint 9 (#1410) 2024-10-30 18:34:17 -07:00
Alex Yang 0fd78d5434 docs(next): fix update llamacloud (#1409) 2024-10-29 21:47:21 -07:00
github-actions[bot] 5c4f4a8d83 Release 0.8.0 (#1397)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-10-27 20:36:08 -05:00
Alex Yang 620c63cd19 feat: add @llamaindex/readers package (#1404) 2024-10-27 20:28:55 -05:00
Alex Yang cb51ad90ea docs(next): update document (#1402) 2024-10-27 13:44:55 -05:00
Alex Yang 359fd33041 refactor(core): move ContextChatEngine and SimpleChatEngine (#1401) 2024-10-27 00:39:03 -05:00
Alex Yang efb7e1b868 docs(next): ask ai using llamacloud (#1400) 2024-10-27 00:01:55 -05:00
Erik 98ba1e71bd feat: implement context-aware agent functionality. (#1394)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-10-26 09:23:10 -05:00
Alex Yang fd4b09d375 docs(next): fix shiki theme (#1395) 2024-10-26 08:19:50 -05:00
Alex Yang 7c90e1b6b4 docs(next): update homepage & init setup toturial (#1386) 2024-10-25 18:52:09 -05:00
github-actions[bot] 21ba0a80d1 Release 0.7.10 (#1392)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-10-24 17:43:00 -07:00
Alex Yang 9df9a8fc1d fix: export all huggingface module (#1390) 2024-10-24 15:55:58 -07:00
Alex Yang 60b185ff53 fix: source nodes is empty (#1391) 2024-10-24 15:55:45 -07:00
github-actions[bot] ca75c81bc0 Release 0.7.9 (#1388)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-10-24 12:32:24 -07:00
Alex Yang 691c5bcaf1 fix: export embeddings utils (#1387) 2024-10-24 12:23:57 -07:00
Alex Yang 9ab998c5d5 chore: add bug report template (#1385) 2024-10-24 11:37:04 -07:00
github-actions[bot] 938b417028 Release 0.7.8 (#1384)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-10-24 10:17:01 -07:00
Alex Yang fa60fc66ae fix(env): no esm shim (#1383) 2024-10-24 10:08:49 -07:00
marcusschiesser 5607ed2fec chore: update lock file 2024-10-24 16:05:41 +07:00
github-actions[bot] f57ad6150e Release 0.7.7 2024-10-24 16:05:41 +07:00
Marcus Schiesser 2486bd8f41 feat: Add files_via_content example for LlamaCloud retrieval 2024-10-24 15:55:08 +07:00
Marcus Schiesser e2a0876ddd fix: Remove chunk size limit for prompt helper (use LLM default) 2024-10-24 15:55:08 +07:00
github-actions[bot] a75d899a57 Release 0.7.6 (#1373)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-24 00:03:09 -07:00
Alex Yang 809a6e7eea docs(next): generate llamacloud api (#1377) 2024-10-24 00:02:59 -07:00
Wassim Chegham da6eb6474b feat: add user-agent to Azure OpenAI LLM and Embedding (#1367) 2024-10-23 20:28:26 -07:00
Alex Yang cd83f8ee4f fix(next-doc): dark mode & create llama preview (#1376) 2024-10-23 19:23:44 -07:00
Thuc Pham 534d5505cb fix: replicate deps warning in nextjs (#1370) 2024-10-23 19:08:04 -07:00
Alex Yang eb87b96518 feat(next-doc): update create llama preview (#1375) 2024-10-23 19:05:21 -07:00
Alex Yang 9510d45046 chore: fix build command 2024-10-23 18:01:09 -07:00
Alex Yang 9b5b012fdf feat: new doc (#1374) 2024-10-23 17:56:59 -07:00
Parham Saidi a5a75f618d feat: added sonnet 3.5 v2 support via bedrock (#1371) 2024-10-23 10:22:06 -07:00
github-actions[bot] 051faddefd Release 0.7.5 (#1368)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-22 22:47:37 -07:00
Thuc Pham 9f22aae57c fix: unable to resolve unpdf in nextjs (#1369) 2024-10-23 11:48:22 +07:00
Marcus Schiesser e9a111d9d3 fix: VectorIndexRetrieverOptions typing (#1366)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-10-22 11:00:07 -07:00
github-actions[bot] bb7622e4d4 Release 0.7.4 (#1365)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-22 00:55:33 -07:00
Alex Yang 06f632b2cb fix(cloud): allow filename in llama parse (#1364) 2024-10-22 00:49:15 -07:00
github-actions[bot] 76b925e62a Release 0.7.3 (#1357)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-10-20 20:15:51 -07:00
Alex Yang 0493f679a4 fix(core): inline python-format-js (#1356) 2024-10-20 20:07:48 -07:00
github-actions[bot] 0e0a627c9a Release 0.7.2 (#1355)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-10-20 19:22:59 -07:00
Alex Yang 4ba2cfe7ab fix(env): align export APIs (#1354) 2024-10-20 17:11:09 -07:00
github-actions[bot] c1578a19d9 Release 0.7.1 (#1342)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-10-20 15:29:19 -07:00
Alex Yang ae49ff4e15 feat: use gpt-tokenizer (#1352) 2024-10-20 15:18:30 -07:00
Alex Yang a75af835a5 chore: fix misc before release (#1351) 2024-10-20 14:34:21 -07:00
Alex Yang 7c7cd34908 fix(pg): allow passing perform setup (#1350) 2024-10-20 14:01:24 -07:00
Alex Yang f651891196 fix: remove internal getImageEmbedModel 2024-10-20 13:21:15 -07:00
Alex Yang 04714c886f chore: move under providers directory (#1349) 2024-10-19 20:19:12 -07:00
Alex Yang cf28574f51 refactor: move clip&huggingface embedding into single package (#1346) 2024-10-19 18:39:52 -07:00
Jason Musgrave 24d065f054 feat: log api response from failed parse jobs (#1348) 2024-10-19 18:39:28 -07:00
Alex Yang b8719586e3 ci: pack all module under packages (#1345) 2024-10-18 17:26:40 -07:00
Alex Yang 07a40aca49 refactor: move llm into single packages (#1344) 2024-10-18 16:12:52 -07:00
Alex Yang 33b562938d refactor: move data-structs module (#1343) 2024-10-18 14:52:39 -07:00
Alex Yang 723b41c23c refactor: move tools into core module (#1316) 2024-10-18 09:45:01 -07:00
Alex Yang 4c38c1be0b fix: do not detect file type in sdk (#1340) 2024-10-18 09:36:01 -07:00
Alex Yang 0dde0ca27f ci: fix pre-release (#1341) 2024-10-17 23:28:58 -07:00
github-actions[bot] f3e0d07f48 Release 0.7.0 (#1337)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-10-17 11:18:29 -07:00
Bruno Bornsztein 1364e8eeed feat: update metadata extractor to use prompt template (#1338) 2024-10-17 11:10:41 -07:00
Bruno Bornsztein 96fc69cc61 feat: use promptTemplate arg correctly. (#1335) 2024-10-16 16:16:03 -07:00
Parham Saidi 3b7736f763 feat: added gemini 002 support (#1336) 2024-10-16 15:52:36 -07:00
Alex Yang a7a7afe66e fix: vector store type (#1334) 2024-10-15 11:53:35 -07:00
github-actions[bot] c646ee2eca Release 0.6.22 (#1333)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-15 11:27:21 +07:00
Marcus Schiesser 5729bd92fd fix: LlamaCloud API calls for ensuring and index and for file uploads (#1332) 2024-10-15 11:21:35 +07:00
github-actions[bot] e0e52cf879 Release 0.6.21 (#1329)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-14 15:36:53 +07:00
Thuc Pham 6f75306c17 feat: support metadata filters for Astra (#1330)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-10-14 15:31:00 +07:00
Thuc Pham 94cb4ad810 feat: ChromaDb metadata filters (#1323)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-10-14 10:21:52 +07:00
github-actions[bot] 1ea4014746 Release 0.6.20 (#1325)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-11 12:55:16 -07:00
Parham Saidi 6a9a7b1458 fix: use init api key for openai embeddings (#1324) 2024-10-11 12:20:20 -07:00
github-actions[bot] 1c168cd531 Release 0.6.19 (#1318)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-10 15:16:02 +07:00
Marcus Schiesser 62cba5236d feat: Add ensureIndex function to LlamaCloudIndex (#1321) 2024-10-10 14:49:12 +07:00
Thuc Pham d265e96420 fix: ignore webpack resolve unpdf for nextjs (#1320)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-10-10 14:22:38 +07:00
Marcus Schiesser d30bbf799f fix: Convert undefined values to null in LlamaCloud filters (#1319) 2024-10-10 12:00:16 +07:00
Marcus Schiesser 53fd00a7c3 fix: getPipelineId in LlamaCloudIndex (#1317) 2024-10-09 17:51:27 +07:00
Thuc Pham 83f2848d47 feat: add test split nodes with UUID (#1315) 2024-10-09 12:34:46 +07:00
github-actions[bot] 313071e9cd Release 0.6.18 (#1310)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-09 12:05:45 +07:00
Marcus Schiesser 5f6782038a Fix that node parsers generate nodes with UUIDs (#1311) 2024-10-09 11:56:02 +07:00
Marcus Schiesser fe08d0451b fix: llamacloud retrieval with multiple pipelines (#1309) 2024-10-09 11:39:55 +07:00
github-actions[bot] 59c5e5c3d4 Release 0.6.17 (#1305)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-07 14:44:04 +07:00
Thuc Pham ee697fb1b3 fix: generate uuid when inserting to Qdrant (#1301) 2024-10-07 14:17:04 +07:00
Alex Yang cf3320a4ea fix: improve getResponseSynthesizer type (#1304) 2024-10-06 19:15:55 -07:00
github-actions[bot] f2ed69f2f8 Release 0.6.16 (#1300)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-06 18:25:11 -07:00
Alex Yang 3489e7de84 fix: num output incorrect in prompt helper (#1303) 2024-10-06 18:19:05 -07:00
Alex Yang 468bda594e fix: correct warning when chunk size smaller than 0 (#1297) 2024-10-04 12:01:10 -07:00
Thuc Pham 6f3a31caf6 feat: add metadata filters for vector stores (#1289) 2024-10-04 14:25:11 +07:00
Thuc Pham 63e9846e97 fix: preFilters doesnot work with asQueryEngine (#1298) 2024-10-04 14:24:01 +07:00
github-actions[bot] b7382b0d24 Release 0.6.15 (#1295)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-03 19:44:55 -07:00
Alex Yang 2a8241328d fix: lazy load openai (#1294) 2024-10-03 17:12:33 -07:00
Alex Yang 0b20ff9f17 fix(cloud): package.json format (#1291) 2024-10-03 17:07:50 -07:00
github-actions[bot] 1fc26046e3 Release 0.6.14 (#1290)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-03 16:35:54 -07:00
LAWG b17d439d6d fix: ensure id_ is correctly passed during creation (#1282)
Co-authored-by: lawrencegb <lawrence@3api.com>
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-10-03 11:52:26 -07:00
github-actions[bot] 040160c360 Release 0.6.13 (#1288)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-02 16:35:52 -07:00
Alex Yang 981811efd1 fix(cloud): llama parse reader save image incorrectly (#1287) 2024-10-02 14:31:03 -07:00
github-actions[bot] d563b45a27 Release (#1286)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-10-02 09:14:15 -07:00
Parham Saidi 2774e80234 feat: Meta Llama 3.2 via bedrock (#1285) 2024-10-02 08:59:09 -07:00
github-actions[bot] 449274ca5a Release 0.6.12 (#1273)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-30 16:34:14 -07:00
Alex Yang 78037a664c chore: update changelog 2024-09-30 16:13:22 -07:00
Alex Yang 1d9e3b1000 fix: export llama reader in non-nodejs runtime (#1279) 2024-09-30 16:13:07 -07:00
Alex Yang df83e32107 fix: bypass service context embed model (#1280) 2024-09-30 16:02:48 -07:00
Thuc Pham f7b4e94231 feat: add filters for pinecone (#1272) 2024-09-30 17:04:43 +07:00
Marcus Schiesser 4c07a2655d text: add cycle test (#1270) 2024-09-29 23:13:59 -07:00
Marcus Schiesser 5c0c8b2ec4 test: add concurrent test for workflows (#1269) 2024-09-29 22:10:21 -07:00
Emmanuel Ferdman e5e18688a6 fix: update reader reference (#1268)
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
2024-09-28 14:44:44 -07:00
github-actions[bot] b6fb10eba8 Release 0.6.11 (#1267)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-27 13:19:52 -07:00
Alex Yang df441e28f4 chore: release for new env package 2024-09-27 12:54:14 -07:00
github-actions[bot] a4e05ec7ab Release 0.6.10 (#1263)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-27 01:51:07 -07:00
irevived1 96f72ad86e fix: openai streaming with token usage and finish_reason (#1265)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-09-26 17:51:59 -07:00
Alex Yang f3556c011c chore: update changeset 2024-09-26 09:36:20 -07:00
Alex Yang ebc510582b feat: support @vercel/postgres (#1262) 2024-09-25 22:39:32 -07:00
Alex Yang f3bfdc29e3 chore: fix changeset 2024-09-25 20:09:37 -07:00
Alex Yang 6cce3b12ea feat: support npm:postgres (#1248) 2024-09-25 19:40:20 -07:00
Alex Yang 0273e9739a chore: fix docs build with turbo (#1260) 2024-09-25 07:32:37 -07:00
Alex Yang 7c8b883448 fix: turbo cache (#1259) 2024-09-25 04:47:01 -07:00
Alex Yang c2bb418542 chore: fix url in package.json (#1258) 2024-09-25 03:52:33 -07:00
Alex Yang ed6acbead0 fix(core): backward support for legacy typescript (#1257) 2024-09-25 03:19:41 -07:00
Alex Yang 976cce40d7 docs: update README.md (#1255) 2024-09-24 15:03:48 -07:00
Alex Yang e4fd4158bb feat: move agent into core (#1254) 2024-09-24 14:55:40 -07:00
Alex Yang 31d5dffcef refactor: move ollama standalone (#1253) 2024-09-24 12:15:50 -07:00
github-actions[bot] d12edee802 Release 0.6.9 (#1252)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-24 10:31:54 -07:00
Alex Yang ac41ed3aae chore: bump cloud sdk version (#1251) 2024-09-24 09:43:45 -07:00
github-actions[bot] d8c1159032 Release 0.6.8 (#1245)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-23 18:41:44 -07:00
Alex Yang c856c5becb revert: stream back to first parameter (#1247) 2024-09-23 18:35:36 -07:00
John Wick 50e6b57be0 feat: add Amazon Bedrock Retriever (#1219)
Co-authored-by: Arnaud JEAN <arnajean@amazon.com>
Co-authored-by: ajohn-wick <ajohnwick@mrwick.org>
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-09-23 15:11:53 -07:00
Alex Yang 8b7fdba544 refactor: move chat engine & retriever into core (#1242) 2024-09-23 13:26:26 -07:00
github-actions[bot] 22ae8d0166 Release 0.6.7 (#1244)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-23 13:25:02 -07:00
Goran 23bcc379a8 fix: add serializer in doc store (#1243)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-09-23 13:11:51 -07:00
github-actions[bot] bdc4bfe7b0 Release 0.6.6 (#1241)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-23 11:54:33 -07:00
Goran 025ffe6b50 fix: update PostgresKVStore constructor params (#1240)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-09-23 10:46:11 -07:00
Cahid Arda Öz a6595747fa feat: add Upstash Vector Store (#1218)
Co-authored-by: ogzhanolguncu <ogzhan11@gmail.com>
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-09-23 10:00:10 -07:00
Marcus Schiesser d902cc3e7e fix: context not working in contextchatengine (#1237) 2024-09-22 15:19:13 -07:00
github-actions[bot] 726eb41359 Release 0.6.5 (#1239)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-20 14:24:23 -07:00
André Mazayev e9714dbfcd feat: update PGVectorStore constructor parameters (#1225)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-09-20 01:34:51 -07:00
Alex Yang a3618e761e chore: fix cache for cloud package (#1236) 2024-09-19 17:48:39 -07:00
github-actions[bot] 24eabe7f35 Release 0.6.4 (#1234)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-19 16:42:39 -07:00
Alex Yang ecfa939ea6 ci: enable remote cache (#1233) 2024-09-19 15:40:34 -07:00
Alex Yang b48bcc3add feat: support custom @xenova/transformers (#1232) 2024-09-19 14:55:23 -07:00
github-actions[bot] fa01fa2051 Release 0.6.3 (#1220)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-09-19 12:38:23 -07:00
Alex Yang fb36eff5e1 fix: use Blob instead of File (#1231) 2024-09-19 12:32:10 -07:00
Alex Yang d24d3d1e8c fix: print warning when llama parse reader has error (#1230) 2024-09-19 09:41:37 -07:00
Aaron Ji 5c4badbcca chore: add 'late_chunking' for Jina embedding (#1223) 2024-09-18 17:38:46 +07:00
Alex Yang 2cd1383dc8 feat: align response-synthesizers & chat-engine module (#1169) 2024-09-17 15:44:44 -07:00
github-actions[bot] 72440c101f Release 0.6.2 (#1217)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-09-16 16:40:33 -07:00
Alex Yang 423d66b07a refactor: chat memory & chat history into core module (#1201) 2024-09-16 16:09:17 -07:00
Alex Yang b42adebd51 fix: get job result in llama parse reader (#1216) 2024-09-16 16:05:47 -07:00
Alex Yang 749b43a3b1 fix: multi model embedding (#1215) 2024-09-16 15:51:24 -07:00
github-actions[bot] 8daaef44ee Release 0.6.1 (#1202)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-09-16 13:08:49 -07:00
Alex Yang ac07e3cbe6 fix: replace instanceof check with .type check (#1214) 2024-09-16 12:46:40 -07:00
Alex Yang 1a6137b323 feat: experimental support for browser (#1213) 2024-09-16 12:11:24 -07:00
Alex Yang 85c2e198a4 feat: llama cloud sdk update (#1206) 2024-09-16 09:29:33 -07:00
Fabian Wimmer 01263c4cfd docs: fix false params (#1211) 2024-09-16 07:55:59 -07:00
Thuc Pham fbd5e0174d refactor: move groq as llm package (#1209) 2024-09-16 17:44:14 +07:00
Marcus Schiesser 70ccb4ae65 feat: allow arbitrary types in workflow's StartEvent and StopEvent (#1210) 2024-09-16 16:31:08 +07:00
Alex Yang 7eb331774d chore: bump typescript (#1205) 2024-09-13 13:18:35 -07:00
Alex Yang 24a3f058a3 chore: update build script (#1204) 2024-09-13 11:44:40 -07:00
Fabian Wimmer 84c28f95f9 docs: restructure, add API references (#1196) 2024-09-13 11:22:37 -07:00
Alex Yang 7af57982fe test: enable dom & edge runtime (#1203) 2024-09-13 10:43:18 -07:00
Aaron Ji 6b70c5408f chore: update JinaEmbedding for v3 release (#1187) 2024-09-13 09:44:43 -07:00
github-actions[bot] 74fc725f37 Release 0.6.0 (#1199)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: marcusschiesser <marcusschiesser@users.noreply.github.com>
2024-09-13 16:07:16 +07:00
Marcus Schiesser a0a74aed60 fix: release openai package (#1200) 2024-09-13 16:01:00 +07:00
Marcus Schiesser 11feef8c82 Add workflows (#1188)
Co-authored-by: Thuc Pham <51660321+thucpn@users.noreply.github.com>
2024-09-13 15:46:02 +07:00
github-actions[bot] 9c5ff164ac Release 0.5.27 (#1195)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-12 13:47:11 -07:00
Alex Yang 7edeb1c2d7 feat: decouple openai from llamaindex module (#1194) 2024-09-12 13:36:08 -07:00
github-actions[bot] 8b95abdc85 Release 0.5.26 (#1193)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-12 11:38:07 -07:00
Alex Yang ffe0cd1ef1 chore: update changelog 2024-09-12 11:33:32 -07:00
Alex Yang 5d2111a19f feat: init support openai o1 model (#1192) 2024-09-12 11:31:05 -07:00
Alex Yang 68ac7fd57f ci: fix syntax (#1186) 2024-09-11 16:54:39 -07:00
Alex Yang 7320d96a36 fix: waku build (#1185) 2024-09-11 15:36:39 -07:00
Goran ee17fb475b feat: add PostgreSQL storage (#1180) 2024-09-11 12:31:04 -07:00
github-actions[bot] 28b877e31f Release 0.5.25 (#1182)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-11 12:08:39 -07:00
Alex Yang 4389b80a52 docs: update README.md (#1183) 2024-09-11 11:07:00 -07:00
Alex Yang d3bc663951 fix: vector store cleanup (#1175) 2024-09-11 10:20:55 -07:00
Kieran Simkin 4810364788 fix: handle RouterQueryEngine with string query (#1181) 2024-09-11 10:19:59 -07:00
github-actions[bot] 2dcad52dd9 Release 0.5.24 (#1178)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-10 23:48:51 -07:00
Alex Yang 0bf8d80b12 fix: llama cloud api build 2024-09-10 23:39:58 -07:00
github-actions[bot] e4bba02aec Release 0.5.23 (#1174)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-10 11:41:49 -07:00
Alex Yang 1caa0da657 chore: fix changeset 2024-09-10 11:34:07 -07:00
Alex Yang 711c814bb2 fix: patch python-format-js (#1173) 2024-09-10 09:49:36 -07:00
Alex Yang 5b832eb927 fix: strict type check (#1170) 2024-09-10 09:28:44 -07:00
Alex Yang 49988431f6 refactor: move settings.llm into core package (#1165) 2024-09-09 10:45:57 -07:00
Alex Yang 72d65dd51a docs: fix example (#1168) 2024-09-09 10:45:30 -07:00
Alex Yang 553bc55b19 refactor: move PromptHelper into core package (#1166) 2024-09-09 10:15:21 -07:00
Alex Yang fc6f69833c fix: example code (#1167) 2024-09-09 10:11:58 -07:00
github-actions[bot] c7fd06841f Release 0.5.22 (#1164)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-09 09:27:26 -07:00
Thuc Pham 4648da6849 fix: wrong tiktoken version caused NextJs CL template run fail (#1162) 2024-09-09 09:23:13 -07:00
Fabian Wimmer 0188cf3bb6 docs: fix typos, add API references (#1161) 2024-09-09 11:40:05 +07:00
Alex Yang e0b4f9c047 refactor: move constant into core module (#1158) 2024-09-06 20:29:08 -07:00
github-actions[bot] 4895bba96e Release 0.5.21 (#1140)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-09-06 15:26:14 -07:00
Alex Yang 76d1df817b chore: update tall-kangaroos-sleep.md 2024-09-06 15:11:10 -07:00
Ryan Lee 83d7f415e2 fix: database insertion for PGVectorStore (#1157) 2024-09-06 14:32:48 -07:00
Fabian Wimmer ae1149ffaf feat: add json streaming to JSONReader (#1119) 2024-09-06 11:22:21 -07:00
Alex Yang 0148354dbe refactor: prompt system (#1154) 2024-09-06 11:22:08 -07:00
Thuc Pham 11b3856334 feat: implement filters for MongoDBAtlasVectorSearch (#1142) 2024-09-05 14:11:31 +07:00
Philipp Serrer e8f229cd01 chore: remove logging from mongodb atlas vector store (#1145) 2024-09-03 18:01:52 -07:00
Alex Yang 75b70e5824 fix: remove Stream API polyfill (#1149) 2024-09-03 18:01:42 -07:00
Marcus Schiesser 1711f6d8fc fix: Export imageToDataUrl for using images in chat (#1146) 2024-09-03 10:56:30 +07:00
Alex Yang 20d16abdf4 chore: bump version (#1143) 2024-08-30 13:08:14 -07:00
Thuc Pham 2411c9fbd0 feat: Auto-create index for MongoDB vector store (if not exists) (#1139)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-08-30 14:24:20 +07:00
Phil Nash be3e280f2a Updates references to SimpleNodeParser to SentenceSplitter. (#1129) 2024-08-30 11:15:57 +07:00
github-actions[bot] 2afcbe6587 Release 0.5.20 (#1132)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-08-28 10:43:26 +07:00
Marcus Schiesser 22ff486fbe fix: Add tiktoken WASM to withLlamaIndex (#1134)
Co-authored-by: Thuc Pham <51660321+thucpn@users.noreply.github.com>
2024-08-28 10:39:14 +07:00
Thuc Pham eed0b0415d fix: use metadata mode LLM for generating context (#1133)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-08-23 22:56:18 +07:00
Sebastian van Gerwen d9d6c56ed5 pgvectorstore support new conditions and operations (#1131)
Co-authored-by: Sebastian van Gerwen <svangerwen@invertigro.com>
Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>
2024-08-23 14:40:39 +07:00
github-actions[bot] f99a237093 Release 0.5.19 (#1128)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-08-19 14:04:47 +07:00
Thuc Pham fcbf18344c feat: implement llamacloud file service (#1125) 2024-08-19 14:01:41 +07:00
github-actions[bot] bf8cbeb6c5 Release 0.5.18 (#1124)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-08-19 12:53:28 +09:00
Alex Yang e27e7dd054 chore: bump natural to 8.0.1 (#1126) 2024-08-17 07:15:08 -07:00
Thuc Pham 8b66cf4341 feat: support organization id in llamacloud index (#1123)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-08-15 13:51:48 +07:00
github-actions[bot] 6f4549bdea Release 0.5.17 (#1117)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-08-12 17:45:29 +07:00
Thuc Pham c654398f75 feat: implement Weaviate Vector Store in TS (#1109) 2024-08-12 17:41:05 +07:00
github-actions[bot] 0664a99945 Release 0.5.16 (#1115)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-08-09 22:09:34 -07:00
Alex Yang 58abc5731b chore: update changeset 2024-08-09 22:06:43 -07:00
github-actions[bot] 7498b1e0f1 Release 0.5.15 (#1108)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-08-09 14:36:47 -07:00
Alex Yang 07a275fea5 chore: bump openai (#1113) 2024-08-09 12:56:30 -07:00
Alex Yang 1b6263e08d fix: export schema in top level (#1112) 2024-08-09 10:10:12 -07:00
Alex Yang 089f1d49c0 refactor: migrate reader type into core (#1111) 2024-08-09 09:53:50 -07:00
Thuc Pham 01c184c608 feat: add is_empty operator for filtering vector store (#1107) 2024-08-09 14:50:57 +07:00
github-actions[bot] 1752463ee6 Release 0.5.14 (#1103)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-08-07 17:03:00 -07:00
Peter Goldstein c825a2f743 Add gpt-4o-mini to Azure. Add 2024-06-01 API version for Azure (#1102) 2024-08-06 14:23:28 +07:00
github-actions[bot] ba058dc8d4 Release 0.5.13 (#1100)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-08-02 09:50:07 -07:00
Philipp Serrer 04b2f8e062 fix: metadata should not be included after sentence splitter (#1099) 2024-08-02 09:22:04 -07:00
Alex Yang 62b874e14f fix: enforce no-base-to-string (#1097) 2024-08-01 14:05:19 -07:00
github-actions[bot] 9c9e9b4e03 Release 0.5.12 (#1091)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-30 15:46:39 -07:00
Alex Yang e3c307ab55 chore: fix changeset 2024-07-30 15:32:24 -07:00
André Lago b1b2baa969 docs: fix minor typo (#1092) 2024-07-30 15:07:46 -07:00
Marcus Schiesser 0452af91cc fix: handling errors in splitBySentenceTokenizer (#1087)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-07-30 09:36:58 -07:00
Marcus Schiesser da5cfc42e5 fix: integrate with create-llama (#1088)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-07-30 08:19:32 -07:00
Alex Yang eb89223386 chore: bump bunchee@5.3.1 (#1090) 2024-07-30 08:19:01 -07:00
Alex Yang 93dc3a31b3 fix: lock hey-api version (#1089) 2024-07-30 08:00:05 -07:00
Fabian Wimmer 345300f110 feat: add split by page mode to LlamaParseReader (#924) 2024-07-29 16:16:46 +07:00
github-actions[bot] f322c5d202 Release 0.5.11 (#1082)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-26 21:26:11 -07:00
Parham Saidi 376d29a78f feat: meta3.1 405b tool calling support (#1080) 2024-07-26 19:53:24 -07:00
Parham Saidi 224d507ab5 fix: prevent anthropic tool calling getting mixed with conversation (#1078) 2024-07-26 09:55:22 -07:00
Alex Yang 1f680d731d chore: bump llamacloud api (#1081) 2024-07-26 09:53:50 -07:00
github-actions[bot] f0a1cc51b4 Release 0.5.10 (#1074)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-25 16:43:17 -07:00
Alex Yang fee3280799 chore: fix changelog 2024-07-25 11:21:16 -07:00
Alex Yang 54925bf1ae chore: fix changelog 2024-07-25 11:20:47 -07:00
Alex Yang 91d02a4fc0 feat: support transform component callable (#1072) 2024-07-25 11:19:57 -07:00
Erik 086b94038e feat: add DeepSeek LLM class and documentation (#1071) 2024-07-25 11:15:34 -07:00
Fabian Wimmer 5d5716b339 feat: add a reader for JSON data (#1063) 2024-07-25 09:40:54 -07:00
Fabian Wimmer fb6db454d4 feat: update/add pageSeparator params to LlamaParseReader (#1051) 2024-07-25 15:09:43 +07:00
Marcus Schiesser e4d4e0d024 docs: update CONTRIBUTING.md (#1073) 2024-07-25 00:59:45 -07:00
Diego Ferreiro Val 17724d961e feat: add support for buffer on loadJSON API on LlamaParseReader (#1069)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-07-25 14:44:46 +07:00
github-actions[bot] 6776910c93 Release 0.5.9 (#1070)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-24 12:04:51 -07:00
Alex Yang 15962b36f0 feat: node parser refactor (#1065) 2024-07-24 10:46:00 -07:00
Parham Saidi 3d9a802734 feat: bedrock meta llama 3.1 8b, 70b and 405B (#1068) 2024-07-24 10:45:49 -07:00
github-actions[bot] 9cd8f8b0cf Release 0.5.8 (#1067)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-24 01:43:09 -07:00
Alex Yang b44330cbc6 chore: fix changelog 2024-07-24 01:28:40 -07:00
Niels Swimberghe 3d5ba0873c fix: update user agent in AssemblyAI (#1039)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-07-24 00:50:35 -07:00
Thuc Pham d917cdc3fa feat: add azure interpreter tool to tool factory (#1064) 2024-07-23 16:04:36 +07:00
github-actions[bot] b370edf329 Release 0.5.7 (#1062)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-22 10:07:44 -07:00
Marcus Schiesser ec59acd329 fix: bundling issue with pnpm (#1060)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-07-22 09:37:13 -07:00
github-actions[bot] c69e740c56 Release 0.5.6 (#1048)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-18 15:20:19 -07:00
Alex Yang 6cf6ae631c feat: abstract query type (#1052) 2024-07-18 13:27:02 -07:00
Alex Yang 2562244fb6 feat: add gpt4o-mini (#1057) 2024-07-18 12:50:51 -07:00
Thuc Pham a2691ee163 fix: always return false when key not exist in metadata (#1056) 2024-07-18 22:52:00 +07:00
Marcus Schiesser ab700ea546 fix: Add missing authentication to LlamaCloudIndex.fromDocuments (#1055) 2024-07-18 16:32:07 +07:00
Marcus Schiesser e775afc3f2 docs: clarify similarityTopK usage (#1053) 2024-07-18 16:24:49 +07:00
Alex Yang 92f07824a7 feat: use query bundle (#702) 2024-07-17 20:17:06 -07:00
Igor Soares b7cfe5bce6 fix: passing max_token option to replicate's api call (#1050)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-07-17 12:00:30 -07:00
Chris Paganon 3ccfb28352 docs: fix deprecated similarityTopK for retriever (#1049) 2024-07-17 11:59:28 -07:00
Thuc Pham 325aa51e51 feat: implement Jina embedding through Jina api (#995)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-07-17 20:57:14 +07:00
Marcus Schiesser d1d9bd6e41 docs: add metadata filter operators (#1047) 2024-07-17 17:00:37 +07:00
github-actions[bot] 9a71382243 Release 0.5.5 (#1046)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-17 16:26:38 +07:00
Thuc Pham b974eea341 feat: add MetadataFilter for SimpleVectorStore and Milvus (#1030)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-07-17 16:21:21 +07:00
github-actions[bot] e82632f83d Release 0.5.4 (#1043)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-16 14:53:20 -07:00
Fabian Wimmer 1a65ead849 feat: add vendorMultiModal params to LlamaParseReader (#1042) 2024-07-16 14:20:34 -07:00
Alex Yang 50b7d1b7bb refactor: put embedding into core (#1041) 2024-07-16 10:49:03 -07:00
github-actions[bot] 09beb72f5b Release 0.5.3 (#1038)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-16 10:25:27 -07:00
Fabian Wimmer 9bbbc67c8e feat: add a reader for Discord messages (#1040) 2024-07-16 10:19:48 -07:00
Brian Peiris b3681bf681 fix: DataCloneError when using FunctionTool (#1037) 2024-07-14 15:24:49 -07:00
Alex Yang b548b1443b chore: bump version (#1032) 2024-07-12 15:14:27 -07:00
github-actions[bot] 0e980d962d Release 0.5.2 (#1035)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-12 11:44:32 -07:00
Alex Yang 3ed6acc6a6 chore: bump cloud api (#1036) 2024-07-12 11:21:37 -07:00
Parham Saidi 56746c240f fix: bedrock handle empty content and added max tokens export (#1034) 2024-07-12 09:47:49 -07:00
Alex Yang 5c1c2c7f5b ci: only commit lock file (#1031) 2024-07-10 10:17:35 -07:00
github-actions[bot] a699086f46 Release 0.5.1 (#1028)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-09 15:36:20 -07:00
Alex Yang 454c204112 chore: bump version (#1029) 2024-07-09 13:42:09 -07:00
Julius Lipp 277468160d feat: add mixedbread ai integration (#953) 2024-07-09 09:36:43 -07:00
Ranjan Mangla a0f424e592 fix: corrected the regex in the ReactAgent (#1022)
Signed-off-by: ranjanmangla1 <ranjanmangla1@gmail.com>
2024-07-09 08:55:38 -07:00
github-actions[bot] 3ae832ca28 Release 0.5.0 (#1024)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: himself65 <himself65@users.noreply.github.com>
2024-07-08 17:16:46 -07:00
Alex Yang 16ef5dd631 feat: simplify callback manager (#1027) 2024-07-08 16:44:54 -07:00
Alex Yang c4bd0a5215 refactor: move llm & callback manager to core module (#1026) 2024-07-08 15:48:59 -07:00
Alex Yang f5c8ca7dfb chore: use bunchee bundler for all (#1025) 2024-07-08 09:45:55 -07:00
Sacha Bron 36ddec44af fix: typo in custom page separator parameter for LlamaParse (#1023) 2024-07-08 09:27:51 -07:00
github-actions[bot] c147d8a271 Release 0.4.14 (#1021)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-05 15:26:31 -07:00
Alex Yang 1c444d58b6 feat(cloud): update openapi.json (#1020) 2024-07-05 15:01:22 -07:00
github-actions[bot] 1f910f7566 Release 0.4.13 (#1016)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-05 11:44:37 -07:00
Thuc Pham 99826cff43 fix: missing dispatch retrieve event on llamacloud retriever (#1018) 2024-07-05 20:43:26 +07:00
Fabian Wimmer e8f8bea969 feat: add boundingBox and targetPages to LlamaParseReader (#1017) 2024-07-05 14:32:26 +07:00
Fabian Wimmer 304484b77a feat: add ignoreErrors flag to LlamaParse (#959)
Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>
2024-07-04 20:51:05 +07:00
abgita 29fed77d58 Fixed a typo in the retriever description (#1009) 2024-07-04 20:15:20 +07:00
Alex Yang db070588c8 ci: fix setup pnpm (#1014) 2024-07-03 12:11:48 -07:00
github-actions[bot] 76deca7fea Release 0.4.12 (#1013)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-03 10:24:22 -07:00
Alex Yang f326ab86d2 chore: bump version 2024-07-03 10:20:46 -07:00
Cássio de Freitas e Silva ca8d9709e0 feat: add support for Meta LLMs in AWS Bedrock (#960) 2024-07-03 01:27:58 -07:00
github-actions[bot] e0af059221 Release 0.4.11 (#1008)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-02 15:07:03 -07:00
Alex Yang 8bf5b4acfd fix: llama parse input spreadsheet (#1007) 2024-07-02 14:48:51 -07:00
Alex Yang 93a003baa0 ci: pre release (#1005) 2024-07-02 00:40:45 -07:00
github-actions[bot] 5d9b0bd3f0 Release 0.4.10 (#1003)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-01 23:59:52 -07:00
Alex Yang 9a5525e1b3 refactor(core): migrate llms type (#1002) 2024-07-01 20:13:35 -07:00
Peron 7dce3d28d3 fix: disable External Filters for Gemini (#994)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-07-01 18:28:22 -07:00
github-actions[bot] d4c1482c1c Release 0.4.9 (#1001)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-01 17:20:47 -07:00
Alex Yang 3a96a483a6 fix: anthropic image input (#999) 2024-07-01 16:03:30 -07:00
Alex Yang 7467fce2d4 docs: remove cloudflare worker section (#1000) 2024-07-01 16:01:55 -07:00
github-actions[bot] 06af08cac4 Release 0.4.8 (#998)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-07-01 15:07:50 -07:00
Alex Yang 83ebdfb1c5 fix: next.js binding (#997) 2024-07-01 14:52:57 -07:00
github-actions[bot] 835b1ac000 Release 0.4.7 (#986)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-28 22:58:14 -07:00
Alex Yang f10b41dbc1 chore: fix release files (#991) 2024-06-28 13:36:55 -07:00
Wassim Chegham 41fe871e2f feat: add support for azure dynamic session tool (#942)
Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>
2024-06-27 13:18:05 -07:00
Alex Yang 321c39ddc7 fix: generate api as class (#988) 2024-06-27 09:58:00 -07:00
Alex Yang f7f1af0139 fix: llamacloud sdk edge case (#985) 2024-06-26 23:10:04 -07:00
github-actions[bot] a8c9c279d6 Release 0.4.6 (#981)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-26 17:22:28 -07:00
Alex Yang eece129831 feat: migrate @llamaindex/cloud package (#984) 2024-06-26 16:51:47 -07:00
Alex Yang 80e4f51a83 fix: remove check-minor-version.mjs
We no longer need that
2024-06-26 15:31:08 -07:00
Alex Yang 22ff0837c3 feat: init @llamaindex/core (#938) 2024-06-26 15:28:57 -07:00
Alex Yang 74d7e05bcb ci: continue when commit lockfile error (#982) 2024-06-26 11:06:06 -07:00
Parham Saidi 1feb23bb83 feat: added Gemini tool calling support (#973) 2024-06-26 10:49:11 -07:00
Marcus Schiesser 08c55ec258 fix: Add metadata to PDFs and use Uint8Array for readers content (#980) 2024-06-26 10:16:23 -07:00
github-actions[bot] 394e797567 Release 0.4.5 (#979)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-26 17:42:19 +07:00
Parham Saidi 6c3e5d08b8 fix: switch to correct reference for a static function (#978) 2024-06-26 17:35:22 +07:00
github-actions[bot] 6e19482814 Release 0.4.4 (#977)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-26 14:46:48 +07:00
Marcus Schiesser 42eb73a08f fix: IngestionPipeline not working without vectorStores (#976) 2024-06-26 14:30:58 +07:00
github-actions[bot] 4b59ffee45 Release 0.4.3 (#971)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-25 15:38:10 -07:00
Alex Yang d4e853c8b5 fix: stronger type declaration (#975) 2024-06-25 15:22:13 -07:00
Alex Yang a94b8ec3d2 chore: fix misc (#974) 2024-06-25 14:41:26 -07:00
Alex Yang ed57e6b7be docs: remove i18n temporary (#972) 2024-06-25 14:00:07 -07:00
Alex Yang 05f006e7e1 chore: fix llamaindex version 2024-06-25 12:21:22 -07:00
Alex Yang c3aed72c29 chore: skip install when releasing new version 2024-06-25 12:08:53 -07:00
Alex Yang 7deba94e6b chore: fix lock file 2024-06-25 11:57:04 -07:00
github-actions[bot] d15811f09f Release 0.4.2 (#966)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-25 11:23:01 -07:00
Tasmiyah Iqbal 2ef62a93bb feat: added support for embeddings via HuggingFace Inference API (#929) 2024-06-25 11:16:41 -07:00
Fabian Wimmer 9015aea527 docs: LlamaParse JSON + SimpleDirectoryReader (#970) 2024-06-25 11:16:27 -07:00
Emanuel Ferreira 4bb401e6f9 feat: upgrade llamacloud index (#944)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-25 10:52:06 -07:00
Parham Saidi a87a4d1222 feat: tool calling for Bedrock's Claude and General LLM Agent (#955) 2024-06-25 10:51:40 -07:00
Marcus Schiesser d27ad16335 test: add e2e test for nextjs/node with tokenizer (#963) 2024-06-25 10:02:01 -07:00
Marcus Schiesser 20498a2bce fix: use tiktoken instead of tiktoken/lite (#967) 2024-06-25 09:51:08 -07:00
Andy Garvin 0730140e62 fix: include node relationships when converting jsonToDoc (#968) 2024-06-25 22:59:16 +07:00
Andy Garvin 810711d355 docs: change references from core package to llamaindex (#969) 2024-06-25 22:55:37 +07:00
Marcus Schiesser f3b34b457c docs: add changeset (#965) 2024-06-25 21:36:00 +07:00
Fabian Wimmer 6f4b9f3372 docs: fix broken links, add API References (#962) 2024-06-24 19:10:16 -07:00
Fabian Wimmer 01658fdb31 docs: update data loaders (#961) 2024-06-24 10:45:17 -07:00
Alex Yang 66c26d9cce fix: json import (#958) 2024-06-21 11:27:08 -07:00
Marcus Schiesser a4060a7914 docs: update anthropic examples to use claude 3.5 (#954) 2024-06-21 17:27:56 +07:00
github-actions[bot] 469e438741 Release 0.4.1 (#949)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-21 17:26:01 +07:00
Marcus Schiesser 56fabbb4f5 fix: Release env changes to tokenizer (#952) 2024-06-21 16:58:02 +07:00
Alex Yang dfd8cc1ba4 chore: fix new-version script (#950) 2024-06-20 16:34:09 -07:00
Fabian Wimmer cba54061a2 fix: every Llama Parse job being called "blob" (#946)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-20 16:32:20 -07:00
Peter Goldstein ed467a9889 feat: add Anthropic Claude 3.5 Sonnet model (#948) 2024-06-20 16:21:58 -07:00
Alex Yang 3c4791007f fix: groq llm (#947) 2024-06-20 16:19:55 -07:00
Alex Yang 8f16a179c3 chore: fix lock 2024-06-20 12:51:34 -07:00
github-actions[bot] ce3a4cac6c Release 0.4.0 (#923)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-20 12:38:05 -07:00
Alex Yang be46044b98 build: fix check-minor-version.mjs 2024-06-20 12:31:13 -07:00
Alex Yang 154c7f8e36 chore: bump version (#945) 2024-06-20 12:25:59 -07:00
Alex Yang 8b6c2b45a6 chore: fix version release (#937) 2024-06-17 16:42:38 -07:00
Parham Saidi b1a4a74270 docs: updated Bedrock Opus region and added a basic README (#935) 2024-06-17 14:34:14 -07:00
Alex Yang d7fb095fbd refactor: rename directory core to llamaindex (#936) 2024-06-17 14:33:53 -07:00
Alex Yang 58791d4bdd fix: tokenizer type (#934) 2024-06-17 10:34:37 -07:00
Parham Saidi d3b635b193 fix: agents to use chat history (#933) 2024-06-17 10:33:57 -07:00
Marcus Schiesser 436bc41f82 refactor: unify response and agent response (#930) 2024-06-17 09:01:08 -07:00
Vishwasa Navada K 834f49275a docs: fixed the broken link on Getting Started Section (#932) 2024-06-17 22:56:10 +07:00
Marcus Schiesser a44e54f9ec feat: truncate embedding tokens (#918)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-15 02:13:39 +08:00
Wassim Chegham a51ed8dd70 feat: add support for managed identity for Azure OpenAI (#922)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-11 16:32:39 -07:00
Fabian Wimmer c8cfc6c06d fix: LlamaParse json mode returns array + basic example (#914)
Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-06-11 10:56:52 -07:00
github-actions[bot] 83b2f0b0af Release 0.3.17 (#920)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-11 10:52:40 -07:00
Alex Yang 1a6abb38bc build: community package cleanup before release (#897) 2024-06-11 10:47:35 -07:00
Fabian Wimmer 6bc5bddb59 feat: add new options to LlamaParseReader (#915) 2024-06-11 16:31:01 +07:00
Alex Yang e6d6576b2f chore: use unpdf (#849) 2024-06-10 16:45:09 -07:00
Alex Yang bf25ff6104 fix: polyfill for cloudflare worker (#919) 2024-06-10 14:08:47 -07:00
Talha Jubair Siam 32ad0992cf docs : fix correctness and relevancy example (#913) 2024-06-10 20:19:06 +07:00
Marcus Schiesser af650343d9 fix: remove debugger statement (#917) 2024-06-10 20:14:26 +07:00
Thuc Pham f6f4ca44bd feat: add gpt-4o tool call fail example (#916)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-06-10 17:29:25 +07:00
github-actions[bot] 9aa918f026 Release 0.3.16 (#896)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-06 07:20:58 -07:00
Marcus Schiesser 00a92cd125 fix: custom reader example 2024-06-06 12:04:27 +02:00
Marcus Schiesser 73819bf19d feat: Unify metadata and ID handling of documents, allow files to be read by Buffer 2024-06-06 11:51:54 +02:00
Marcus Schiesser d10cca28fc chore: use FileReader interface when possible (#912) 2024-06-06 15:37:20 +07:00
Alex Yang 1378ec4e50 feat: set default model to gpt-4o (#911) 2024-06-05 22:44:52 -07:00
Fabian Wimmer 24a9d1e816 feat: add json mode and image retrieval to LlamaParse (#910)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-05 13:50:51 -07:00
Yi Ding b100684bad chore: bump version (#892)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-05 13:50:33 -07:00
Alex Yang c375cd5c6b fix: multiple tool call (#905) 2024-06-05 10:23:41 -07:00
Fabian Wimmer 45952dee59 feat: add parallel processing to SimpleDirectoryReader (#908)
Co-authored-by: Alex Yang <himself65@outlook.com>
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-06-05 23:17:47 +07:00
Marcus Schiesser 6db7f23ec7 Revert "feat: add parallel processing to SimpleDirectoryReader (#883)"
This reverts commit da1f025229.
2024-06-05 13:35:58 +02:00
Marcus Schiesser 0721a84900 fix: ignore empty vector store (#861) 2024-06-04 10:26:16 -07:00
Marcus Schiesser 4d4bd85448 fix: calling tools with large inputs (#901) 2024-06-04 09:07:19 -07:00
Philipp Serrer 11ae9267ae feat: add numCandidates setting to MongoDBAtlasVectorStore for tuning queries (#893)
Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>
2024-06-04 16:11:54 +07:00
Fabian Wimmer 174cb3e6da docs: update data loader documentation (#900)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-03 13:50:48 -07:00
Alex Yang 5ab5e5191d fix: empty prefix with inputs (#899) 2024-06-03 12:11:57 -07:00
Parham Saidi 54230f0477 feat: Gemini latest GA released models (#898)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-03 11:41:15 -07:00
Oguz Vuruskaner 3d484da1c5 feat: DeepInfra Embeddings implementation (#890)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-03 11:34:07 -07:00
Oguz Vuruskaner 631f0001ef feat: DeepInfra LLM implementation (#894)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-03 11:21:23 -07:00
Alex Yang 060b700e09 chore: fix changelog 2024-06-03 09:53:15 -07:00
justinmann 83c24f4d50 cannot pass embedModel to MongoDBAtlasVectorStore (#887) 2024-06-03 23:08:33 +07:00
Parham Saidi 883266939e feat: Bedrock support added, only for Anthropic models (#847)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-06-03 09:07:17 -07:00
Philipp Serrer a29d8351c8 fix: setDocumentHash should be async (#868) 2024-06-03 09:05:23 -07:00
Fabian Wimmer da1f025229 feat: add parallel processing to SimpleDirectoryReader (#883)
Co-authored-by: Alex Yang <himself65@outlook.com>
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-06-03 23:01:27 +07:00
Fabian Wimmer 6b1ded41a9 feat: LlamaParse: add gpt4o-mode, invalidate cache, skip diagonal text, update supported file types (#889)
Co-authored-by: Marcus Schiesser <marcus.schiesser@googlemail.com>
2024-06-03 22:22:18 +07:00
github-actions[bot] e01cc053e3 Release 0.3.15 (#884)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-06-03 21:29:46 +07:00
Marcus Schiesser 6e156edb11 feat: use images in context chat engine (#886) 2024-06-03 21:24:43 +07:00
Marcus Schiesser 0b519958e9 chore: downgrade changeset to patch 2024-06-03 11:18:15 +02:00
Philipp Serrer 265976df12 fix: incorrect hash because of missing params in decorator (#891) 2024-05-28 16:05:24 -07:00
Marcus Schiesser 7e1b96a2db fix: default to Settings.llm (#885) 2024-05-24 22:15:09 +07:00
Marcus Schiesser 8e26f753b7 feat: Add retrieval for images using multi-modal messages (#870) 2024-05-24 22:08:20 +07:00
github-actions[bot] 31e3251435 Release 0.3.14 (#878)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-23 16:00:09 -07:00
Yi Ding 058c275a72 New azure versions (#877) 2024-05-23 09:27:04 -07:00
Parham Saidi 6ff7576eb9 feature: added the latest gpt-4o to azure (#875) 2024-05-23 09:22:25 -07:00
Parham Saidi 94543decad feature: added latest gemini pro models (#876) 2024-05-23 09:21:52 -07:00
Marcus Schiesser b963782137 docs: reorder installation steps (#869) 2024-05-22 06:54:27 -07:00
github-actions[bot] 52c47cada3 Release 0.3.13 (#856)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-22 16:31:23 +07:00
Marcus Schiesser 9216312b11 docs: fix changsets and format 2024-05-22 11:25:09 +02:00
Philipp Serrer 660a2b3495 fix: text before heading in markdown reader (#864) 2024-05-22 16:49:52 +08:00
Henry Heng 6d21092805 Fix/Agent llm initialization (#866) 2024-05-21 15:35:18 -07:00
Laurie Voss fb2c1fa917 Docs update: (#857)
Co-authored-by: Yi Ding <yi.s.ding@gmail.com>
2024-05-20 13:53:23 -07:00
Parham Saidi 37525df529 feat: Gemini Access via Vertex AI (#838) 2024-05-20 17:09:25 +07:00
Marcus Schiesser a1f24753d9 docs: systemprompt changeset 2024-05-20 11:05:20 +02:00
Thuc Pham aa0f586330 feat: allow adding system prompt to chat engine (#855)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-05-20 15:57:58 +07:00
Alex Yang ff03139799 Revert "fix: cloudflare dev (#851)"
`@xenova/transformers` only ship node.js and browser output, it's not possible to load this in edge runtime and workerd

This reverts commit 34fb1d8992.
2024-05-17 12:11:31 -07:00
Marcus Schiesser 1b1081b9c9 feat: bind embedding models to vec stores and use vector store map (#821)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-05-17 22:30:33 +07:00
Thuc Pham 047ae07e74 feat: add local hugging face LLM (#854) 2024-05-17 16:01:10 +07:00
github-actions[bot] d8aa29a115 Release 0.3.12 (#852)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-16 17:45:09 -07:00
Alex Yang 34fb1d8992 fix: cloudflare dev (#851) 2024-05-16 17:25:32 -07:00
github-actions[bot] c517f35526 Release 0.3.11 (#835)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-16 16:35:57 -07:00
Alex Yang e072c45393 fix: remove non-standard API pipeline (#850) 2024-05-16 16:31:48 -07:00
Alex Yang 51241865f8 feat: improve BaseNode (#848) 2024-05-16 16:29:16 -07:00
Thuc Pham 10c83485d2 fix: allow custom task query for agents (#846) 2024-05-16 12:48:50 -07:00
Alex Yang 1e6a18ad2d build: fix jsr release 2024-05-15 18:03:22 -07:00
Alex Yang 9e133ac10d refactor: remove defaultFS from parameters (#841) 2024-05-15 17:37:51 -07:00
Alex Yang ba217eec2c chore: remove test.py (#842) 2024-05-15 16:47:39 -07:00
Alex Yang 64ef70b735 build: ignore example project 2024-05-15 16:10:08 -07:00
Alex Yang 6615aaa4ab chore: use pnpm format
Using `pnpm format:write` will cause two commits which is not expected
2024-05-15 13:11:53 -07:00
Parham Saidi 447105a6dc fix: Gemini text chat - prevent sending broken messageContent and history (#822) 2024-05-15 16:33:55 +07:00
Huu Le (Lee) 320be3fab6 chore: rollback chromadb version to 1.7.3 (#834)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-05-14 16:07:44 +07:00
Alex Yang bbd9f85a45 chore: bump openai (#833) 2024-05-13 12:53:12 -07:00
github-actions[bot] 5f29ba5e2c Release 0.3.10 (#832)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-13 10:53:59 -07:00
Alex Yang 4aba02eb82 feat: support gpt4-o (#831) 2024-05-13 10:51:10 -07:00
Alex Yang 75736ad01b build: release output files 2024-05-10 14:08:21 -07:00
Alex Yang 68a508fcd0 test: fix check host (#829) 2024-05-10 11:07:40 -07:00
github-actions[bot] 6281fc8c91 Release 0.3.9 (#828)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-09 11:16:08 -07:00
Alex Yang c3747d092a feat: add nextjs plugin for llamaindex (#824) 2024-05-09 02:29:11 -05:00
Marcus Schiesser 24a39aefb8 feat: send retrieve start and end events (#827) 2024-05-09 14:16:34 +07:00
Alex Yang 0b1299036d chore: bump version (#826) 2024-05-09 00:11:21 -05:00
Alex Yang 2c8d7941f0 ci: fix publish (#825) 2024-05-08 23:30:17 -05:00
Fabian Wimmer a1a72ab223 feat: LlamaParseReader: update Supported File Types to match python version (#823) 2024-05-09 09:51:01 +07:00
Alex Yang b99ab056d1 feat: init @llamaindex/autotool (#819) 2024-05-08 02:56:42 -05:00
github-actions[bot] 1a45b44307 Release 0.3.8 (#816)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-07 13:05:08 -05:00
JT-Dev-215 804c57519f fix: PGVector similarity score (#817) 2024-05-07 12:54:13 -05:00
Marcus Schiesser ce94780b95 feat: add page number to read PDFs (#815) 2024-05-07 10:45:55 +07:00
ezirmusitua 645fcf6c24 fix: use sha256 hash value as the Document.id_ in MarkdownReader (#768)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-05-07 10:07:39 +07:00
Marcus Schiesser e37fa5d9ca docs: add retriever tool example (#814) 2024-05-07 09:41:14 +07:00
github-actions[bot] 97e4ecd5b8 Release 0.3.7 (#812)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-05 22:11:54 -05:00
Alex Yang b6a660651b feat: allow to change ollama port (#811) 2024-05-05 19:08:00 -05:00
github-actions[bot] 456d3fb0b3 Release 0.3.6 (#810)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-05 18:40:58 -05:00
Alex Yang efa326a871 chore: update package.json and usage of lodash (#809) 2024-05-05 18:30:46 -05:00
Alex Yang 5765b637ce build: fix jsr release 2024-05-03 18:21:08 -05:00
github-actions[bot] 72687b4f69 Release 0.3.5 (#805)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-03 18:16:39 -05:00
Alex Yang 0c67e1f8f3 build: fix new version script 2024-05-03 18:13:24 -05:00
Alex Yang 4a0619758a chore: fix jsr.json 2024-05-03 18:09:05 -05:00
Alex Yang bc7a11cdbe fix: inline ollama build (#807) 2024-05-03 18:03:23 -05:00
Alex Yang 5596e31947 feat: improve @llamaindex/env (#787) 2024-05-03 18:03:14 -05:00
Alex Yang 2fe2b813ba fix: filter with multiple filters in ChromaDB (#784) 2024-05-03 17:07:45 -05:00
Alex Yang be5df5b01b fix(core): multple chat on anthropic agent (#799) 2024-05-03 16:18:46 -05:00
JT-Dev-215 e74fe88342 fix: change <-> to <=> in the SELECT query (#804)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-05-03 12:10:36 -05:00
github-actions[bot] f1862ccab1 Release 0.3.4 (#797)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-02 20:02:06 -05:00
Yi Ding 9e74a4327f feat: add top k to asQueryEngine (#801)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-05-02 19:59:36 -05:00
Alex Yang 5e61934d5a fix: remove clone object in CallbackManager.dispatchEvent (#802) 2024-05-02 19:55:41 -05:00
Alex Yang 2008efe0ee feat: add verbose mode to Agent (#800) 2024-05-02 19:54:05 -05:00
Alex Yang ee719a1fda fix: streaming for ReAct Agent (#798) 2024-05-02 18:52:18 -05:00
Alex Yang 1dce275a7c fix: export StorageContext on edge runtime (#793) 2024-05-02 14:52:16 -05:00
Thuc Pham d10533ef77 feat: add hugging face llm (#796) 2024-05-02 18:43:05 +08:00
github-actions[bot] 8aeb8ae690 Release 0.3.3 (#792)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-01 21:47:16 -05:00
Thuc Pham e8c41c5c27 fix: wrong gemini streaming chat response (#791) 2024-05-02 08:39:57 +07:00
github-actions[bot] 051b4ddfa2 Release 0.3.2 (#790)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-01 19:30:09 -05:00
Alex Yang 61103b677b fix: streaming for Agent.createTask (#788) 2024-05-01 19:26:06 -05:00
Alex Yang e69cac672a docs: update blog post 2024-05-01 13:01:55 -05:00
Alex Yang 94246a3ca8 chore: bump jsr.json 2024-05-01 12:59:03 -05:00
github-actions[bot] b440a008e5 Release 0.3.1 (#786)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-05-01 12:39:37 -05:00
Alex Yang 46227f2a70 fix: build error on next.js nodejs runtime (#785) 2024-05-01 12:37:43 -05:00
Alex Yang 77f0298f6f chore: update jsr.json 2024-04-30 22:47:09 -05:00
github-actions[bot] c14e112236 Release 0.3.0 (#783)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-04-30 22:46:10 -05:00
Alex Yang 62b035fdc1 build: fix test package naming 2024-04-30 22:42:06 -05:00
Alex Yang aa0be1469b build: update expectedMinorVersion 2024-04-30 22:37:14 -05:00
Alex Yang 5016f21d52 feat(core): better next.js/cloudflare/vite support 2024-04-30 22:34:54 -05:00
Marcus Schiesser 130b7992a1 refactor: clean gemini embedding (#781) 2024-04-30 10:51:22 +07:00
Yi Ding 0d50b22dbf fix(core): add more exports on llm/index (#780) 2024-04-28 20:43:14 -05:00
Alex Yang db1d1f57c9 build(wasm-tools): fix type check 2024-04-28 20:29:01 -05:00
Alex Yang dccb8163d8 fix(core): polyfill Web Stream APIs (#777) 2024-04-28 18:35:33 -05:00
Fabian Wimmer 1ab3ba407e feat: add Language and parsingInstruction to LlamaParseReader (#779)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-04-28 17:00:58 -05:00
Alex Yang b03f765733 chore: update husky script (#776) 2024-04-27 01:10:34 -05:00
Alex Yang 7488d3c235 fix: agent callback with step infomation (#774) 2024-04-26 18:13:05 -05:00
github-actions[bot] 5cb270d07f Release 0.2.13 (#773)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-04-26 13:26:12 -05:00
Alex Yang 62771058aa fix: empty tools (#772) 2024-04-26 13:10:57 -05:00
github-actions[bot] ca348a6570 Release 0.2.12 (#770)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-04-26 13:11:23 +07:00
Marcus Schiesser 44a7fd72e8 ci: publish github release on tag pushes (#771) 2024-04-26 13:09:25 +07:00
Thuc Pham d8d952d937 feat: init gemini llm (#769) 2024-04-26 11:04:33 +07:00
github-actions[bot] 216ba1f22b Release 0.2.11 (#765)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2024-04-25 17:53:17 -07:00
Marcus Schiesser 74686f5776 ci: add version to release PR (#766) 2024-04-25 10:55:02 +07:00
Marcus Schiesser 1ebf9e67a4 ci: add release action (#764) 2024-04-25 10:09:55 +07:00
Alex Yang aeefc77da0 test: load large amount of data won't cause error (#762) 2024-04-24 15:04:29 -05:00
ezirmusitua 13d8d7cbbe fix: use Array.prototype.flat (#760)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-04-24 14:36:12 -05:00
Alex Yang 9c34e44b85 ci: coverage node.js 22 (#761) 2024-04-24 14:19:12 -05:00
Thuc Pham cb2dc802d9 docs: update next config for external packages (#759) 2024-04-24 17:27:20 +08:00
Ziniu Yu 5a6cc0e32e feat: support jina ai embedding and reranker (#734) 2024-04-24 15:45:36 +07:00
Marcus Schiesser a63256eb84 feat: add default file metadata (#758) 2024-04-24 13:54:29 +07:00
Alex Yang 0a160b97a0 fix(docs): api generation (#756) 2024-04-23 14:24:17 -05:00
Thuc Pham 95602c7959 feat: overide generate hash function for image document (#751)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-04-23 11:56:37 +07:00
Alex Yang 20bc466ca1 chore: bump notion reader (#753) 2024-04-22 15:14:06 -05:00
Thuc Pham efb1c56ba5 fix: return buffer when loading image data (#749) 2024-04-22 15:28:19 +07:00
Alex Yang 286499388d fix: agent class should implement ChatEngine interface (#746) 2024-04-22 02:13:29 -05:00
Alex Yang 460c6574cc fix: rename ReACTAgent to ReActAgent (#748) 2024-04-22 00:57:43 -05:00
Marcus Schiesser 8b0e0e3cc8 docs: use dedicated embedding model for ollama (#745) 2024-04-22 10:40:39 +07:00
Alex Yang 87142b29fa chore: update changeset 2024-04-21 20:32:57 -05:00
Alex Yang 501b844f0f refactor: use official ollama sdk (#744) 2024-04-21 20:31:16 -05:00
Alex Yang 03157dc295 feat: use json format for tool result (#742) 2024-04-21 19:27:10 -05:00
Alex Yang ef80b684f7 chore: fix llamaindex node_modules link (#743) 2024-04-21 18:21:15 -05:00
Alex Yang 472e70feee refactor: full typed & iterator of agent worker/runner (part 3) (#728)
Fixes: https://github.com/run-llama/LlamaIndexTS/issues/692, https://github.com/run-llama/LlamaIndexTS/issues/557

Refs: https://github.com/run-llama/llama_index/blob/5a6ffe32faa75db0b4737d1e7a85e6fe4afe94af/docs/module_guides/deploying/agents/agent_runner.md
2024-04-19 17:52:36 -05:00
Alex Yang cfb90f7666 docs: update (#738) 2024-04-19 15:17:48 -05:00
Mike Fortman 2e3a287a27 refactor: astra options (#737) 2024-04-19 11:57:34 -05:00
Marcus Schiesser 635fbb8618 release 0.2.10 2024-04-19 16:14:44 +08:00
Marcus Schiesser d2d34acb31 Add streaming for replicate (Llama 3) (#735) 2024-04-19 15:09:20 +07:00
Yi Ding cf70edbede llama 3 support (#731)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-04-18 17:08:40 -07:00
Mike Fortman 79b7d246bd chore: update deps Astra (#733) 2024-04-18 17:55:31 -05:00
Marcus Schiesser bcc3d0b4d1 release v0.2.9 2024-04-17 13:53:31 +08:00
Marcus Schiesser 238ca86534 fix: google fonts not reachable during build 2024-04-17 13:47:11 +08:00
Marcus Schiesser 1f3efe8947 fix: ensure to use build for examples (#729) 2024-04-17 10:40:02 +07:00
yemiscale3 89324b4067 docs: Add Langtrace to observability tools (#726)
Co-authored-by: Yi Ding <yi.s.ding@gmail.com>
2024-04-16 20:13:59 -07:00
Alex Yang 8cc848aee6 docs: fix example code (#727) 2024-04-16 16:00:26 -05:00
Alex Yang cd54a7a66b docs: remove verbose (#725) 2024-04-16 15:54:40 -05:00
Marcus Schiesser dca02f7277 refactor: VectorStoreIndex: use TransformerComponent to calc embeddings (#721) 2024-04-16 10:01:26 +07:00
Marcus Schiesser b757fa9aa3 fix: type-check of modified example 2024-04-16 10:35:26 +08:00
Marcus Schiesser bc594a0674 doc: update vector index example to show source nodes 2024-04-16 10:27:34 +08:00
Alex Yang 208282d62f feat: init anthropic agent (part 2) (#719) 2024-04-15 16:22:47 -05:00
Wessel 060880abfe fix: toolretriever for Agent OpenAI broken (#718) 2024-04-15 13:45:19 -05:00
Marcus Schiesser 728b35e774 chore: remove LLM.ts (#720) 2024-04-14 23:35:15 -05:00
Alex Yang bdaa043404 feat: init claude function call (part 1) (#717) 2024-04-14 15:55:34 -05:00
Alex Yang a55cf8d870 fix: type import 2024-04-14 01:30:54 -05:00
Alex Yang cf4244fd3a chore: put eslint into top level (#716) 2024-04-13 20:39:27 -05:00
Marcus Schiesser 76c3fd64ad feat: add scores to source nodes (#714) 2024-04-12 09:28:46 -07:00
Marcus Schiesser 701e0ac2be release 0.2.8 2024-04-12 12:43:45 +08:00
Alex Yang a285f8ba3a feat: improve ToolsFactory type (#713) 2024-04-11 21:26:14 -05:00
Alex Yang 663821cdf6 test: add openai agent stream chat (#712) 2024-04-11 19:21:02 -05:00
Alex Yang c4b95494ac fix: memory type (#711) 2024-04-11 18:11:33 -05:00
Marcus Schiesser 980fb4e5a3 release llamaindex@0.2.7 2024-04-11 14:57:01 +08:00
Alex Yang 96f8f40291 fix: agent stream (#710) 2024-04-10 23:22:11 -05:00
Alex Yang 1c698df6e0 fix: package.json version 2024-04-10 19:49:16 -05:00
Alex Yang 298cb433be feat: improve base tool type (#709) 2024-04-10 19:40:47 -05:00
Yi Ding 63af7dd99d Fix protobuf (#708) 2024-04-10 17:20:32 -07:00
Alex Yang af5df1d083 feat: add llm-stream event (#707) 2024-04-10 09:26:26 -05:00
Marcus Schiesser a3b44093c2 fix: agent streaming with new OpenAI models (#706)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-04-10 08:38:54 -05:00
Alex Yang c80bf3311f fix: response.raw should be null (#705) 2024-04-10 02:54:36 -05:00
Alex Yang 7940d249b0 test: coverage on mock mode (#704) 2024-04-10 02:40:37 -05:00
Marcus Schiesser 4a07c81f71 release llamaindex@0.2.5 2024-04-10 15:01:10 +08:00
Marcus Schiesser 7d56cdf045 fix: Allow OpenAIAgent to be called without tools (#703) 2024-04-10 13:43:38 +07:00
Marcus Schiesser 0affe621d5 ci: update pnpm lockfile after updating package.json from edge 2024-04-10 11:46:01 +08:00
Alex Yang 93932b1a9c refactor: chat message type (#701) 2024-04-09 21:56:47 -05:00
Yi Ding a87f13b9d2 release 2024-04-09 16:23:29 -07:00
Yi Ding 8d2b21ee75 update mistral (#700) 2024-04-09 16:19:51 -07:00
Yi Ding 87741c9be8 update example packages 2024-04-09 13:22:03 -07:00
Yi Ding 171cb89170 security update (docs) 2024-04-09 13:17:44 -07:00
Yi Ding 5dad867bbe update packages 2024-04-09 13:04:43 -07:00
Yi Ding 13f26fd84d pnpm version 2024-04-09 12:45:12 -07:00
Yi Ding 3bc77f7d7f gpt-4-turbo GA (#698) 2024-04-09 12:42:16 -07:00
Alex Yang aac1ee3af3 e2e: init llamaindex e2e test (#697) 2024-04-06 23:57:21 -05:00
Alex Yang e85893ac0f fix: message content type (#696) 2024-04-06 18:59:12 -05:00
Alex Yang 315947ee6f refactor: move anthropic class (#695) 2024-04-06 17:13:53 -05:00
Alex Yang 23a0d44b11 fix: jsr disallow global type 2024-04-06 17:09:39 -05:00
Alex Yang 3b501de057 chore: jsr release 2024-04-06 17:04:20 -05:00
Alex Yang 6cc645aa2a refactor: improve agent type (#694) 2024-04-05 15:21:49 -05:00
Marcus Schiesser 0b37207adc Release llamaindex@0.2.3 2024-04-05 15:15:39 +08:00
Marcus Schiesser f0704ec705 Add streaming for OpenAI agents (#693) 2024-04-05 12:53:26 +07:00
Thuc Pham 4fcbdf710e Add tool calls for openai streaming (#682)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-04-05 08:33:23 +07:00
Marcus Schiesser 866149193a fix: use LLM's context window to specify agent's token limit (#689) 2024-04-03 17:04:35 -05:00
Thuc Pham 6ffb161618 feat: add ts eslint plugin (#688) 2024-04-03 14:21:13 +07:00
Marcus Schiesser 8e4b49824b doc: document docstore strategies (#690) 2024-04-03 13:26:38 +07:00
Alex Yang 5263576de1 ci: test matrix on nodejs 18/20/21 (#687) 2024-04-02 17:23:11 -05:00
WarlaxZ 6d4e2ea0e9 fix: dynamic import cjs module pg (#685)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-04-02 16:07:13 -05:00
Emanuel Ferreira 3cbfa98e6b feat: LlamaCloudIndex from documents (#677) 2024-04-02 14:03:45 -03:00
Alex Yang d256cbe0e0 refactor: use event.reason, remove parentEvent (#681) 2024-04-01 17:03:39 -07:00
Alex Yang a6dfa30dcf RELEASING: Releasing 3 package(s) 2024-04-01 14:34:40 -05:00
Alex Yang d0365dc434 fix: docs dependencies (#680) 2024-04-01 14:19:37 -05:00
Alex Yang aa41432bbb refactor: remove llm.tokens api (#679) 2024-04-01 14:12:17 -05:00
Emanuel Ferreira 98a2b4a547 feat: add global settings (#668)
Co-authored-by: Alex Yang <himself65@outlook.com>
2024-04-01 13:43:35 -05:00
Benny 806ce9a360 fix: README links and examples (#678) 2024-04-01 13:16:10 -05:00
Marcus Schiesser 8b28092cc8 feat: Add doc store strategies to VectorStoreIndex.fromDocuments (#646) 2024-04-01 10:12:08 -07:00
Marcus Schiesser 5c5f4c1c84 Revert "feat: support calculate llama 2 tokens (#676)"
This reverts commit 041acd11fe.
2024-04-01 13:52:07 +08:00
Marcus Schiesser 949d330295 fix: typecheck 2024-04-01 12:26:22 +08:00
Marcus Schiesser 9a5ee4f37a Revert "fix: support import subdirectory (#655)"
This reverts commit 98d4cbdf95.
2024-04-01 11:52:41 +08:00
Alex Yang 7a23cc6c84 feat: improve callback manager (#675) 2024-03-31 15:34:48 -05:00
Alex Yang 041acd11fe feat: support calculate llama 2 tokens (#676) 2024-03-29 20:12:26 -05:00
Emanuel Ferreira 24b4033db9 feat: add result type json (#673) 2024-03-28 16:24:33 -03:00
Emanuel Ferreira 1115f83b8f fix: pipeline not found (#672) 2024-03-28 15:31:18 -03:00
Thuc Pham 60a1603636 fix: make edge run build after core (#670) 2024-03-28 18:26:35 +08:00
Peter Goldstein ea467fa031 Update to latest supported version list as of 2024-04-02. (#669) 2024-03-28 10:53:33 +07:00
Marcus Schiesser b0e6f73b1d docs: update readme for Edge runtime 2024-03-26 15:18:19 +08:00
Marcus Schiesser 6d9e015b5e feat: use claude3 with react agent (#661)
Co-authored-by: Emanuel Ferreira <contatoferreirads@gmail.com>
2024-03-22 09:25:31 -03:00
Thuc Pham fececd89ab feat: add tool factory (#663) 2024-03-22 14:40:41 +07:00
Marcus Schiesser 48e287892f test: use unique tmp dir for storage tests and wait to clean VectorStoreIndex files 2024-03-21 13:04:25 +07:00
Marcus Schiesser f118400820 docs: Add changeset instructions for PRs 2024-03-20 11:45:33 +07:00
Marcus Schiesser 3f8407c7af docs: changeset for pipeline.register added 2024-03-20 10:20:30 +07:00
Marcus Schiesser 83317739c7 feat: add pipeline.register (#589) 2024-03-19 13:32:32 -07:00
Thuc Pham 0b665bd1ca feat: add wikipedia tool (#648)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-03-19 11:31:08 +07:00
Alex Yang 98d4cbdf95 fix: support import subdirectory (#655) 2024-03-18 21:00:46 -05:00
Marcus Schiesser 6cb75b54a0 docs: update release process 2024-03-18 16:22:59 +07:00
Marcus Schiesser 53edfe93cf release llamaindex@0.2.1 2024-03-18 16:17:58 +07:00
Marcus Schiesser b856deae43 fix: fix syncing edge with core version 2024-03-18 15:53:31 +07:00
Marcus Schiesser 259c842259 Support NextJS edge runtime (#618) 2024-03-18 15:13:27 +07:00
shodevacc ffb195ea7a Fix: Metadata filters doesn't seem to work for Qdrant (#623) 2024-03-18 11:53:51 +07:00
Alex Yang b4677534d1 ci: install node_modules (#653) 2024-03-18 12:49:28 +08:00
Peli de Halleux f967b82467 [docs] missing await in sample (#650) 2024-03-15 16:23:27 -03:00
Marcus Schiesser c81946930e test: fix openai mock 2024-03-15 15:20:57 +07:00
Marcus Schiesser 1008b775a4 test: cleaned up tests and added test to ignore duplicates 2024-03-15 12:05:58 +07:00
Huu Le (Lee) 41210dfc51 feat: Add auto create collection and node metadata for Milvus vector store (#645) 2024-03-15 10:46:25 +07:00
Emanuel Ferreira 67b7272249 feat: expected minor version (#644) 2024-03-14 09:34:21 -03:00
Marcus Schiesser 964e045903 feat: add support for snapshots 2024-03-14 10:23:58 +07:00
Marcus Schiesser 137cf67f40 fix: Use Pinecone namespaces for all operations (#633) 2024-03-14 10:15:52 +07:00
Emanuel Ferreira 309a526e3c RELEASING: Releasing 5 package(s) (#643) 2024-03-13 22:17:27 -03:00
yisding dd95927498 Claude haiku (#642) 2024-03-13 19:57:45 -03:00
Thuc Pham 4f72feae91 Feat: add tools module (#621) 2024-03-13 16:41:36 +07:00
Marcus Schiesser 3cd8f9f597 refactor: move create-llama to own repo (#641) 2024-03-13 15:53:33 +07:00
Huu Le (Lee) d2e8d0c62a feat: Add Milvus vector store (#640)
Co-authored-by: Michael Schramm <michael@tucan.ai>
2024-03-13 13:55:48 +07:00
Huu Le (Lee) fafbd8c9c7 fix: add missing env value; improve docs and error message (#638) 2024-03-13 09:08:53 +07:00
Marcus Schiesser a40c91b054 docs: fixed path 2024-03-12 14:45:27 +07:00
Marcus Schiesser 98894055c6 fix: create-llama release 2024-03-12 13:42:38 +07:00
Marcus Schiesser 4589a84643 RELEASING: Releasing 1 package(s)
Releases:
  create-llama@0.0.28

[skip ci]
2024-03-12 13:41:36 +07:00
Huu Le (Lee) e6b7f52d3e fix: add missing check env logic (#636) 2024-03-12 12:29:00 +07:00
Marcus Schiesser b169db617a refactor: use a function for webpack config (#634) 2024-03-12 11:10:31 +07:00
Huu Le (Lee) 89a49f4f4f feat: Add more. env variables to config host, port, llm and embedding (#630) 2024-03-12 09:22:21 +07:00
Marcus Schiesser 58490715fe refactor: clean nextjs config generation (use JSON) (#631) 2024-03-11 14:16:15 +07:00
Huu Le (Lee) 4c2283c4e5 fix: Rename folder e2e/.cache to e2e/cache (#632) 2024-03-11 14:15:13 +07:00
Eka Prasetia a059070dec docs: Fix typo in transformations.md (#625) 2024-03-11 12:16:23 +07:00
Emanuel Ferreira 20dfeb4cfa chore: remove comment (#624) 2024-03-08 15:54:24 -03:00
Emanuel Ferreira aefc3266c1 feat: experimental package + json query engine (#613) 2024-03-07 14:34:55 -03:00
Huu Le (Lee) fdf48dd459 feat: Add start in VSCode option and support python for dev container (#619) 2024-03-07 17:19:08 +07:00
Alex Yang 66525346a2 build: use single swc config (#620) 2024-03-06 23:41:42 -06:00
Alex Yang c9b2ec4a2b fix: release 2024-03-06 23:32:02 -06:00
Marcus Schiesser bf583a7266 Use parameter object for retrieve function of Retriever (#616) 2024-03-06 21:15:22 -08:00
Marcus Schiesser de194d1c73 fix: running new-create-llama 2024-03-06 15:13:20 +07:00
Marcus Schiesser ecdc289df1 RELEASING: Releasing 1 package(s)
Releases:
  create-llama@0.0.27

[skip ci]
2024-03-06 15:11:47 +07:00
Marcus Schiesser 9e198ac40d fix: build types for core locally (#615) 2024-03-06 14:35:31 +07:00
Huu Le (Lee) 0a06998690 fix: hardcode "en" as default language for llama-parse and use llama cloud key from env (#614) 2024-03-06 14:31:21 +07:00
Wojciech Grzebieniowski 484a7105a9 fix: restore missing exports (#610) 2024-03-05 14:56:25 -06:00
Alex Yang 8d18ea167b fix: publish.yml 2024-03-05 14:37:54 -06:00
Alex Yang a2ca89bfe0 fix: config (#611) 2024-03-05 14:20:58 -06:00
Alex Yang edeea40898 ci: add publish.yml 2024-03-05 13:49:49 -06:00
Alex Yang 2a7080b094 build: fix version 2024-03-05 12:26:47 -06:00
Huu Le (Lee) b354f2386b feat: add embedding model option to create-llama (#608) 2024-03-05 16:59:51 +07:00
Emanuel Ferreira d766bd03d2 feat: OpenAI Agent Stream (#597) 2024-03-05 15:46:44 +07:00
Huu Le (Lee) 6a69148356 fix: add --no-llama-parse and improve e2e test (#607) 2024-03-05 14:57:38 +07:00
Marcus Schiesser e1e1b0b522 RELEASING: Releasing 1 package(s)
Releases:
  llamaindex@0.1.21

[skip ci]
2024-03-05 13:00:16 +07:00
Marcus Schiesser d824876653 docs(changeset): Add support for Claude 3 2024-03-05 12:59:51 +07:00
Marcus Schiesser 2048698f77 docs: add interactive chat for anthropic 2024-03-05 11:15:50 +07:00
Emanuel Ferreira 9942979aa7 feat: Claude 3 (#604) 2024-03-04 15:02:18 -08:00
Alex Yang 3c2655a1f9 fix: .tsbuildinfo 2024-03-04 16:05:45 -06:00
Marcus Schiesser 552a61a66f Add quantized parameter to HuggingFaceEmbedding (#601) 2024-03-04 12:10:40 +07:00
Alex Yang d13143e322 RELEASING: Releasing 3 package(s)
Releases:
  llamaindex@0.1.20
  @llamaindex/env@0.0.5
  docs@0.0.4

[skip ci]
2024-03-02 18:42:24 -06:00
Alex Yang 5116ad8d08 fix: compatibility issue with Deno (#598) 2024-03-02 18:40:01 -06:00
Emanuel Ferreira 64683a55f3 fix: prefix messages always true (#596) 2024-03-01 21:45:02 -03:00
Emanuel Ferreira 698cd9c631 fix: step wise agent + examples (#594) 2024-03-01 21:28:02 -03:00
Alex Yang c744a99102 chore: bump @llamaindex/cloud (#595) 2024-03-01 17:22:50 -06:00
Huu Le (Lee) 2d2935085e feat: Add use LlamaParse option to create-llama (#591) 2024-03-01 16:54:06 +07:00
Marcus Schiesser 1b31e2c8cd chore: update @llamaindex/cloud to 0.0.2 2024-03-01 15:59:10 +07:00
Thuc Pham 7257751993 fix: empty store bugs (#592)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-03-01 15:04:10 +07:00
Marcus Schiesser de6bfdb1b1 RELEASING: Releasing 1 package(s)
Releases:
  llamaindex@0.1.19

[skip ci]
2024-02-29 15:35:13 +07:00
Marcus Schiesser 9e49f4411b fix: copy README and license 2024-02-29 15:34:27 +07:00
Thuc Pham 026d068ddf feat: enhance pinecone usage (#586) 2024-02-29 15:34:08 +07:00
Marcus Schiesser 7055d6fc3c docs: add OpenAIEmbedding to examples 2024-02-29 11:11:43 +07:00
Alex Yang e9c2366bf1 fix: allow passing model metadata (#588) 2024-02-29 10:41:06 +07:00
Alex Yang 6278152e49 fix: lazy import pg (#584) 2024-02-27 19:16:54 -06:00
Emanuel Ferreira 76010c0cea chore: remove duplicated example and minor example update (#582) 2024-02-27 09:02:37 -03:00
Emanuel Ferreira 889b84cfb9 docs: remove query engine from correctness evaluator (#581) 2024-02-27 08:15:41 -03:00
Marcus Schiesser a26681c416 RELEASING: Releasing 1 package(s)
Releases:
  llamaindex@0.1.18

[skip ci]
2024-02-27 13:45:28 +07:00
Thuc Pham 90027a7b44 fix: enable split long sentence by default (#568)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-02-27 13:44:04 +07:00
Emanuel Ferreira aab56faf88 refactor: qdrant minor updates (#580) 2024-02-26 22:13:45 -03:00
Emanuel Ferreira c57bd11c45 feat: update and refactor title extractor (#579) 2024-02-26 21:49:07 -03:00
Alex Yang 3fa1e29468 RELEASING: Releasing 3 package(s)
Releases:
  llamaindex@0.1.17
  @llamaindex/env@0.0.4
  docs@0.0.3

[skip ci]
2024-02-26 17:01:47 -06:00
Alex Yang cf87f84900 fix: type backward compatibility (#578) 2024-02-26 16:59:09 -06:00
Alex Yang 402d4ef013 docs: update tutorial (#576) 2024-02-26 14:11:09 -06:00
Alex Yang fc94906a1e fix: keep dynamic import in cjs (#575) 2024-02-26 12:27:17 -06:00
Alex Yang b83fcd11e4 fix(core): type generation (#574) 2024-02-26 12:15:40 -06:00
Emanuel Ferreira c28af7c7bc chore: remove storage context from multi_doc_agent example (#572) 2024-02-26 12:05:30 -03:00
Emanuel Ferreira dbc853bcc5 chore: fix paths and docs (#569) 2024-02-26 10:37:08 -03:00
Emanuel Ferreira c8396c5a3c feat: add base evaluator and correctness evaluator (#559) 2024-02-26 09:38:56 -03:00
Thuc Pham 65af8d3a26 fix: missing dependency for local development (#566) 2024-02-26 15:54:47 +07:00
Marcus Schiesser 329b6ec958 fix: SummaryIndex and VectorStoreIndex must be able to share storage context (#567) 2024-02-26 15:52:33 +07:00
Graden Rea 09bf27abd7 feat: Add Groq LLM integration (#561) 2024-02-26 13:46:27 +07:00
Alex Yang 2ec6a529c7 RELEASING: Releasing 2 package(s)
Releases:
  llamaindex@0.1.16
  @llamaindex/env@0.0.3

[skip ci]
2024-02-23 19:03:04 -06:00
Alex Yang e8e21a0e4e docs(changeset): build: set files in package.json 2024-02-23 19:02:42 -06:00
Alex Yang 88d243f145 RELEASING: Releasing 1 package(s)
Releases:
  llamaindex@0.1.15

[skip ci]
2024-02-23 18:57:10 -06:00
Alex Yang 3a6e287443 feat: enable verbatimModuleSyntax (#562) 2024-02-23 18:56:44 -06:00
Alex Yang beb3e5cd7f RELEASING: Releasing 2 package(s)
Releases:
  llamaindex@0.1.14
  @llamaindex/env@0.0.2

[skip ci]
2024-02-23 18:09:31 -06:00
Alex Yang 7416a87e10 build: cjs file not found 2024-02-23 18:09:15 -06:00
Alex Yang 65b85b237e RELEASING: Releasing 1 package(s)
Releases:
  llamaindex@0.1.13

[skip ci]
2024-02-23 17:59:06 -06:00
Alex Yang b17a80014a fix: unset private package 2024-02-23 17:58:46 -06:00
Alex Yang ff87f99807 fix: avoid publishing test package 2024-02-23 17:56:38 -06:00
Alex Yang 65d834615d docs(changeset): feat: abstract @llamaindex/env package 2024-02-23 17:45:43 -06:00
Alex Yang b8be4c09e2 docs(changeset): build: use ESM as default 2024-02-23 17:45:01 -06:00
Alex Yang e5fb332538 build: leave code as-is (#560)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-02-23 17:39:25 -06:00
Marcus Schiesser 491033d534 fix: lint errors 2024-02-23 14:55:45 +07:00
Marcus Schiesser 885fa316a5 chore: add prefer const lint 2024-02-23 14:45:17 +07:00
Marcus Schiesser b6ed679771 RELEASING: Releasing 1 package(s)
Releases:
  create-llama@0.0.26

[skip ci]
2024-02-23 12:00:37 +07:00
Marcus Schiesser 68fc6e8b50 fix: don't need similarityTopK parameter for LlamaCloud 2024-02-23 11:43:22 +07:00
Marcus Schiesser ea0331ef5a refactor: simplify generated python code (#558)
Co-authored-by: leehuwuj <leehuwuj@gmail.com>
2024-02-23 11:14:02 +07:00
Marcus Schiesser 6827e245b8 fix: don't allow runApp for LlamaPacks 2024-02-22 16:20:57 +07:00
Huu Le (Lee) ef25d6960c Upgrade llama-index version to v0.10+ for create-llama (#556) 2024-02-22 13:50:53 +07:00
Marcus Schiesser f740f44cf2 RELEASING: Releasing 1 package(s)
Releases:
  llamaindex@0.1.12

[skip ci]
2024-02-22 12:02:35 +07:00
Marcus Schiesser a5e4e6d857 Add support for LlamaCloud (#554) 2024-02-22 11:59:32 +07:00
Thuc Pham cfdd6db530 feat: add pinecone support to create llama (#555) 2024-02-22 09:55:50 +07:00
Marcus Schiesser d4eda9f396 docs: add llamaparse docs (#553) 2024-02-21 14:37:13 +07:00
Alex Yang a433b107e0 RELEASING: Releasing 1 package(s)
Releases:
  llamaindex@0.1.11

[skip ci]
2024-02-20 12:58:54 -06:00
Yufei (Benny) Chen 59f9fb6c3f Add Fireworks to LlamaIndex (#539)
Co-authored-by: Emanuel Ferreira <contatoferreirads@gmail.com>
2024-02-20 10:53:09 -03:00
Thuc Pham 09d532ebcc feat(create-llama-pack): generate llama pack project from llama index (#549) 2024-02-20 08:22:54 +07:00
Emanuel Ferreira cfd6f3ca8c feat: prompt mixin (#543) 2024-02-18 18:44:08 -03:00
Emanuel Ferreira 95add73c38 feat: multi-document agents (#531) 2024-02-18 18:43:52 -03:00
Emanuel Ferreira 9ee036b160 docs: remove duplicate embedding (#545) 2024-02-13 23:21:13 -03:00
Erick Sosa Garcia c2b521199c fix: some errors in available llms examples (#544) 2024-02-13 21:16:47 -03:00
Emanuel Ferreira ee9f3f373a refactor: openai agent and utils (#542) 2024-02-11 20:24:36 -03:00
Emanuel Ferreira f205358587 feat: add markdown node parser (#541) 2024-02-11 20:23:49 -03:00
Emanuel Ferreira 255ae7dced fix: react agent history (#540) 2024-02-11 18:46:55 -03:00
Emanuel Ferreira b4c6d509a0 docs: available embeddings (#538) 2024-02-10 22:10:20 -03:00
Emanuel Ferreira 34cd57b639 feat(react): add react agent (#511) 2024-02-10 20:52:11 -03:00
yisding 50dfd7bf60 dep security vulns (#537) 2024-02-11 04:37:42 +08:00
Emanuel Ferreira 0b57187909 docs: add available LLMs (#536) 2024-02-10 13:54:13 -03:00
Emanuel Ferreira e78e9f4832 feat(reranker): cohere reranker (#535) 2024-02-10 12:07:14 -03:00
Marcus Schiesser 383933adb5 feat: Add reader for LlamaParse (#530) 2024-02-09 11:27:50 +07:00
Marcus Schiesser dd054137bf feat: use batching in vector store index (#524)
Co-authored-by: Alex Yang <himself65@outlook.com>
Co-authored-by: Emanuel Ferreira <contatoferreirads@gmail.com>
2024-02-08 08:59:56 -03:00
byteninja cf3b7571eb feat: add filtering of metadata to PGVectorStore (#525) 2024-02-08 10:54:52 +07:00
Alex Yang ae7a2c202a fix: add alias class OllamaEmbedding (#527) 2024-02-07 14:26:39 -06:00
Alex Yang 9b00d578bc feat: improve reader interfaces (#498) 2024-02-07 11:44:01 -06:00
Marcus Schiesser b8173e4c4e RELEASING: Releasing 1 package(s)
Releases:
  create-llama@0.0.25

[skip ci]
2024-02-07 16:53:46 +07:00
Marcus Schiesser 67b5445fb9 fix(cl): improved error messages for python installation 2024-02-07 16:16:06 +07:00
Marcus Schiesser 87419ef5d1 Revert "fix: add handle error from template installation (#522)"
This reverts commit ad218160d8.
2024-02-07 16:01:08 +07:00
Huu Le (Lee) ad218160d8 fix: add handle error from template installation (#522)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-02-07 15:30:26 +07:00
Marcus Schiesser eeb90d7991 fix(cl): add link to configure search tool 2024-02-07 14:07:57 +07:00
Marcus Schiesser 7b7329bd18 feat(cl): Added latest turbo models for GPT-3.5 and GPT 4 2024-02-07 12:46:19 +07:00
Alex Yang b3acbb06f4 docs: update CONTRIBUTING.md (#516) 2024-02-07 12:05:29 +07:00
Marcus Schiesser 7db7562841 fix(cl): just retrieve top-k 3 for context to prevent token exceed 2024-02-07 10:59:31 +07:00
yisding 0e75b124c3 minor update 2024-02-06 12:24:06 -08:00
yisding d79a0b76f3 update packages 2024-02-06 11:55:38 -08:00
yisding c3eb4933fb RELEASING: Releasing 1 package(s)
Releases:
  llamaindex@0.1.10

[skip ci]
2024-02-06 11:50:39 -08:00
yisding e3a956aedd pnpm install 2024-02-06 11:48:12 -08:00
yisding e562e479dc Merge branch 'main' of github.com:run-llama/LlamaIndexTS 2024-02-06 11:39:07 -08:00
Alex Yang 1900e019e3 build: fix build errors (#521) 2024-02-06 12:54:08 -06:00
Emanuel Ferreira 317f140822 fix: revert embed batch temporarily (#520) 2024-02-06 12:01:48 -03:00
Emanuel Ferreira cd829474d6 feat(queryEngineTool): add query engine tool to agents (#509) 2024-02-06 11:11:26 -03:00
Emanuel Ferreira b6c1500570 feat(embedding): add batch embed size (#407) 2024-02-06 10:19:14 -03:00
Huu Le (Lee) d06a85bd34 feat: Add support for llamahub tools (#517)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-02-06 17:34:03 +07:00
Ian Sinnott 6b9a2feac5 Consistent Document IDs in NotionReader.ts (#519) 2024-02-06 15:52:29 +07:00
Mike Fortman bd08004afe Update Astra DB Vectorstore to support namespaces (#485)
Co-authored-by: Marcus Schiesser <mail@marcusschiesser.de>
2024-02-06 11:31:08 +07:00
yisding 36f2903eb3 RELEASING: Releasing 1 package(s)
Releases:
  llamaindex@0.1.9

[skip ci]
2024-02-02 11:26:00 -08:00
yisding 09464e6da7 docs(changeset): add OpenAIAgent (thanks @EmanuelCampos) 2024-02-02 11:23:03 -08:00
3056 changed files with 211338 additions and 123187 deletions
+1 -1
View File
@@ -1,7 +1,7 @@
{
"$schema": "https://unpkg.com/@changesets/config@2.3.1/schema.json",
"changelog": "@changesets/cli/changelog",
"commit": true,
"commit": false,
"fixed": [],
"linked": [],
"access": "public",
-5
View File
@@ -1,5 +0,0 @@
---
"llamaindex": patch
---
fix: update `VectorIndexRetriever` constructor parameters' type.
+16
View File
@@ -0,0 +1,16 @@
{
"jsc": {
"parser": {
"syntax": "typescript",
"decorators": true
},
"target": "esnext",
"transform": {
"decoratorVersion": "2022-03"
}
},
"module": {
"type": "commonjs",
"ignoreDynamic": true
}
}
+2 -2
View File
@@ -4,6 +4,6 @@
"ghcr.io/devcontainers/features/node:1": {},
"ghcr.io/devcontainers-contrib/features/turborepo-npm:1": {},
"ghcr.io/devcontainers-contrib/features/typescript:2": {},
"ghcr.io/devcontainers-contrib/features/pnpm:2": {},
},
"ghcr.io/devcontainers-contrib/features/pnpm:2": {}
}
}
-14
View File
@@ -1,14 +0,0 @@
module.exports = {
root: true,
// This tells ESLint to load the config from the package `eslint-config-custom`
extends: ["custom"],
settings: {
next: {
rootDir: ["apps/*/"],
},
},
rules: {
"max-params": ["error", 4],
},
ignorePatterns: ["dist/"],
};
+2
View File
@@ -0,0 +1,2 @@
examples/readers/data/** binary
examples/data/** binary
+46
View File
@@ -0,0 +1,46 @@
---
name: Bug report
about: Create a report to help us improve
title: ""
labels: bug
assignees: ""
---
**Describe the bug**
A clear and concise description of what the bug is.
**To Reproduce**
Code to reproduce the behavior:
```ts
// paste the code here
```
**Expected behavior**
A clear and concise description of what you expected to happen.
**Screenshots**
If applicable, add screenshots to help explain your problem.
**Desktop (please complete the following information):**
- OS: [e.g. macOS, Linux]
- JS Runtime / Framework / Bundler (select all applicable)
- [ ] Node.js
- [ ] Deno
- [ ] Bun
- [ ] Next.js
- [ ] ESBuild
- [ ] Rollup
- [ ] Webpack
- [ ] Turbopack
- [ ] Vite
- [ ] Waku
- [ ] Edge Runtime
- [ ] AWS Lambda
- [ ] Cloudflare Worker
- [ ] Others (please elaborate on this)
- Version [e.g. 22]
**Additional context**
Add any other context about the problem here.
-68
View File
@@ -1,68 +0,0 @@
name: E2E Tests
on:
push:
branches: [main]
pull_request:
paths:
- "packages/create-llama/**"
- ".github/workflows/e2e.yml"
branches: [main]
env:
POETRY_VERSION: "1.6.1"
jobs:
e2e:
name: create-llama
timeout-minutes: 60
strategy:
fail-fast: true
matrix:
node-version: [18, 20]
python-version: ["3.11"]
os: [macos-latest, windows-latest]
defaults:
run:
shell: bash
runs-on: ${{ matrix.os }}
steps:
- uses: actions/checkout@v4
- name: Set up python ${{ matrix.python-version }}
uses: actions/setup-python@v4
with:
python-version: ${{ matrix.python-version }}
- name: Install Poetry
uses: snok/install-poetry@v1
with:
version: ${{ env.POETRY_VERSION }}
- uses: pnpm/action-setup@v2
- name: Setup Node.js ${{ matrix.node-version }}
uses: actions/setup-node@v4
with:
node-version: ${{ matrix.node-version }}
cache: "pnpm"
- name: Install dependencies
run: pnpm install
- name: Install Playwright Browsers
run: pnpm exec playwright install --with-deps
working-directory: ./packages/create-llama
- name: Build create-llama
run: pnpm run build
working-directory: ./packages/create-llama
- name: Pack
run: pnpm pack --pack-destination ./output
working-directory: ./packages/create-llama
- name: Extract Pack
run: tar -xvzf ./output/*.tgz -C ./output
working-directory: ./packages/create-llama
- name: Run Playwright tests
run: pnpm exec playwright test
env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
working-directory: ./packages/create-llama
- uses: actions/upload-artifact@v3
if: always()
with:
name: playwright-report
path: ./packages/create-llama/playwright-report/
retention-days: 30
+6 -3
View File
@@ -8,14 +8,17 @@ on:
branches:
- main
env:
TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
TURBO_TEAM: ${{ vars.TURBO_TEAM }}
TURBO_REMOTE_ONLY: true
jobs:
lint:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v2
with:
version: latest
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
+33
View File
@@ -0,0 +1,33 @@
name: Publish Preview
on: [pull_request]
env:
TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
TURBO_TEAM: ${{ vars.TURBO_TEAM }}
TURBO_REMOTE_ONLY: true
jobs:
pre_release:
name: Pre Release
runs-on: ubuntu-latest
steps:
- name: Checkout Repo
uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version-file: ".nvmrc"
cache: "pnpm"
- name: Install dependencies
run: pnpm install
- name: Build
run: pnpm run build
- name: Pre Release
run: pnpx pkg-pr-new publish --pnpm ./packages/* ./packages/providers/* ./packages/providers/storage/*
+37
View File
@@ -0,0 +1,37 @@
name: Publish to GitHub Releases
on:
push:
tags:
- "llamaindex@*"
jobs:
build-and-publish:
runs-on: ubuntu-latest
steps:
- name: Checkout Repo
uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version-file: ".nvmrc"
cache: "pnpm"
- name: Install dependencies
run: pnpm install
- name: Build tarball
run: |
pnpm pack
working-directory: packages/llamaindex
- name: Create release
uses: ncipollo/release-action@v1
with:
artifacts: "packages/llamaindex/llamaindex-*.tgz"
name: Release ${{ github.ref }}
bodyFile: "packages/llamaindex/CHANGELOG.md"
token: ${{ secrets.GITHUB_TOKEN }}
+70
View File
@@ -0,0 +1,70 @@
name: Release
on:
push:
branches:
- main
concurrency: ${{ github.workflow }}-${{ github.ref }}
jobs:
release:
name: Release
runs-on: ubuntu-latest
steps:
- name: Checkout Repo
uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version-file: ".nvmrc"
cache: "pnpm"
- name: Install dependencies
run: pnpm install
- name: Add auth token to .npmrc file
run: |
cat << EOF >> ".npmrc"
//registry.npmjs.org/:_authToken=$NPM_TOKEN
EOF
env:
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
- name: Get changeset status
id: get-changeset-status
run: |
pnpm changeset status --output .changeset/status.json
new_version=$(jq -r '.releases[] | select(.name == "llamaindex") | .newVersion' < .changeset/status.json)
rm -v .changeset/status.json
echo "new-version=${new_version}" >> "$GITHUB_OUTPUT"
- name: Create Release Pull Request or Publish to npm
id: changesets
uses: changesets/action@v1
with:
commit: Release ${{ steps.get-changeset-status.outputs.new-version }}
title: Release ${{ steps.get-changeset-status.outputs.new-version }}
# update version PR with the latest changesets
version: pnpm new-version
# build package and call changeset publish
publish: pnpm release
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
# Refs: https://github.com/changesets/changesets/issues/421
- name: Update lock file
continue-on-error: true
run: pnpm install --lockfile-only
- name: Commit lock file
continue-on-error: true
uses: stefanzweifel/git-auto-commit-action@v5
with:
commit_message: "chore: update lock file"
branch: changeset-release/main
file_pattern: "pnpm-lock.yaml"
+165 -14
View File
@@ -1,18 +1,68 @@
name: Run Tests
on: [push, pull_request]
on:
push:
branches:
- main
pull_request:
branches:
- main
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
env:
POSTGRES_HOST_AUTH_METHOD: trust
TURBO_TOKEN: ${{ secrets.TURBO_TOKEN }}
TURBO_TEAM: ${{ vars.TURBO_TEAM }}
TURBO_REMOTE_ONLY: true
jobs:
test:
e2e:
strategy:
fail-fast: false
matrix:
node-version: [20.x, 22.x, 23.x]
name: E2E on Node.js ${{ matrix.node-version }}
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v2
- uses: ankane/setup-postgres@v1
with:
database: llamaindex_node_test
dev-files: true
- run: |
cd /tmp
git clone --branch v0.7.0 https://github.com/pgvector/pgvector.git
cd pgvector
make
sudo make install
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version-file: ".nvmrc"
node-version: ${{ matrix.node-version }}
cache: "pnpm"
- name: Install dependencies
run: pnpm install
- name: Run E2E Tests
run: pnpm run e2e
test:
strategy:
fail-fast: false
matrix:
node-version: [20.x, 22.x, 23.x]
name: Test on Node.js ${{ matrix.node-version }}
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version: ${{ matrix.node-version }}
cache: "pnpm"
- name: Install dependencies
run: pnpm install
@@ -23,7 +73,7 @@ jobs:
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v2
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
@@ -32,18 +82,95 @@ jobs:
- name: Install dependencies
run: pnpm install
- name: Build
run: pnpm run build --filter llamaindex
run: pnpm run build
- name: Run Type Check
run: pnpm run type-check
- name: Run Circular Dependency Check
run: pnpm run circular-check
working-directory: ./packages/core
e2e-npm:
runs-on: ubuntu-latest
name: Test using packages with npm
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version-file: ".nvmrc"
- name: Install dependencies
run: pnpm install
- name: Build packages
run: pnpm run build
- name: Pack packages
run: |
pnpm pack --pack-destination ${{ runner.temp }} -C packages/llamaindex
pnpm pack --pack-destination ${{ runner.temp }} -C packages/workflow
- name: Install packed packages
run: npm add ${{ runner.temp }}/*.tgz
working-directory: e2e/npm
- name: Run tests
run: npm test
working-directory: e2e/npm
e2e-llamaindex-examples:
strategy:
fail-fast: false
matrix:
packages:
- cloudflare-worker-agent
- nextjs-agent
- nextjs-edge-runtime
- nextjs-node-runtime
- waku-query-engine
- llama-parse-browser
- vite-import-llamaindex
runs-on: ubuntu-latest
name: Build LlamaIndex Example (${{ matrix.packages }})
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version-file: ".nvmrc"
cache: "pnpm"
- name: Install dependencies
run: pnpm install
- name: Build llamaindex
run: pnpm run build
- name: Build ${{ matrix.packages }}
run: pnpm run build
working-directory: e2e/examples/${{ matrix.packages }}
size-limit:
runs-on: ubuntu-latest
if: github.event_name == 'pull_request'
name: Size Limit
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
node-version-file: ".nvmrc"
cache: "pnpm"
- name: Install dependencies
run: pnpm install
- name: Build llamaindex
run: pnpm run build
- uses: andresz1/size-limit-action@94bc357df29c36c8f8d50ea497c3e225c3c95d1d
with:
github_token: ${{ secrets.GITHUB_TOKEN }}
directory: e2e/examples/vite-import-llamaindex
skip_step: "install"
build_script: build
package_manager: pnpm
typecheck-examples:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: pnpm/action-setup@v2
- uses: pnpm/action-setup@v4
- name: Setup Node.js
uses: actions/setup-node@v4
with:
@@ -52,15 +179,39 @@ jobs:
- name: Install dependencies
run: pnpm install
- name: Build
run: pnpm run build --filter llamaindex
run: pnpm run build
- name: Copy examples
run: rsync -rv --exclude=node_modules ./examples ${{ runner.temp }}
- name: Pack
run: pnpm pack --pack-destination ${{ runner.temp }}
working-directory: packages/core
- name: Install llamaindex
- name: Pack packages
run: |
for dir in packages/*; do
if [ -d "$dir" ] && [ -f "$dir/package.json" ] && [[ ! "$dir" =~ autotool ]]; then
echo "Packing $dir"
pnpm pack --pack-destination ${{ runner.temp }} -C $dir
else
echo "Skipping $dir, no package.json found"
fi
done
- name: Pack provider packages
run: |
for dir in packages/providers/* packages/providers/storage/*; do
if [ -d "$dir" ] && [ -f "$dir/package.json" ]; then
echo "Packing $dir"
pnpm pack --pack-destination ${{ runner.temp }} -C $dir
else
echo "Skipping $dir, no package.json found"
fi
done
- name: Install
run: npm add ${{ runner.temp }}/*.tgz
working-directory: ${{ runner.temp }}/examples
- name: Run Type Check
run: npx tsc --project ./tsconfig.json
working-directory: ${{ runner.temp }}/examples
- uses: actions/upload-artifact@v4
if: failure()
with:
name: build-dist
path: |
${{ runner.temp }}/*.tgz
if-no-files-found: error
+4
View File
@@ -44,6 +44,10 @@ test-results/
playwright-report/
blob-report/
playwright/.cache/
.tsbuildinfo
# intellij
**/.idea
# generated API
packages/cloud/src/client
+1 -3
View File
@@ -1,3 +1 @@
pnpm format
pnpm lint
npx lint-staged
pnpm run lint-staged
-1
View File
@@ -1 +0,0 @@
pnpm test
+3
View File
@@ -1,2 +1,5 @@
auto-install-peers = true
enable-pre-post-scripts = true
prefer-workspace-packages = true
save-workspace-protocol = true
link-workspace-packages = true
+1 -1
View File
@@ -1 +1 @@
18
22
+4
View File
@@ -4,3 +4,7 @@ pnpm-lock.yaml
lib/
dist/
.docusaurus/
.source/
# prttier doesn't support mdx3 we are using
*.mdx
packages/server/server/
+12
View File
@@ -0,0 +1,12 @@
{
"jsc": {
"parser": {
"syntax": "typescript",
"decorators": true
},
"target": "esnext",
"transform": {
"decoratorVersion": "2022-03"
}
}
}
+2 -1
View File
@@ -10,8 +10,9 @@
"name": "Debug Example",
"skipFiles": ["<node_internals>/**"],
"runtimeExecutable": "pnpm",
"console": "integratedTerminal",
"cwd": "${workspaceFolder}/examples",
"runtimeArgs": ["ts-node", "${fileBasename}"]
"runtimeArgs": ["npx", "tsx", "${file}"]
}
]
}
+1
View File
@@ -0,0 +1 @@
LlamaIndexTS
+3 -2
View File
@@ -5,7 +5,6 @@
"[xml]": {
"editor.defaultFormatter": "redhat.vscode-xml"
},
"jest.rootPath": "./packages/core",
"[python]": {
"editor.defaultFormatter": "ms-python.black-formatter"
},
@@ -14,5 +13,7 @@
},
"[json]": {
"editor.defaultFormatter": "esbenp.prettier-vscode"
}
},
"prettier.prettierPath": "./node_modules/prettier",
"prettier.configPath": "prettier.config.mjs"
}
+79 -47
View File
@@ -2,79 +2,111 @@
## Structure
This is a monorepo built with Turborepo
LlamaIndex.TS uses pnpm monorepo.
Right now there are two packages of importance:
We recommend you to understand the basics of Node.js, TypeScript, pnpm, and of course, LLM before contributing.
packages/core which is the main NPM library llamaindex
There are some important folders in the repository:
examples is where the demo code lives
### Turborepo docs
You can checkout how Turborepo works using the default [README-turborepo.md](/README-turborepo.md)
- `packages/*`: Contains the source code of the packages. Each package is a separate npm package.
- `llamaindex`: The starter package for LlamaIndex.TS, which contains the all sub-packages.
- `core`: The core package of LlamaIndex.TS, which contains the abstract classes and interfaces. It is designed for
all JS runtime environments.
- `env`: The environment package of LlamaIndex.TS, which contains the environment-specific classes and interfaces. It
includes compatibility layers for Node.js, Deno, Vercel Edge Runtime, Cloudflare Workers...
- `providers/*`: The providers package of LlamaIndex.TS, which contains the providers for LLM and other services.
- `apps/*`: The applications based on LlamaIndex.TS.
- `next`: Our documentation website based on Next.js.
- `examples`: The code examples of LlamaIndex.TS using Node.js.
## Getting Started
Install NodeJS. Preferably v18 using nvm or n.
Inside the LlamaIndexTS directory:
Make sure you have Node.js LTS (Long-term Support) installed. You can check your Node.js version by running:
```shell
node -v
# v20.x.x
```
npm i -g pnpm ts-node
### Use pnpm
```shell
npm install -g pnpm
```
### Install dependencies
```shell
pnpm install
```
Note: we use pnpm in this repo, which has a lot of the same functionality and CLI options as npm but it does do some things better in a monorepo, like centralizing dependencies and caching.
### Build the packages
PNPM's has documentation on its [workspace feature](https://pnpm.io/workspaces) and Turborepo had some [useful documentation also](https://turbo.build/repo/docs/core-concepts/monorepos/running-tasks).
To build all packages, run:
### Running Typescript
When we publish to NPM we will have a tsc compiled version of the library in JS. For now, the easiest thing to do is use ts-node.
### Test cases
To run them, run
```
pnpm run test
```shell
pnpm build
```
To write new test cases write them in [packages/core/src/tests](/packages/core/src/tests)
### Run tests
We use Jest https://jestjs.io/ to write our test cases. Jest comes with a bunch of built in assertions using the expect function: https://jestjs.io/docs/expect
#### Unit tests
### Demo applications
After build, to run all unit tests, call:
There is an existing ["example"](/examples/README.md) demos folder with mainly NodeJS scripts. Feel free to add additional demos to that folder. If you would like to try out your changes in the core package with a new demo, you need to run the build command in the README.
You can create new demo applications in the apps folder. Just run pnpm init in the folder after you create it to create its own package.json
### Installing packages
To install packages for a specific package or demo application, run
```
pnpm add [NPM Package] --filter [package or application i.e. core or docs]
```shell
pnpm test
```
To install packages for every package or application run
Unit tests are located in the `tests` folder of each package. They are using their own package (e.g. `@llamaindex/core-tests` for `@llamaindex/core`). The tests are importing the package under test and the test package is not published.
#### E2E tests
To run all E2E tests, call:
```shell
pnpm e2e
```
pnpm add -w [NPM Package]
```
All E2E tests are in the `e2e` folder.
### Docs
To contribute to the docs, go to the docs website folder and run the Docusaurus instance.
See the [docs](./apps/next/README.md) for more information.
```bash
cd apps/docs
pnpm install
pnpm start
## Adding a new package
Please follow these steps to add a new package:
1. Only add new packages to the `packages/providers` folder.
2. Use the `package.json` and `tsconfig.json` of an existing packages as template.
3. Reference your new package in the root `tsconfig.json` file
4. Add your package to the `examples/package.json` file if you add a new example.
## Before sending a PR
Before sending a PR, make sure of the following:
1. Tests are all running and you added meaningful tests for your change.
2. If you have a new feature, document it in the `apps/next` docs folder.
3. If you have a new feature, add a new example in the `examples` folder.
4. You have a descriptive changeset for each PR:
### Changesets
We use [changesets](https://github.com/changesets/changesets) for managing versions and changelogs. To create a new
changeset, run in the root folder:
```shell
pnpm changeset
```
That should start a webserver which will serve the docs on https://localhost:3000
## Publishing (maintainers only)
Any changes you make should be reflected in the browser. If you need to regenerate the API docs and find that your TSDoc isn't getting the updates, feel free to remove apps/docs/api. It will automatically regenerate itself when you run pnpm start again.
The [Release Github Action](.github/workflows/release.yml) is automatically generating and updating a
PR called "Release {version}".
This PR will update the `package.json` and `CHANGELOG.md` files of each package according to
the current changesets in the [.changeset](.changeset) folder.
If this PR is merged it will automatically add version tags to the repository and publish the updated packages to NPM.
-81
View File
@@ -1,81 +0,0 @@
# Turborepo starter
This is an official starter Turborepo.
## Using this example
Run the following command:
```sh
npx create-turbo@latest
```
## What's inside?
This Turborepo includes the following packages/apps:
### Apps and Packages
- `docs`: a [Next.js](https://nextjs.org/) app
- `web`: another [Next.js](https://nextjs.org/) app
- `ui`: a stub React component library shared by both `web` and `docs` applications
- `eslint-config-custom`: `eslint` configurations (includes `eslint-config-next` and `eslint-config-prettier`)
- `tsconfig`: `tsconfig.json`s used throughout the monorepo
Each package/app is 100% [TypeScript](https://www.typescriptlang.org/).
### Utilities
This Turborepo has some additional tools already setup for you:
- [TypeScript](https://www.typescriptlang.org/) for static type checking
- [ESLint](https://eslint.org/) for code linting
- [Prettier](https://prettier.io) for code formatting
### Build
To build all apps and packages, run the following command:
```
cd my-turborepo
pnpm build
```
### Develop
To develop all apps and packages, run the following command:
```
cd my-turborepo
pnpm dev
```
### Remote Caching
Turborepo can use a technique known as [Remote Caching](https://turbo.build/repo/docs/core-concepts/remote-caching) to share cache artifacts across machines, enabling you to share build caches with your team and CI/CD pipelines.
By default, Turborepo will cache locally. To enable Remote Caching you will need an account with Vercel. If you don't have an account you can [create one](https://vercel.com/signup), then enter the following commands:
```
cd my-turborepo
npx turbo login
```
This will authenticate the Turborepo CLI with your [Vercel account](https://vercel.com/docs/concepts/personal-accounts/overview).
Next, you can link your Turborepo to your Remote Cache by running the following command from the root of your Turborepo:
```
npx turbo link
```
## Useful Links
Learn more about the power of Turborepo:
- [Tasks](https://turbo.build/repo/docs/core-concepts/monorepos/running-tasks)
- [Caching](https://turbo.build/repo/docs/core-concepts/caching)
- [Remote Caching](https://turbo.build/repo/docs/core-concepts/remote-caching)
- [Filtering](https://turbo.build/repo/docs/core-concepts/monorepos/filtering)
- [Configuration Options](https://turbo.build/repo/docs/reference/configuration)
- [CLI Usage](https://turbo.build/repo/docs/reference/command-line-reference)
+55 -96
View File
@@ -1,13 +1,18 @@
# LlamaIndex.TS
<p align="center">
<img height="100" width="100" alt="LlamaIndex logo" src="https://ts.llamaindex.ai/square.svg" />
</p>
<h1 align="center">LlamaIndex.TS</h1>
<h3 align="center">
Data framework for your LLM application.
</h3>
[![NPM Version](https://img.shields.io/npm/v/llamaindex)](https://www.npmjs.com/package/llamaindex)
[![NPM License](https://img.shields.io/npm/l/llamaindex)](https://www.npmjs.com/package/llamaindex)
[![NPM License](https://img.shields.io/npm/l/llamaindex)](https://github.com/run-llama/LlamaIndexTS/blob/main/LICENSE)
[![NPM Downloads](https://img.shields.io/npm/dm/llamaindex)](https://www.npmjs.com/package/llamaindex)
[![Discord](https://img.shields.io/discord/1059199217496772688)](https://discord.com/invite/eN6D2HQ4aX)
[![Twitter](https://img.shields.io/twitter/follow/llama_index)](https://x.com/llama_index)
LlamaIndex is a data framework for your LLM application.
Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in Typescript and Javascript.
Use your own data with large language models (LLMs, OpenAI ChatGPT and others) in JS runtime environments with TypeScript support.
Documentation: https://ts.llamaindex.ai/
@@ -19,58 +24,58 @@ Try examples online:
LlamaIndex.TS aims to be a lightweight, easy to use set of libraries to help you integrate large language models into your applications with your own data.
## Getting started with an example:
## Compatibility
LlamaIndex.TS requires Node v18 or higher. You can download it from https://nodejs.org or use https://nvm.sh (our preferred option).
### Multiple JS Environment Support
In a new folder:
LlamaIndex.TS supports multiple JS environments, including:
```bash
export OPENAI_API_KEY="sk-......" # Replace with your key from https://platform.openai.com/account/api-keys
pnpm init
pnpm install typescript
pnpm exec tsc --init # if needed
- Node.js >= 20 ✅
- Deno ✅
- Bun ✅
- Nitro ✅
- Vercel Edge Runtime ✅ (with some limitations)
- Cloudflare Workers ✅ (with some limitations)
For now, browser support is limited due to the lack of support for [AsyncLocalStorage-like APIs](https://github.com/tc39/proposal-async-context)
### Supported LLMs:
- OpenAI LLms
- Anthropic LLms
- Groq LLMs
- Llama2, Llama3, Llama3.1 LLMs
- MistralAI LLMs
- Fireworks LLMs
- DeepSeek LLMs
- ReplicateAI LLMs
- TogetherAI LLMs
- HuggingFace LLms
- DeepInfra LLMs
- Gemini LLMs
## Getting started
```shell
npm install llamaindex
pnpm install llamaindex
pnpm install @types/node
yarn add llamaindex
```
Create the file example.ts
### Setup in Node.js, Deno, Bun, TypeScript...?
```ts
// example.ts
import fs from "fs/promises";
import { Document, VectorStoreIndex } from "llamaindex";
See our official document: https://ts.llamaindex.ai/docs/llamaindex/getting_started
async function main() {
// Load essay from abramov.txt in Node
const essay = await fs.readFile(
"node_modules/llamaindex/examples/abramov.txt",
"utf-8",
);
### Adding provider packages
// Create Document object with essay
const document = new Document({ text: essay });
In most cases, you'll also need to install provider packages to use LlamaIndexTS. These are for adding AI models, file readers for ingestion or storing documents, e.g. in vector databases.
// Split text and create embeddings. Store them in a VectorStoreIndex
const index = await VectorStoreIndex.fromDocuments([document]);
For example, to use the OpenAI LLM, you would install the following package:
// Query the index
const queryEngine = index.asQueryEngine();
const response = await queryEngine.query({
query: "What did the author do in college?",
});
// Output response
console.log(response.toString());
}
main();
```
Then you can run it using
```bash
pnpm dlx ts-node example.ts
```shell
npm install @llamaindex/openai
pnpm install @llamaindex/openai
yarn add @llamaindex/openai
```
## Playground
@@ -79,59 +84,13 @@ Check out our NextJS playground at https://llama-playground.vercel.app/. The sou
## Core concepts for getting started:
- [Document](/packages/core/src/Node.ts): A document represents a text file, PDF file or other contiguous piece of data.
- [Node](/packages/core/src/Node.ts): The basic data building block. Most commonly, these are parts of the document split into manageable pieces that are small enough to be fed into an embedding model and LLM.
- [Embedding](/packages/core/src/Embedding.ts): Embeddings are sets of floating point numbers which represent the data in a Node. By comparing the similarity of embeddings, we can derive an understanding of the similarity of two pieces of data. One use case is to compare the embedding of a question with the embeddings of our Nodes to see which Nodes may contain the data needed to answer that quesiton.
- [Indices](/packages/core/src/indices/): Indices store the Nodes and the embeddings of those nodes. QueryEngines retrieve Nodes from these Indices using embedding similarity.
- [QueryEngine](/packages/core/src/QueryEngine.ts): Query engines are what generate the query you put in and give you back the result. Query engines generally combine a pre-built prompt with selected Nodes from your Index to give the LLM the context it needs to answer your query.
- [ChatEngine](/packages/core/src/ChatEngine.ts): A ChatEngine helps you build a chatbot that will interact with your Indices.
- [SimplePrompt](/packages/core/src/Prompt.ts): A simple standardized function call definition that takes in inputs and formats them in a template literal. SimplePrompts can be specialized using currying and combined using other SimplePrompt functions.
## Note: NextJS:
If you're using NextJS App Router, you'll need to use the NodeJS runtime (default) and add the following config to your next.config.js to have it use imports/exports in the same way Node does.
```js
export const runtime = "nodejs"; // default
```
```js
// next.config.js
/** @type {import('next').NextConfig} */
const nextConfig = {
experimental: {
serverComponentsExternalPackages: ["pdf2json"],
},
webpack: (config) => {
config.resolve.alias = {
...config.resolve.alias,
sharp$: false,
"onnxruntime-node$": false,
};
return config;
},
};
module.exports = nextConfig;
```
## Supported LLMs:
- OpenAI GPT-3.5-turbo and GPT-4
- Anthropic Claude Instant and Claude 2
- Llama2 Chat LLMs (70B, 13B, and 7B parameters)
- MistralAI Chat LLMs
See our documentation: https://ts.llamaindex.ai/docs/llamaindex/getting_started/concepts
## Contributing:
We are in the very early days of LlamaIndex.TS. If youre interested in hacking on it with us check out our [contributing guide](/CONTRIBUTING.md)
Please see our [contributing guide](CONTRIBUTING.md) for more information.
You are highly encouraged to contribute to LlamaIndex.TS!
## Bugs? Questions?
## Community
Please join our Discord! https://discord.com/invite/eN6D2HQ4aX
-21
View File
@@ -1,21 +0,0 @@
# Dependencies
/node_modules
# Production
/build
# Generated files
.docusaurus
.cache-loader
lib
# Misc
.DS_Store
.env.local
.env.development.local
.env.test.local
.env.production.local
npm-debug.log*
yarn-debug.log*
yarn-error.log*
-13
View File
@@ -1,13 +0,0 @@
# docs
## 0.0.2
### Patch Changes
- 0f64084: docs: update API references
## 0.0.1
### Patch Changes
- 3154f52: chore: add qdrant readme
-47
View File
@@ -1,47 +0,0 @@
# Website
This website is built using [Docusaurus 2](https://docusaurus.io/), a modern static website generator.
### Installation
```
$ pnpm
```
### Local Development
```
$ pnpm start
```
This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
However, the searchbar may not function with `yarn start`. Instead, run `yarn build` and launch a server:
```
$ npx http-server ./build
```
### Build
```
$ pnpm build
```
This command generates static content into the `build` directory and can be served using any static contents hosting service.
### Deployment
Using SSH:
```
$ USE_SSH=true pnpm deploy
```
Not using SSH:
```
$ GIT_USER=<Your GitHub username> pnpm deploy
```
If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.
-3
View File
@@ -1,3 +0,0 @@
module.exports = {
presets: [require.resolve("@docusaurus/core/lib/babel/preset")],
};
-1
View File
@@ -1 +0,0 @@
api/
-2
View File
@@ -1,2 +0,0 @@
label: Examples
position: 2
-85
View File
@@ -1,85 +0,0 @@
# Agents
A built-in agent that can take decisions and reasoning based on the tools provided to it.
## OpenAI Agent
```ts
import { FunctionTool, OpenAIAgent } from "llamaindex";
// Define a function to sum two numbers
function sumNumbers({ a, b }: { a: number; b: number }): number {
return a + b;
}
// Define a function to divide two numbers
function divideNumbers({ a, b }: { a: number; b: number }): number {
return a / b;
}
// Define the parameters of the sum function as a JSON schema
const sumJSON = {
type: "object",
properties: {
a: {
type: "number",
description: "The first number",
},
b: {
type: "number",
description: "The second number",
},
},
required: ["a", "b"],
};
// Define the parameters of the divide function as a JSON schema
const divideJSON = {
type: "object",
properties: {
a: {
type: "number",
description: "The dividend to divide",
},
b: {
type: "number",
description: "The divisor to divide by",
},
},
required: ["a", "b"],
};
async function main() {
// Create a function tool from the sum function
const sumFunctionTool = new FunctionTool(sumNumbers, {
name: "sumNumbers",
description: "Use this function to sum two numbers",
parameters: sumJSON,
});
// Create a function tool from the divide function
const divideFunctionTool = new FunctionTool(divideNumbers, {
name: "divideNumbers",
description: "Use this function to divide two numbers"
parameters: divideJSON,
});
// Create an OpenAIAgent with the function tools
const agent = new OpenAIAgent({
tools: [sumFunctionTool, divideFunctionTool],
verbose: true,
});
// Chat with the agent
const response = await agent.chat({
message: "How much is 5 + 5? then divide by 2",
});
// Print the response
console.log(String(response));
}
main().then(() => {
console.log("Done");
});
```
-12
View File
@@ -1,12 +0,0 @@
---
sidebar_position: 1
---
import CodeBlock from "@theme/CodeBlock";
import CodeSource from "!raw-loader!../../../../examples/chatEngine";
# Chat Engine
Chat Engine is a class that allows you to create a chatbot from a retriever. It is a wrapper around a retriever that allows you to chat with it in a conversational manner.
<CodeBlock language="ts">{CodeSource}</CodeBlock>
@@ -1,7 +0,0 @@
---
sidebar_position: 5
---
# More examples
You can check out more examples in the [examples](https://github.com/run-llama/LlamaIndexTS/tree/main/examples) folder of the repository.
@@ -1,10 +0,0 @@
---
sidebar_position: 4
---
import CodeBlock from "@theme/CodeBlock";
import CodeSource from "!raw-loader!../../../../examples/storageContext";
# Save/Load an Index
<CodeBlock language="ts">{CodeSource}</CodeBlock>
-10
View File
@@ -1,10 +0,0 @@
---
sidebar_position: 3
---
import CodeBlock from "@theme/CodeBlock";
import CodeSource from "!raw-loader!../../../../examples/summaryIndex";
# Summary Index
<CodeBlock language="ts">{CodeSource}</CodeBlock>
-10
View File
@@ -1,10 +0,0 @@
---
sidebar_position: 2
---
import CodeBlock from "@theme/CodeBlock";
import CodeSource from "!raw-loader!../../../../examples/vectorIndex";
# Vector Index
<CodeBlock language="ts">{CodeSource}</CodeBlock>
@@ -1,2 +0,0 @@
label: Getting Started
position: 1
@@ -1,78 +0,0 @@
---
sidebar_position: 3
---
# Concepts
LlamaIndex.TS helps you build LLM-powered applications (e.g. Q&A, chatbot) over custom data.
In this high-level concepts guide, you will learn:
- how an LLM can answer questions using your own data.
- key concepts and modules in LlamaIndex.TS for composing your own query pipeline.
## Answering Questions Across Your Data
LlamaIndex uses a two stage method when using an LLM with your data:
1. **indexing stage**: preparing a knowledge base, and
2. **querying stage**: retrieving relevant context from the knowledge to assist the LLM in responding to a question
![](../_static/concepts/rag.jpg)
This process is also known as Retrieval Augmented Generation (RAG).
LlamaIndex.TS provides the essential toolkit for making both steps super easy.
Let's explore each stage in detail.
### Indexing Stage
LlamaIndex.TS help you prepare the knowledge base with a suite of data connectors and indexes.
![](../_static/concepts/indexing.jpg)
[**Data Loaders**](../modules/data_loader.md):
A data connector (i.e. `Reader`) ingest data from different data sources and data formats into a simple `Document` representation (text and simple metadata).
[**Documents / Nodes**](../modules/documents_and_nodes/index.md): A `Document` is a generic container around any data source - for instance, a PDF, an API output, or retrieved data from a database. A `Node` is the atomic unit of data in LlamaIndex and represents a "chunk" of a source `Document`. It's a rich representation that includes metadata and relationships (to other nodes) to enable accurate and expressive retrieval operations.
[**Data Indexes**](../modules/data_index.md):
Once you've ingested your data, LlamaIndex helps you index data into a format that's easy to retrieve.
Under the hood, LlamaIndex parses the raw documents into intermediate representations, calculates vector embeddings, and stores your data in-memory or to disk.
### Querying Stage
In the querying stage, the query pipeline retrieves the most relevant context given a user query,
and pass that to the LLM (along with the query) to synthesize a response.
This gives the LLM up-to-date knowledge that is not in its original training data,
(also reducing hallucination).
The key challenge in the querying stage is retrieval, orchestration, and reasoning over (potentially many) knowledge bases.
LlamaIndex provides composable modules that help you build and integrate RAG pipelines for Q&A (query engine), chatbot (chat engine), or as part of an agent.
These building blocks can be customized to reflect ranking preferences, as well as composed to reason over multiple knowledge bases in a structured way.
![](../_static/concepts/querying.jpg)
#### Building Blocks
[**Retrievers**](../modules/retriever.md):
A retriever defines how to efficiently retrieve relevant context from a knowledge base (i.e. index) when given a query.
The specific retrieval logic differs for difference indices, the most popular being dense retrieval against a vector index.
[**Response Synthesizers**](../modules/response_synthesizer.md):
A response synthesizer generates a response from an LLM, using a user query and a given set of retrieved text chunks.
#### Pipelines
[**Query Engines**](../modules/query_engines):
A query engine is an end-to-end pipeline that allow you to ask question over your data.
It takes in a natural language query, and returns a response, along with reference context retrieved and passed to the LLM.
[**Chat Engines**](../modules/chat_engine.md):
A chat engine is an end-to-end pipeline for having a conversation with your data
(multiple back-and-forth instead of a single question & answer).
@@ -1,15 +0,0 @@
---
sidebar_position: 2
---
# Environments
LlamaIndex currently officially supports NodeJS 18 and NodeJS 20.
## NextJS App Router
If you're using NextJS App Router route handlers/serverless functions, you'll need to use the NodeJS mode:
```js
export const runtime = "nodejs"; // default
```
@@ -1,63 +0,0 @@
---
sidebar_position: 0
---
# Installation and Setup
Make sure you have NodeJS v18 or higher.
## Using create-llama
The easiest way to get started with LlamaIndex is by using `create-llama`. This CLI tool enables you to quickly start building a new LlamaIndex application, with everything set up for you.
Just run
<Tabs>
<TabItem value="1" label="npm" default>
```bash
npx create-llama@latest
```
</TabItem>
<TabItem value="2" label="Yarn">
```bash
yarn create llama
```
</TabItem>
<TabItem value="3" label="pnpm">
```bash
pnpm create llama@latest
```
</TabItem>
</Tabs>
to get started. Once your app is generated, run
```bash npm2yarn
npm run dev
```
to start the development server. You can then visit [http://localhost:3000](http://localhost:3000) to see your app
## Installation from NPM
```bash npm2yarn
npm install llamaindex
```
### Environment variables
Our examples use OpenAI by default. You'll need to set up your Open AI key like so:
```bash
export OPENAI_API_KEY="sk-......" # Replace with your key from https://platform.openai.com/account/api-keys
```
If you want to have it automatically loaded every time, add it to your `.zshrc/.bashrc`.
WARNING: do not check in your OpenAI key into version control.
-56
View File
@@ -1,56 +0,0 @@
---
sidebar_position: 1
---
# Starter Tutorial
Once you have [installed LlamaIndex.TS using NPM](installation) and set up your OpenAI key, you're ready to start your first app:
In a new folder:
```bash npm2yarn
npm install typescript
npm install @types/node
npx tsc --init # if needed
```
Create the file `example.ts`. This code will load some example data, create a document, index it (which creates embeddings using OpenAI), and then creates query engine to answer questions about the data.
```ts
// example.ts
import fs from "fs/promises";
import { Document, VectorStoreIndex } from "llamaindex";
async function main() {
// Load essay from abramov.txt in Node
const essay = await fs.readFile(
"node_modules/llamaindex/examples/abramov.txt",
"utf-8",
);
// Create Document object with essay
const document = new Document({ text: essay });
// Split text and create embeddings. Store them in a VectorStoreIndex
const index = await VectorStoreIndex.fromDocuments([document]);
// Query the index
const queryEngine = index.asQueryEngine();
const response = await queryEngine.query({
query: "What did the author do in college?",
});
// Output response
console.log(response.toString());
}
main();
```
Then you can run it using
```bash
npx ts-node example.ts
```
Ready to learn more? Check out our NextJS playground at https://llama-playground.vercel.app/. The source is available at https://github.com/run-llama/ts-playground
-56
View File
@@ -1,56 +0,0 @@
---
sidebar_position: 0
slug: /
---
# What is LlamaIndex.TS?
LlamaIndex.TS is a data framework for LLM applications to ingest, structure, and access private or domain-specific data. While a python package is also available (see [here](https://docs.llamaindex.ai/en/stable/)), LlamaIndex.TS offers core features in a simple package, optimized for usage with TypeScript.
## 🚀 Why LlamaIndex.TS?
At their core, LLMs offer a natural language interface between humans and inferred data. Widely available models come pre-trained on huge amounts of publicly available data, from Wikipedia and mailing lists to textbooks and source code.
Applications built on top of LLMs often require augmenting these models with private or domain-specific data. Unfortunately, that data can be distributed across siloed applications and data stores. It's behind APIs, in SQL databases, or trapped in PDFs and slide decks.
That's where **LlamaIndex.TS** comes in.
## 🦙 How can LlamaIndex.TS help?
LlamaIndex.TS provides the following tools:
- **Data loading** ingest your existing `.txt`, `.pdf`, `.csv`, `.md` and `.docx` data directly
- **Data indexes** structure your data in intermediate representations that are easy and performant for LLMs to consume.
- **Engines** provide natural language access to your data. For example:
- Query engines are powerful retrieval interfaces for knowledge-augmented output.
- Chat engines are conversational interfaces for multi-message, "back and forth" interactions with your data.
## 👨‍👩‍👧‍👦 Who is LlamaIndex for?
LlamaIndex.TS provides a core set of tools, essential for anyone building LLM apps with JavaScript and TypeScript.
Our high-level API allows beginner users to use LlamaIndex.TS to ingest and query their data.
For more complex applications, our lower-level APIs allow advanced users to customize and extend any module—data connectors, indices, retrievers, and query engines, to fit their needs.
## Getting Started
`npm install llamaindex`
Our documentation includes [Installation Instructions](./getting_started/installation.mdx) and a [Starter Tutorial](./getting_started/starter.md) to build your first application.
Once you're up and running, [High-Level Concepts](./getting_started/concepts.md) has an overview of LlamaIndex's modular architecture. For more hands-on practical examples, look through our Examples section on the sidebar.
## 🗺️ Ecosystem
To download or contribute, find LlamaIndex on:
- Github: https://github.com/run-llama/LlamaIndexTS
- NPM: https://www.npmjs.com/package/llamaindex
## Community
Need help? Have a feature suggestion? Join the LlamaIndex community:
- Twitter: https://twitter.com/llama_index
- Discord https://discord.gg/dGcwcsnxhU
-3
View File
@@ -1,3 +0,0 @@
label: "Modules"
collapsed: false
position: 5
@@ -1 +0,0 @@
label: "Agents"
-14
View File
@@ -1,14 +0,0 @@
# Agents
An “agent” is an automated reasoning and decision engine. It takes in a user input/query and can make internal decisions for executing that query in order to return the correct result. The key agent components can include, but are not limited to:
- Breaking down a complex question into smaller ones
- Choosing an external Tool to use + coming up with parameters for calling the Tool
- Planning out a set of tasks
- Storing previously completed tasks in a memory module
## Getting Started
LlamaIndex.TS comes with a few built-in agents, but you can also create your own. The built-in agents include:
- [OpenAI Agent](./openai.mdx)
-183
View File
@@ -1,183 +0,0 @@
# OpenAI Agent
OpenAI API that supports function calling, its never been easier to build your own agent!
In this notebook tutorial, we showcase how to write your own OpenAI agent
## Setup
First, you need to install the `llamaindex` package. You can do this by running the following command in your terminal:
```bash
pnpm i llamaindex
```
Then we can define a function to sum two numbers and another function to divide two numbers.
```ts
function sumNumbers({ a, b }: { a: number; b: number }): number {
return a + b;
}
// Define a function to divide two numbers
function divideNumbers({ a, b }: { a: number; b: number }): number {
return a / b;
}
```
## Create a function tool
Now we can create a function tool from the sum function and another function tool from the divide function.
For the parameters of the sum function, we can define a JSON schema.
### JSON Schema
```ts
const sumJSON = {
type: "object",
properties: {
a: {
type: "number",
description: "The first number",
},
b: {
type: "number",
description: "The second number",
},
},
required: ["a", "b"],
};
const divideJSON = {
type: "object",
properties: {
a: {
type: "number",
description: "The dividend a to divide",
},
b: {
type: "number",
description: "The divisor b to divide by",
},
},
required: ["a", "b"],
};
const sumFunctionTool = new FunctionTool(sumNumbers, {
name: "sumNumbers",
description: "Use this function to sum two numbers",
parameters: sumJSON,
});
const divideFunctionTool = new FunctionTool(divideNumbers, {
name: "divideNumbers",
description: "Use this function to divide two numbers",
parameters: divideJSON,
});
```
## Create an OpenAIAgent
Now we can create an OpenAIAgent with the function tools.
```ts
const worker = new OpenAIAgent({
tools: [sumFunctionTool, divideFunctionTool],
verbose: true,
});
```
## Chat with the agent
Now we can chat with the agent.
```ts
const response = await worker.chat({
message: "How much is 5 + 5? then divide by 2",
});
console.log(String(response));
```
## Full code
```ts
import { FunctionTool, OpenAIAgent } from "llamaindex";
// Define a function to sum two numbers
function sumNumbers({ a, b }: { a: number; b: number }): number {
return a + b;
}
// Define a function to divide two numbers
function divideNumbers({ a, b }: { a: number; b: number }): number {
return a / b;
}
// Define the parameters of the sum function as a JSON schema
const sumJSON = {
type: "object",
properties: {
a: {
type: "number",
description: "The first number",
},
b: {
type: "number",
description: "The second number",
},
},
required: ["a", "b"],
};
// Define the parameters of the divide function as a JSON schema
const divideJSON = {
type: "object",
properties: {
a: {
type: "number",
description: "The argument a to divide",
},
b: {
type: "number",
description: "The argument b to divide",
},
},
required: ["a", "b"],
};
async function main() {
// Create a function tool from the sum function
const sumFunctionTool = new FunctionTool(sumNumbers, {
name: "sumNumbers",
description: "Use this function to sum two numbers",
parameters: sumJSON,
});
// Create a function tool from the divide function
const divideFunctionTool = new FunctionTool(divideNumbers, {
name: "divideNumbers",
description: "Use this function to divide two numbers",
parameters: divideJSON,
});
// Create an OpenAIAgent with the function tools
const agent = new OpenAIAgent({
tools: [sumFunctionTool, divideFunctionTool],
verbose: true,
});
// Chat with the agent
const response = await agent.chat({
message: "How much is 5 + 5? then divide by 2",
});
// Print the response
console.log(String(response));
}
main().then(() => {
console.log("Done");
});
```
-29
View File
@@ -1,29 +0,0 @@
---
sidebar_position: 4
---
# ChatEngine
The chat engine is a quick and simple way to chat with the data in your index.
```typescript
const retriever = index.asRetriever();
const chatEngine = new ContextChatEngine({ retriever });
// start chatting
const response = await chatEngine.chat({ message: query });
```
The `chat` function also supports streaming, just add `stream: true` as an option:
```typescript
const stream = await chatEngine.chat({ message: query, stream: true });
for await (const chunk of stream) {
process.stdout.write(chunk.response);
}
```
## Api References
- [ContextChatEngine](../api/classes/ContextChatEngine.md)
- [CondenseQuestionChatEngine](../api/classes/ContextChatEngine.md)
-23
View File
@@ -1,23 +0,0 @@
---
sidebar_position: 4
---
# Index
An index is the basic container and organization for your data. LlamaIndex.TS supports two indexes:
- `VectorStoreIndex` - will send the top-k `Node`s to the LLM when generating a response. The default top-k is 2.
- `SummaryIndex` - will send every `Node` in the index to the LLM in order to generate a response
```typescript
import { Document, VectorStoreIndex } from "llamaindex";
const document = new Document({ text: "test" });
const index = await VectorStoreIndex.fromDocuments([document]);
```
## API Reference
- [SummaryIndex](../api/classes/SummaryIndex.md)
- [VectorStoreIndex](../api/classes/VectorStoreIndex.md)
-17
View File
@@ -1,17 +0,0 @@
---
sidebar_position: 3
---
# Reader / Loader
LlamaIndex.TS supports easy loading of files from folders using the `SimpleDirectoryReader` class. Currently, `.txt`, `.pdf`, `.csv`, `.md` and `.docx` files are supported, with more planned in the future!
```typescript
import { SimpleDirectoryReader } from "llamaindex";
documents = new SimpleDirectoryReader().loadData("./data");
```
## API Reference
- [SimpleDirectoryReader](../api/classes/SimpleDirectoryReader.md)
@@ -1,2 +0,0 @@
label: "Document / Nodes"
position: 0
@@ -1,18 +0,0 @@
---
sidebar_position: 1
---
# Documents and Nodes
`Document`s and `Node`s are the basic building blocks of any index. While the API for these objects is similar, `Document` objects represent entire files, while `Node`s are smaller pieces of that original document, that are suitable for an LLM and Q&A.
```typescript
import { Document } from "llamaindex";
document = new Document({ text: "text", metadata: { key: "val" } });
```
## API Reference
- [Document](../api/classes/Document.md)
- [TextNode](../api/classes/TextNode.md)
@@ -1,45 +0,0 @@
# Metadata Extraction Usage Pattern
You can use LLMs to automate metadata extraction with our `Metadata Extractor` modules.
Our metadata extractor modules include the following "feature extractors":
- `SummaryExtractor` - automatically extracts a summary over a set of Nodes
- `QuestionsAnsweredExtractor` - extracts a set of questions that each Node can answer
- `TitleExtractor` - extracts a title over the context of each Node by document and combine them
- `KeywordExtractor` - extracts keywords over the context of each Node
Then you can chain the `Metadata Extractors` with the `IngestionPipeline` to extract metadata from a set of documents.
```ts
import {
IngestionPipeline,
TitleExtractor,
QuestionsAnsweredExtractor,
Document,
OpenAI,
} from "llamaindex";
async function main() {
const pipeline = new IngestionPipeline({
transformations: [
new TitleExtractor(),
new QuestionsAnsweredExtractor({
questions: 5,
}),
],
});
const nodes = await pipeline.run({
documents: [
new Document({ text: "I am 10 years old. John is 20 years old." }),
],
});
for (const node of nodes) {
console.log(node.metadata);
}
}
main().then(() => console.log("done"));
```
-22
View File
@@ -1,22 +0,0 @@
---
sidebar_position: 3
---
# Embedding
The embedding model in LlamaIndex is responsible for creating numerical representations of text. By default, LlamaIndex will use the `text-embedding-ada-002` model from OpenAI.
This can be explicitly set in the `ServiceContext` object.
```typescript
import { OpenAIEmbedding, serviceContextFromDefaults } from "llamaindex";
const openaiEmbeds = new OpenAIEmbedding();
const serviceContext = serviceContextFromDefaults({ embedModel: openaiEmbeds });
```
## API Reference
- [OpenAIEmbedding](../api/classes/OpenAIEmbedding.md)
- [ServiceContext](../api/interfaces//ServiceContext.md)
@@ -1,2 +0,0 @@
label: "Ingestion Pipeline"
position: 2
@@ -1,99 +0,0 @@
# Ingestion Pipeline
An `IngestionPipeline` uses a concept of `Transformations` that are applied to input data.
These `Transformations` are applied to your input data, and the resulting nodes are either returned or inserted into a vector database (if given).
## Usage Pattern
The simplest usage is to instantiate an IngestionPipeline like so:
```ts
import fs from "node:fs/promises";
import {
Document,
IngestionPipeline,
MetadataMode,
OpenAIEmbedding,
TitleExtractor,
SimpleNodeParser,
} from "llamaindex";
async function main() {
// Load essay from abramov.txt in Node
const path = "node_modules/llamaindex/examples/abramov.txt";
const essay = await fs.readFile(path, "utf-8");
// Create Document object with essay
const document = new Document({ text: essay, id_: path });
const pipeline = new IngestionPipeline({
transformations: [
new SimpleNodeParser({ chunkSize: 1024, chunkOverlap: 20 }),
new TitleExtractor(),
new OpenAIEmbedding(),
],
});
// run the pipeline
const nodes = await pipeline.run({ documents: [document] });
// print out the result of the pipeline run
for (const node of nodes) {
console.log(node.getContent(MetadataMode.NONE));
}
}
main().catch(console.error);
```
## Connecting to Vector Databases
When running an ingestion pipeline, you can also chose to automatically insert the resulting nodes into a remote vector store.
Then, you can construct an index from that vector store later on.
```ts
import fs from "node:fs/promises";
import {
Document,
IngestionPipeline,
MetadataMode,
OpenAIEmbedding,
TitleExtractor,
SimpleNodeParser,
QdrantVectorStore,
VectorStoreIndex,
} from "llamaindex";
async function main() {
// Load essay from abramov.txt in Node
const path = "node_modules/llamaindex/examples/abramov.txt";
const essay = await fs.readFile(path, "utf-8");
const vectorStore = new QdrantVectorStore({
host: "http://localhost:6333",
});
// Create Document object with essay
const document = new Document({ text: essay, id_: path });
const pipeline = new IngestionPipeline({
transformations: [
new SimpleNodeParser({ chunkSize: 1024, chunkOverlap: 20 }),
new TitleExtractor(),
new OpenAIEmbedding(),
],
vectorStore,
});
// run the pipeline
const nodes = await pipeline.run({ documents: [document] });
// create an index
const index = VectorStoreIndex.fromVectorStore(vectorStore);
}
main().catch(console.error);
```
@@ -1,77 +0,0 @@
# Transformations
A transformation is something that takes a list of nodes as an input, and returns a list of nodes. Each component that implements the Transformatio class has both a `transform` definition responsible for transforming the nodes
Currently, the following components are Transformation objects:
- [SimpleNodeParser](../api/classes/SimpleNodeParser.md)
- [MetadataExtractor](../documents_and_nodes/metadata_extraction.md)
- Embeddings
## Usage Pattern
While transformations are best used with with an IngestionPipeline, they can also be used directly.
```ts
import { SimpleNodeParser, TitleExtractor, Document } from "llamaindex";
async function main() {
let nodes = new SimpleNodeParser().getNodesFromDocuments([
new Document({ text: "I am 10 years old. John is 20 years old." }),
]);
const titleExtractor = new TitleExtractor();
nodes = await titleExtractor.transform(nodes);
for (const node of nodes) {
console.log(node.getContent(MetadataMode.NONE));
}
}
main().catch(console.error);
```
## Custom Transformations
You can implement any transformation yourself by implementing the `TransformerComponent`.
The following custom transformation will remove any special characters or punctutaion in text.
```ts
import { TransformerComponent, Node } from "llamaindex";
class RemoveSpecialCharacters extends TransformerComponent {
async transform(nodes: Node[]): Promise<Node[]> {
for (const node of nodes) {
node.text = node.text.replace(/[^\w\s]/gi, "");
}
return nodes;
}
}
```
These can then be used directly or in any IngestionPipeline.
```ts
import { IngestionPipeline, Document } from "llamaindex";
async function main() {
const pipeline = new IngestionPipeline({
transformations: [new RemoveSpecialCharacters()],
});
const nodes = await pipeline.run({
documents: [
new Document({ text: "I am 10 years old. John is 20 years old." }),
],
});
for (const node of nodes) {
console.log(node.getContent(MetadataMode.NONE));
}
}
main().catch(console.error);
```
-34
View File
@@ -1,34 +0,0 @@
---
sidebar_position: 3
---
# LLM
The LLM is responsible for reading text and generating natural language responses to queries. By default, LlamaIndex.TS uses `gpt-3.5-turbo`.
The LLM can be explicitly set in the `ServiceContext` object.
```typescript
import { OpenAI, serviceContextFromDefaults } from "llamaindex";
const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
```
## Azure OpenAI
To use Azure OpenAI, you only need to set a few environment variables.
For example:
```
export AZURE_OPENAI_KEY="<YOUR KEY HERE>"
export AZURE_OPENAI_ENDPOINT="<YOUR ENDPOINT, see https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart?tabs=command-line%2Cpython&pivots=rest-api>"
export AZURE_OPENAI_DEPLOYMENT="gpt-4" # or some other deployment name
```
## API Reference
- [OpenAI](../api/classes/OpenAI.md)
- [ServiceContext](../api/interfaces//ServiceContext.md)
-33
View File
@@ -1,33 +0,0 @@
---
sidebar_position: 3
---
# NodeParser
The `NodeParser` in LlamaIndex is responsible for splitting `Document` objects into more manageable `Node` objects. When you call `.fromDocuments()`, the `NodeParser` from the `ServiceContext` is used to do this automatically for you. Alternatively, you can use it to split documents ahead of time.
```typescript
import { Document, SimpleNodeParser } from "llamaindex";
const nodeParser = new SimpleNodeParser();
const nodes = nodeParser.getNodesFromDocuments([
new Document({ text: "I am 10 years old. John is 20 years old." }),
]);
```
## TextSplitter
The underlying text splitter will split text by sentences. It can also be used as a standalone module for splitting raw text.
```typescript
import { SentenceSplitter } from "llamaindex";
const splitter = new SentenceSplitter({ chunkSize: 1 });
const textSplits = splitter.splitText("Hello World");
```
## API Reference
- [SimpleNodeParser](../api/classes/SimpleNodeParser.md)
- [SentenceSplitter](../api/classes/SentenceSplitter.md)
@@ -1,2 +0,0 @@
label: "Query Engines"
position: 2
@@ -1,41 +0,0 @@
# QueryEngine
A query engine wraps a `Retriever` and a `ResponseSynthesizer` into a pipeline, that will use the query string to fetech nodes and then send them to the LLM to generate a response.
```typescript
const queryEngine = index.asQueryEngine();
const response = await queryEngine.query({ query: "query string" });
```
The `query` function also supports streaming, just add `stream: true` as an option:
```typescript
const stream = await queryEngine.query({ query: "query string", stream: true });
for await (const chunk of stream) {
process.stdout.write(chunk.response);
}
```
## Sub Question Query Engine
The basic concept of the Sub Question Query Engine is that it splits a single query into multiple queries, gets an answer for each of those queries, and then combines those different answers into a single coherent response for the user. You can think of it as the "think this through step by step" prompt technique but iterating over your data sources!
### Getting Started
The easiest way to start trying the Sub Question Query Engine is running the subquestion.ts file in [examples](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/subquestion.ts).
```bash
npx ts-node subquestion.ts
```
### Tools
SubQuestionQueryEngine is implemented with Tools. The basic idea of Tools is that they are executable options for the large language model. In this case, our SubQuestionQueryEngine relies on QueryEngineTool, which as you guessed it is a tool to run queries on a QueryEngine. This allows us to give the model an option to query different documents for different questions for example. You could also imagine that the SubQuestionQueryEngine could use a Tool that searches for something on the web or gets an answer using Wolfram Alpha.
You can learn more about Tools by taking a look at the LlamaIndex Python documentation https://gpt-index.readthedocs.io/en/latest/core_modules/agent_modules/tools/root.html
## API Reference
- [RetrieverQueryEngine](../../api/classes/RetrieverQueryEngine.md)
- [SubQuestionQueryEngine](../../api/classes/SubQuestionQueryEngine.md)
- [QueryEngineTool](../../api/interfaces/QueryEngineTool.md)
@@ -1,152 +0,0 @@
# Metadata Filtering
Metadata filtering is a way to filter the documents that are returned by a query based on the metadata associated with the documents. This is useful when you want to filter the documents based on some metadata that is not part of the document text.
You can also check our multi-tenancy blog post to see how metadata filtering can be used in a multi-tenant environment. [https://blog.llamaindex.ai/building-multi-tenancy-rag-system-with-llamaindex-0d6ab4e0c44b] (the article uses the Python version of LlamaIndex, but the concepts are the same).
## Setup
Firstly if you haven't already, you need to install the `llamaindex` package:
```bash
pnpm i llamaindex
```
Then you can import the necessary modules from `llamaindex`:
```ts
import {
ChromaVectorStore,
Document,
VectorStoreIndex,
storageContextFromDefaults,
} from "llamaindex";
const collectionName = "dog_colors";
```
## Creating documents with metadata
You can create documents with metadata using the `Document` class:
```ts
const docs = [
new Document({
text: "The dog is brown",
metadata: {
color: "brown",
dogId: "1",
},
}),
new Document({
text: "The dog is red",
metadata: {
color: "red",
dogId: "2",
},
}),
];
```
## Creating a ChromaDB vector store
You can create a `ChromaVectorStore` to store the documents:
```ts
const chromaVS = new ChromaVectorStore({ collectionName });
const serviceContext = await storageContextFromDefaults({
vectorStore: chromaVS,
});
const index = await VectorStoreIndex.fromDocuments(docs, {
storageContext: serviceContext,
});
```
## Querying the index with metadata filtering
Now you can query the index with metadata filtering using the `preFilters` option:
```ts
const queryEngine = index.asQueryEngine({
preFilters: {
filters: [
{
key: "dogId",
value: "2",
filterType: "ExactMatch",
},
],
},
});
const response = await queryEngine.query({
query: "What is the color of the dog?",
});
console.log(response.toString());
```
## Full Code
```ts
import {
ChromaVectorStore,
Document,
VectorStoreIndex,
storageContextFromDefaults,
} from "llamaindex";
const collectionName = "dog_colors";
async function main() {
try {
const docs = [
new Document({
text: "The dog is brown",
metadata: {
color: "brown",
dogId: "1",
},
}),
new Document({
text: "The dog is red",
metadata: {
color: "red",
dogId: "2",
},
}),
];
console.log("Creating ChromaDB vector store");
const chromaVS = new ChromaVectorStore({ collectionName });
const ctx = await storageContextFromDefaults({ vectorStore: chromaVS });
console.log("Embedding documents and adding to index");
const index = await VectorStoreIndex.fromDocuments(docs, {
storageContext: ctx,
});
console.log("Querying index");
const queryEngine = index.asQueryEngine({
preFilters: {
filters: [
{
key: "dogId",
value: "2",
filterType: "ExactMatch",
},
],
},
});
const response = await queryEngine.query({
query: "What is the color of the dog?",
});
console.log(response.toString());
} catch (e) {
console.error(e);
}
}
main();
```
@@ -1,189 +0,0 @@
# Router Query Engine
In this tutorial, we define a custom router query engine that selects one out of several candidate query engines to execute a query.
## Setup
First, we need to install import the necessary modules from `llamaindex`:
```bash
pnpm i lamaindex
```
```ts
import {
OpenAI,
RouterQueryEngine,
SimpleDirectoryReader,
SimpleNodeParser,
SummaryIndex,
VectorStoreIndex,
serviceContextFromDefaults,
} from "llamaindex";
```
## Loading Data
Next, we need to load some data. We will use the `SimpleDirectoryReader` to load documents from a directory:
```ts
const documents = await new SimpleDirectoryReader().loadData({
directoryPath: "node_modules/llamaindex/examples",
});
```
## Service Context
Next, we need to define some basic rules and parse the documents into nodes. We will use the `SimpleNodeParser` to parse the documents into nodes and `ServiceContext` to define the rules (eg. LLM API key, chunk size, etc.):
```ts
const nodeParser = new SimpleNodeParser({
chunkSize: 1024,
});
const serviceContext = serviceContextFromDefaults({
nodeParser,
llm: new OpenAI(),
});
```
## Creating Indices
Next, we need to create some indices. We will create a `VectorStoreIndex` and a `SummaryIndex`:
```ts
const vectorIndex = await VectorStoreIndex.fromDocuments(documents, {
serviceContext,
});
const summaryIndex = await SummaryIndex.fromDocuments(documents, {
serviceContext,
});
```
## Creating Query Engines
Next, we need to create some query engines. We will create a `VectorStoreQueryEngine` and a `SummaryQueryEngine`:
```ts
const vectorQueryEngine = vectorIndex.asQueryEngine();
const summaryQueryEngine = summaryIndex.asQueryEngine();
```
## Creating a Router Query Engine
Next, we need to create a router query engine. We will use the `RouterQueryEngine` to create a router query engine:
We're defining two query engines, one for summarization and one for retrieving specific context. The router query engine will select the most appropriate query engine based on the query.
```ts
const queryEngine = RouterQueryEngine.fromDefaults({
queryEngineTools: [
{
queryEngine: vectorQueryEngine,
description: "Useful for summarization questions related to Abramov",
},
{
queryEngine: summaryQueryEngine,
description: "Useful for retrieving specific context from Abramov",
},
],
serviceContext,
});
```
## Querying the Router Query Engine
Finally, we can query the router query engine:
```ts
const summaryResponse = await queryEngine.query({
query: "Give me a summary about his past experiences?",
});
console.log({
answer: summaryResponse.response,
metadata: summaryResponse?.metadata?.selectorResult,
});
```
## Full code
```ts
import {
OpenAI,
RouterQueryEngine,
SimpleDirectoryReader,
SimpleNodeParser,
SummaryIndex,
VectorStoreIndex,
serviceContextFromDefaults,
} from "llamaindex";
async function main() {
// Load documents from a directory
const documents = await new SimpleDirectoryReader().loadData({
directoryPath: "node_modules/llamaindex/examples",
});
// Parse the documents into nodes
const nodeParser = new SimpleNodeParser({
chunkSize: 1024,
});
// Create a service context
const serviceContext = serviceContextFromDefaults({
nodeParser,
llm: new OpenAI(),
});
// Create indices
const vectorIndex = await VectorStoreIndex.fromDocuments(documents, {
serviceContext,
});
const summaryIndex = await SummaryIndex.fromDocuments(documents, {
serviceContext,
});
// Create query engines
const vectorQueryEngine = vectorIndex.asQueryEngine();
const summaryQueryEngine = summaryIndex.asQueryEngine();
// Create a router query engine
const queryEngine = RouterQueryEngine.fromDefaults({
queryEngineTools: [
{
queryEngine: vectorQueryEngine,
description: "Useful for summarization questions related to Abramov",
},
{
queryEngine: summaryQueryEngine,
description: "Useful for retrieving specific context from Abramov",
},
],
serviceContext,
});
// Query the router query engine
const summaryResponse = await queryEngine.query({
query: "Give me a summary about his past experiences?",
});
console.log({
answer: summaryResponse.response,
metadata: summaryResponse?.metadata?.selectorResult,
});
const specificResponse = await queryEngine.query({
query: "Tell me about abramov first job?",
});
console.log({
answer: specificResponse.response,
metadata: specificResponse.metadata.selectorResult,
});
}
main().then(() => console.log("Done"));
```
@@ -1,64 +0,0 @@
---
sidebar_position: 6
---
# ResponseSynthesizer
The ResponseSynthesizer is responsible for sending the query, nodes, and prompt templates to the LLM to generate a response. There are a few key modes for generating a response:
- `Refine`: "create and refine" an answer by sequentially going through each retrieved text chunk.
This makes a separate LLM call per Node. Good for more detailed answers.
- `CompactAndRefine` (default): "compact" the prompt during each LLM call by stuffing as
many text chunks that can fit within the maximum prompt size. If there are
too many chunks to stuff in one prompt, "create and refine" an answer by going through
multiple compact prompts. The same as `refine`, but should result in less LLM calls.
- `TreeSummarize`: Given a set of text chunks and the query, recursively construct a tree
and return the root node as the response. Good for summarization purposes.
- `SimpleResponseBuilder`: Given a set of text chunks and the query, apply the query to each text
chunk while accumulating the responses into an array. Returns a concatenated string of all
responses. Good for when you need to run the same query separately against each text
chunk.
```typescript
import { NodeWithScore, ResponseSynthesizer, TextNode } from "llamaindex";
const responseSynthesizer = new ResponseSynthesizer();
const nodesWithScore: NodeWithScore[] = [
{
node: new TextNode({ text: "I am 10 years old." }),
score: 1,
},
{
node: new TextNode({ text: "John is 20 years old." }),
score: 0.5,
},
];
const response = await responseSynthesizer.synthesize({
query: "What age am I?",
nodesWithScore,
});
console.log(response.response);
```
The `synthesize` function also supports streaming, just add `stream: true` as an option:
```typescript
const stream = await responseSynthesizer.synthesize({
query: "What age am I?",
nodesWithScore,
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.response);
}
```
## API Reference
- [ResponseSynthesizer](../api/classes/ResponseSynthesizer.md)
- [Refine](../api/classes/Refine.md)
- [CompactAndRefine](../api/classes/CompactAndRefine.md)
- [TreeSummarize](../api/classes/TreeSummarize.md)
- [SimpleResponseBuilder](../api/classes/SimpleResponseBuilder.md)
-21
View File
@@ -1,21 +0,0 @@
---
sidebar_position: 5
---
# Retriever
A retriever in LlamaIndex is what is used to fetch `Node`s from an index using a query string. Aa `VectorIndexRetriever` will fetch the top-k most similar nodes. Meanwhile, a `SummaryIndexRetriever` will fetch all nodes no matter the query.
```typescript
const retriever = vector_index.asRetriever();
retriever.similarityTopK = 3;
// Fetch nodes!
const nodesWithScore = await retriever.retrieve("query string");
```
## API Reference
- [SummaryIndexRetriever](../api/classes/SummaryIndexRetriever.md)
- [SummaryIndexLLMRetriever](../api/classes/SummaryIndexLLMRetriever.md)
- [VectorIndexRetriever](../api/classes/VectorIndexRetriever.md)
-26
View File
@@ -1,26 +0,0 @@
---
sidebar_position: 7
---
# Storage
Storage in LlamaIndex.TS works automatically once you've configured a `StorageContext` object. Just configure the `persistDir` and attach it to an index.
Right now, only saving and loading from disk is supported, with future integrations planned!
```typescript
import { Document, VectorStoreIndex, storageContextFromDefaults } from "./src";
const storageContext = await storageContextFromDefaults({
persistDir: "./storage",
});
const document = new Document({ text: "Test Text" });
const index = await VectorStoreIndex.fromDocuments([document], {
storageContext,
});
```
## API Reference
- [StorageContext](../api/interfaces//StorageContext.md)
@@ -1,2 +0,0 @@
label: "Vector Stores"
position: 1
@@ -1,86 +0,0 @@
# Qdrant Vector Store
To run this example, you need to have a Qdrant instance running. You can run it with Docker:
```bash
docker pull qdrant/qdrant
docker run -p 6333:6333 qdrant/qdrant
```
## Importing the modules
```ts
import fs from "node:fs/promises";
import { Document, VectorStoreIndex, QdrantVectorStore } from "llamaindex";
```
## Load the documents
```ts
const path = "node_modules/llamaindex/examples/abramov.txt";
const essay = await fs.readFile(path, "utf-8");
```
## Setup Qdrant
```ts
const vectorStore = new QdrantVectorStore({
url: "http://localhost:6333",
});
```
## Setup the index
```ts
const document = new Document({ text: essay, id_: path });
const index = await VectorStoreIndex.fromDocuments([document], {
vectorStore,
});
```
## Query the index
```ts
const queryEngine = index.asQueryEngine();
const response = await queryEngine.query({
query: "What did the author do in college?",
});
// Output response
console.log(response.toString());
```
## Full code
```ts
import fs from "node:fs/promises";
import { Document, VectorStoreIndex, QdrantVectorStore } from "llamaindex";
async function main() {
const path = "node_modules/llamaindex/examples/abramov.txt";
const essay = await fs.readFile(path, "utf-8");
const vectorStore = new QdrantVectorStore({
url: "http://localhost:6333",
});
const document = new Document({ text: essay, id_: path });
const index = await VectorStoreIndex.fromDocuments([document], {
vectorStore,
});
const queryEngine = index.asQueryEngine();
const response = await queryEngine.query({
query: "What did the author do in college?",
});
// Output response
console.log(response.toString());
}
main().catch(console.error);
```
@@ -1,2 +0,0 @@
label: Observability
position: 5
-35
View File
@@ -1,35 +0,0 @@
# Observability
LlamaIndex provides **one-click observability** 🔭 to allow you to build principled LLM applications in a production setting.
A key requirement for principled development of LLM applications over your data (RAG systems, agents) is being able to observe, debug, and evaluate
your system - both as a whole and for each component.
This feature allows you to seamlessly integrate the LlamaIndex library with powerful observability/evaluation tools offered by our partners.
Configure a variable once, and you'll be able to do things like the following:
- View LLM/prompt inputs/outputs
- Ensure that the outputs of any component (LLMs, embeddings) are performing as expected
- View call traces for both indexing and querying
Each provider has similarities and differences. Take a look below for the full set of guides for each one!
## OpenLLMetry
[OpenLLMetry](https://github.com/traceloop/openllmetry-js) is an open-source project based on OpenTelemetry for tracing and monitoring
LLM applications. It connects to [all major observability platforms](https://www.traceloop.com/docs/openllmetry/integrations/introduction) and installs in minutes.
### Usage Pattern
```bash
npm install @traceloop/node-server-sdk
```
```js
import * as traceloop from "@traceloop/node-server-sdk";
traceloop.initialize({
apiKey: process.env.TRACELOOP_API_KEY,
disableBatch: true,
});
```
-181
View File
@@ -1,181 +0,0 @@
// @ts-check
// Note: type annotations allow type checking and IDEs autocompletion
const renderer = require("prism-react-renderer");
const lightCodeTheme = renderer.themes.github;
const darkCodeTheme = renderer.themes.dracula;
/** @type {import('@docusaurus/types').Config} */
const config = {
title: "LlamaIndex.TS",
tagline: "Unleash the power of LLMs over your data in TypeScript",
favicon: "img/favicon.png",
// Set the production url of your site here
url: "https://ts.llamaindex.ai",
// Set the /<baseUrl>/ pathname under which your site is served
// For GitHub pages deployment, it is often '/<projectName>/'
baseUrl: "/",
// GitHub pages deployment config.
// If you aren't using GitHub pages, you don't need these.
organizationName: "run-llama", // Usually your GitHub org/user name.
projectName: "LlamaIndex.TS", // Usually your repo name.
onBrokenLinks: "warn",
onBrokenMarkdownLinks: "warn",
// Even if you don't use internalization, you can use this field to set useful
// metadata like html lang. For example, if your site is Chinese, you may want
// to replace "en" with "zh-Hans".
i18n: {
defaultLocale: "en",
locales: [
"en",
"zh-Hans",
"es",
"fr",
"de",
"ja",
"ko",
"pt",
"ar",
"it",
"tr",
"pl",
"nl",
"vi",
"th",
], // "fa", "ru", "ro", "sv", "hu", "cs", "el", "da", "fi", "he", "no", "hi", "in", "sl", "se", "sk", "uk", "bg", "hr", "lt", "lv", "et", "cat"
},
presets: [
[
"@docusaurus/preset-classic",
/** @type {import('@docusaurus/preset-classic').Options} */
({
docs: {
path: "docs",
routeBasePath: "/",
sidebarPath: require.resolve("./sidebars.js"),
// Please change this to your repo.
// Remove this to remove the "edit this page" links.
// editUrl:
// "https://github.com/facebook/docusaurus/tree/main/packages/create-docusaurus/templates/shared/",
remarkPlugins: [
[require("@docusaurus/remark-plugin-npm2yarn"), { sync: true }],
],
},
blog: false,
gtag: {
trackingID: "G-NB9B8LW9W5",
anonymizeIP: true,
},
}),
],
],
themeConfig:
/** @type {import('@docusaurus/preset-classic').ThemeConfig} */
({
// Replace with your project's social card
image: "img/favicon.png", // TODO change this
navbar: {
title: "LlamaIndex.TS",
logo: {
alt: "LlamaIndex.TS",
src: "img/favicon.png",
},
items: [
{
type: "docSidebar",
sidebarId: "mySidebar",
position: "left",
label: "Docs",
},
{
type: "localeDropdown",
position: "left",
},
{
href: "https://github.com/run-llama/LlamaIndexTS",
label: "GitHub",
position: "right",
},
],
},
footer: {
style: "dark",
links: [
{
title: "Docs",
items: [
{
label: "API",
to: "/api",
},
],
},
{
title: "Community",
items: [
{
label: "Discord",
href: "https://discord.com/invite/eN6D2HQ4aX",
},
{
label: "Twitter",
href: "https://twitter.com/LlamaIndex",
},
],
},
{
title: "More",
items: [
{
label: "GitHub",
href: "https://github.com/run-llama/LlamaIndexTS",
},
],
},
],
copyright: `Copyright © ${new Date().getFullYear()} LlamaIndex. Built with Docusaurus.`,
},
prism: {
theme: lightCodeTheme,
darkTheme: darkCodeTheme,
},
algolia: {
// The application ID provided by Algolia
appId: "DYKPM6G4CX",
// Public API key: it is safe to commit it
apiKey: "c4ff3789f20bb72a5d735082aef17719",
indexName: "ts-llamaindex",
// Optional: see doc section below
contextualSearch: true,
},
}),
plugins: [
[
"docusaurus-plugin-typedoc",
{
entryPoints: ["../../packages/core/src/index.ts"],
tsconfig: "../../packages/core/tsconfig.json",
readme: "none",
sourceLinkTemplate:
"https://github.com/run-llama/LlamaIndexTS/blob/{gitRevision}/{path}#L{line}",
sidebar: {
position: 6,
},
},
],
],
markdown: {
format: "detect",
},
};
module.exports = config;
Binary file not shown.

Before

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 49 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 36 KiB

@@ -1 +0,0 @@
../../../../docs/api
@@ -1,86 +0,0 @@
---
sidebar_position: 3
---
# المفاهيم على المستوى العالي
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
يساعدك LlamaIndex.TS في بناء تطبيقات قائمة على LLM (مثل Q&A و chatbot) على بيانات مخصصة.
في هذا الدليل عن المفاهيم على المستوى العالي، ستتعلم:
- كيف يمكن لـ LLM الإجابة على الأسئلة باستخدام بياناتك الخاصة.
- المفاهيم الرئيسية والوحدات في LlamaIndex.TS لبناء خط أنابيب الاستعلام الخاص بك.
## الإجابة على الأسئلة عبر بياناتك
يستخدم LlamaIndex طريقة مكونة من مرحلتين عند استخدام LLM مع بياناتك:
1. **مرحلة الفهرسة**: إعداد قاعدة المعرفة، و
2. **مرحلة الاستعلام**: استرداد السياق ذي الصلة من المعرفة لمساعدة LLM في الاستجابة لسؤال
![](./_static/concepts/rag.jpg)
تُعرف هذه العملية أيضًا باسم "استرجاع معزز للتوليد" (RAG).
يوفر LlamaIndex.TS أدوات أساسية لجعل كلا المرحلتين سهلتين للغاية.
دعنا نستكشف كل مرحلة بالتفصيل.
### مرحلة الفهرسة
يساعدك LlamaIndex.TS في إعداد قاعدة المعرفة باستخدام مجموعة من موصلات البيانات والفهارس.
![](./_static/concepts/indexing.jpg)
[**محمّلات البيانات**](./modules/high_level/data_loader.md):
موصل البيانات (أي `Reader`) يقوم بتجميع البيانات من مصادر بيانات مختلفة وتنسيقات بيانات مختلفة في تمثيل بسيط للـ `Document` (نص وبيانات تعريفية بسيطة).
[**المستندات / العقد**](./modules/high_level/documents_and_nodes.md): المستند هو حاوية عامة حول أي مصدر بيانات - على سبيل المثال، ملف PDF، نتائج واجهة برمجة التطبيقات، أو بيانات استرداد من قاعدة بيانات. العقد هو الوحدة الذرية للبيانات في LlamaIndex ويمثل "قطعة" من المستند الأصلي. إنه تمثيل غني يتضمن بيانات تعريفية وعلاقات (مع عقد أخرى) لتمكين عمليات الاسترجاع الدقيقة والتعبيرية.
[**فهارس البيانات**](./modules/high_level/data_index.md):
بمجرد أن تقوم بتجميع بياناتك، يساعدك LlamaIndex في فهرسة البيانات في تنسيق سهل الاسترداد.
تحت الغطاء، يقوم LlamaIndex بتحليل المستندات الخام إلى تمثيلات وسيطة، وحساب تضمينات الناقلات، وتخزين بياناتك في الذاكرة أو على القرص.
"
### مرحلة الاستعلام
في مرحلة الاستعلام، يقوم خط الأنابيب للاستعلام بجلب السياق الأكثر صلة بناءً على استعلام المستخدم،
ويمرر ذلك إلى LLM (جنبًا إلى جنب مع الاستعلام) لتوليد استجابة.
يمنح ذلك LLM معرفة محدثة ليست موجودة في بيانات التدريب الأصلية لديه،
(مما يقلل أيضًا من الهلوسة).
التحدي الرئيسي في مرحلة الاستعلام هو الاسترجاع والتنسيق والاستدلال عبر قواعد المعرفة (المحتملة).
يوفر LlamaIndex وحدات قابلة للتركيب تساعدك في بناء ودمج خطوط أنابيب RAG لـ Q&A (محرك الاستعلام)، chatbot (محرك الدردشة)، أو كجزء من وكيل.
يمكن تخصيص هذه الكتل البنائية لتعكس تفضيلات التصنيف، وكذلك تركيبها للاستدلال عبر عدة قواعد معرفة بطريقة منظمة.
![](./_static/concepts/querying.jpg)
#### الكتل الأساسية
[**مسترجعات**](./modules/low_level/retriever.md):
يحدد المسترجع كيفية استرجاع السياق ذي الصلة بكفاءة من قاعدة المعرفة (أي الفهرس) عند إعطاء استعلام.
تختلف منطق الاسترجاع المحددة حسب الفهارس المختلفة، والأكثر شيوعًا هو الاسترجاع الكثيف ضد فهرس الناقل.
[**مركبات الاستجابة**](./modules/low_level/response_synthesizer.md):
تقوم مركبة الاستجابة بتوليد استجابة من LLM باستخدام استعلام المستخدم ومجموعة معينة من أجزاء النص المسترجعة.
"
#### خطوط الأنابيب
[**محركات الاستعلام**](./modules/high_level/query_engine.md):
محرك الاستعلام هو خط أنابيب شامل يتيح لك طرح الأسئلة على بياناتك.
يأخذ استعلامًا بلغة طبيعية ويعيد استجابة، جنبًا إلى جنب مع السياق المرجعي المسترجع والممرر إلى LLM.
[**محركات الدردشة**](./modules/high_level/chat_engine.md):
محرك الدردشة هو خط أنابيب شامل لإجراء محادثة مع بياناتك
(عدة تفاعلات بدلاً من سؤال وجواب واحد).
"
@@ -1,61 +0,0 @@
---
sidebar_position: 4
---
# أمثلة من البداية إلى النهاية
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
نقدم العديد من الأمثلة من البداية إلى النهاية باستخدام LlamaIndex.TS في المستودع
تحقق من الأمثلة أدناه أو جربها وأكملها في دقائق مع دروس تفاعلية على Github Codespace المقدمة من Dev-Docs [هنا](https://codespaces.new/team-dev-docs/lits-dev-docs-playground?devcontainer_path=.devcontainer%2Fjavascript_ltsquickstart%2Fdevcontainer.json):
## [محرك الدردشة](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/chatEngine.ts)
اقرأ ملفًا وتحدث عنه مع LLM.
## [فهرس الفيكتور](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/vectorIndex.ts)
إنشاء فهرس فيكتور واستعلامه. سيستخدم فهرس الفيكتور التضمينات لاسترداد أعلى k عقد ذات صلة. بشكل افتراضي ، يكون k الأعلى هو 2.
"
## [مؤشر الملخص](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/summaryIndex.ts)
إنشاء مؤشر قائمة واستعلامه. يستخدم هذا المثال أيضًا `LLMRetriever` ، الذي سيستخدم LLM لتحديد أفضل العقد لاستخدامها عند إنشاء الإجابة.
"
## [حفظ / تحميل فهرس](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/storageContext.ts)
إنشاء وتحميل فهرس ناقل. يحدث التخزين المؤقت على القرص تلقائيًا في LlamaIndex.TS بمجرد إنشاء كائن سياق التخزين.
"
## [فهرس الناقل المخصص](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/vectorIndexCustomize.ts)
إنشاء فهرس ناقل واستعلامه، مع تكوين `LLM` و `ServiceContext` و `similarity_top_k`.
"
## [OpenAI LLM](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/openai.ts)
أنشئ OpenAI LLM واستخدمه مباشرة للدردشة.
"
## [Llama2 DeuceLLM](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/llamadeuce.ts)
إنشاء Llama-2 LLM واستخدامه مباشرة للدردشة.
"
## [محرك استعلام الأسئلة الفرعية](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/subquestion.ts)
يستخدم `محرك استعلام الأسئلة الفرعية` الذي يقسم الاستعلامات المعقدة إلى أسئلة فرعية متعددة، ثم يجمع الاستجابة عبر الإجابات على جميع الأسئلة الفرعية.
"
## [وحدات منخفضة المستوى](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/lowlevel.ts)
يستخدم هذا المثال العديد من المكونات منخفضة المستوى، مما يزيل الحاجة إلى محرك استعلام فعلي. يمكن استخدام هذه المكونات في أي مكان، في أي تطبيق، أو تخصيصها وتصنيفها الفرعي لتلبية احتياجاتك الخاصة.
@@ -1,17 +0,0 @@
---
sidebar_position: 5
---
# البيئات
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
يدعم LlamaIndex حاليًا رسميًا NodeJS 18 و NodeJS 20.
## NextJS App Router
إذا كنت تستخدم معالج الطرق / الوظائف الخادمة في NextJS App Router ، فستحتاج إلى استخدام وضع NodeJS:
```js
export const runtime = "nodejs"; // الافتراضي
```
@@ -1,67 +0,0 @@
---
sidebar_position: 1
---
# التثبيت والإعداد
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
تأكد من أن لديك NodeJS v18 أو أحدث.
## باستخدام create-llama
أسهل طريقة للبدء مع LlamaIndex هي باستخدام `create-llama`. هذه الأداة سطر الأوامر تمكنك من بدء بناء تطبيق LlamaIndex جديد بسرعة، مع كل شيء معد لك.
ما عليك سوى تشغيل
<Tabs>
<TabItem value="1" label="npm" default>
```bash
npx create-llama@latest
```
</TabItem>
<TabItem value="2" label="Yarn">
```bash
yarn create llama
```
</TabItem>
<TabItem value="3" label="pnpm">
```bash
pnpm create llama@latest
```
</TabItem>
</Tabs>
للبدء. بمجرد إنشاء التطبيق الخاص بك، قم بتشغيل
```bash npm2yarn
npm run dev
```
لبدء خادم التطوير. يمكنك ثم زيارة [http://localhost:3000](http://localhost:3000) لرؤية تطبيقك.
## التثبيت من NPM
```bash npm2yarn
npm install llamaindex
```
### المتغيرات البيئية
تستخدم أمثلتنا OpenAI افتراضيًا. ستحتاج إلى إعداد مفتاح Open AI الخاص بك على النحو التالي:
```bash
export OPENAI_API_KEY="sk-......" # استبدله بالمفتاح الخاص بك من https://platform.openai.com/account/api-keys
```
إذا كنت ترغب في تحميله تلقائيًا في كل مرة، قم بإضافته إلى ملف .zshrc/.bashrc الخاص بك.
تحذير: لا تقم بإضافة مفتاح OpenAI الخاص بك إلى نظام التحكم في الإصدارات.
"
@@ -1,60 +0,0 @@
---
sidebar_position: 0
slug: /
---
# ما هو LlamaIndex.TS؟
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
LlamaIndex.TS هو إطار بيانات لتطبيقات LLM لاستيعاب وتنظيم والوصول إلى البيانات الخاصة أو الخاصة بالمجال. في حين أن حزمة Python متاحة أيضًا (انظر [هنا](https://docs.llamaindex.ai/en/stable/)), يوفر LlamaIndex.TS ميزات أساسية في حزمة بسيطة ، محسنة للاستخدام مع TypeScript.
## 🚀 لماذا LlamaIndex.TS؟
في جوهرها ، توفر LLMs واجهة لغة طبيعية بين البشر والبيانات المستنتجة. تأتي النماذج المتاحة على نطاق واسع محملة مسبقًا بكميات هائلة من البيانات المتاحة للجمهور ، من ويكيبيديا وقوائم البريد الإلكتروني إلى الكتب المدرسية وشفرة المصدر.
غالبًا ما تتطلب التطبيقات المبنية على LLMs تعزيز هذه النماذج بالبيانات الخاصة أو الخاصة بالمجال. للأسف ، يمكن توزيع هذه البيانات عبر تطبيقات ومخازن بيانات معزولة. إنها خلف واجهات برمجة التطبيقات ، في قواعد البيانات SQL ، أو محبوسة في ملفات PDF وعروض تقديمية.
هنا يأتي دور **LlamaIndex.TS**.
## 🦙 كيف يمكن أن يساعد LlamaIndex.TS؟
يوفر LlamaIndex.TS الأدوات التالية:
- **تحميل البيانات**: استيعاب البيانات الحالية الخاصة بك بتنسيقات `.txt`, `.pdf`, `.csv`, `.md` و `.docx` مباشرة.
- **فهارس البيانات**: تنظيم البيانات الخاصة بك في تمثيلات وسيطة سهلة وفعالة للاستخدام من قبل LLMs.
- **المحركات**: توفر واجهات الوصول إلى اللغة الطبيعية لبياناتك. على سبيل المثال:
- محركات الاستعلام هي واجهات استرجاع قوية للإخراج المعزز بالمعرفة.
- محركات الدردشة هي واجهات محادثة للتفاعلات "ذهابًا وإيابًا" متعددة الرسائل مع بياناتك.
## 👨‍👩‍👧‍👦 من أجل من هو LlamaIndex؟
يوفر LlamaIndex.TS مجموعة أدوات أساسية ، ضرورية لأي شخص يقوم ببناء تطبيقات LLM باستخدام JavaScript و TypeScript.
يتيح لنا واجهة برمجة التطبيقات على مستوى عالي استخدام LlamaIndex.TS لاستيعاب واستعلام البيانات الخاصة بهم.
بالنسبة للتطبيقات المعقدة أكثر ، تتيح لنا واجهات برمجة التطبيقات على مستوى أدنى للمستخدمين المتقدمين تخصيص وتوسيع أي وحدة - موصلات البيانات والفهارس وأجهزة الاسترجاع ومحركات الاستعلام - لتناسب احتياجاتهم.
## البدء
`npm install llamaindex`
تتضمن وثائقنا [تعليمات التثبيت](./installation.mdx) و[دليل البداية](./starter.md) لبناء تطبيقك الأول.
بمجرد أن تكون جاهزًا وتعمل ، يحتوي [مفاهيم عالية المستوى](./getting_started/concepts.md) على نظرة عامة على الهندسة المعمارية المتعددة المستويات لـ LlamaIndex. لمزيد من الأمثلة العملية التفصيلية ، يمكنك الاطلاع على [دروس النهاية إلى النهاية](./end_to_end.md).
## 🗺️ النظام البيئي
لتنزيل أو المساهمة ، ابحث عن LlamaIndex على:
- Github: https://github.com/run-llama/LlamaIndexTS
- NPM: https://www.npmjs.com/package/llamaindex
"
## المجتمع
هل تحتاج إلى مساعدة؟ هل لديك اقتراح لميزة؟ انضم إلى مجتمع LlamaIndex:
- تويتر: https://twitter.com/llama_index
- ديسكورد: https://discord.gg/dGcwcsnxhU
@@ -1,22 +0,0 @@
---
sidebar_position: 4
---
# محرك الدردشة (ChatEngine)
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
محرك الدردشة هو طريقة سريعة وبسيطة للدردشة مع البيانات في الفهرس الخاص بك.
```typescript
const retriever = index.asRetriever();
const chatEngine = new ContextChatEngine({ retriever });
// بدء الدردشة
const response = await chatEngine.chat(query);
```
## مراجع الواجهة البرمجية
- [محرك الدردشة السياقي (ContextChatEngine)](../../api/classes/ContextChatEngine.md)
- [محرك الدردشة المكثف للأسئلة (CondenseQuestionChatEngine)](../../api/classes/ContextChatEngine.md)
@@ -1,27 +0,0 @@
---
sidebar_position: 2
---
# الفهرس
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
الفهرس هو الحاوية الأساسية والتنظيم لبياناتك. يدعم LlamaIndex.TS نوعين من الفهارس:
- `VectorStoreIndex` - سيقوم بإرسال أعلى `Node` الموجودة إلى LLM عند إنشاء استجابة. القيمة الافتراضية لأعلى `k` هي 2.
- `SummaryIndex` - سيقوم بإرسال كل `Node` في الفهرس إلى LLM لإنشاء استجابة.
```typescript
import { Document, VectorStoreIndex } from "llamaindex";
const document = new Document({ text: "اختبار" });
const index = await VectorStoreIndex.fromDocuments([document]);
```
## مرجع الواجهة البرمجية
- [SummaryIndex](../../api/classes/SummaryIndex.md)
- [VectorStoreIndex](../../api/classes/VectorStoreIndex.md)
"
@@ -1,19 +0,0 @@
---
sidebar_position: 1
---
# قارئ / محمل
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
يدعم LlamaIndex.TS تحميل الملفات بسهولة من المجلدات باستخدام فئة `SimpleDirectoryReader`. حاليًا ، يتم دعم الملفات `.txt` ، `.pdf` ، `.csv` ، `.md` و `.docx` ، مع المزيد المخطط له في المستقبل!
```typescript
import { SimpleDirectoryReader } from "llamaindex";
documents = new SimpleDirectoryReader().loadData("./data");
```
## مرجع الواجهة البرمجية
- [SimpleDirectoryReader](../../api/classes/SimpleDirectoryReader.md)
@@ -1,22 +0,0 @@
---
sidebar_position: 0
---
# المستندات والعقد
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
`المستندات` و `العقد` هما العناصر الأساسية لأي فهرس. بينما يكون واجهة برمجة التطبيق (API) لهذه الكائنات مشابهة، يُمثل كائن `المستند` ملفات كاملة، بينما تكون `العقد` قطعًا أصغر من ذلك المستند الأصلي، والتي تكون مناسبة لـ LLM و Q&A.
```typescript
import { Document } from "llamaindex";
document = new Document({ text: "نص", metadata: { key: "val" } });
```
## مرجع الواجهة البرمجية
- [المستند (Document)](../../api/classes/Document.md)
- [نص العقد (TextNode)](../../api/classes/TextNode.md)
"
@@ -1,42 +0,0 @@
---
sidebar_position: 3
---
# محرك الاستعلامات (QueryEngine)
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
يقوم محرك الاستعلامات بتجميع "Retriever" و "ResponseSynthesizer" في أنبوبة، والتي ستستخدم سلسلة الاستعلام لاسترداد العقد ومن ثم إرسالها إلى LLM لتوليد استجابة.
```typescript
const queryEngine = index.asQueryEngine();
const response = await queryEngine.query("سلسلة الاستعلام");
```
## محرك الاستعلام للأسئلة الفرعية
الفكرة الأساسية لمحرك الاستعلام للأسئلة الفرعية هي تقسيم استعلام واحد إلى استعلامات متعددة، والحصول على إجابة لكل من تلك الاستعلامات، ثم دمج تلك الإجابات المختلفة في استجابة واحدة متسقة للمستخدم. يمكنك أن تفكر فيها كتقنية "فكر في ذلك خطوة بخطوة" ولكن بتكرار مصادر البيانات الخاصة بك!
### البدء
أسهل طريقة لبدء تجربة محرك الاستعلام للأسئلة الفرعية هي تشغيل ملف subquestion.ts في [examples](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/subquestion.ts).
```bash
npx ts-node subquestion.ts
```
"
### الأدوات
يتم تنفيذ محرك الاستعلام للأسئلة الفرعية باستخدام الأدوات. الفكرة الأساسية للأدوات هي أنها خيارات قابلة للتنفيذ لنموذج اللغة الكبيرة. في هذه الحالة، يعتمد محرك الاستعلام للأسئلة الفرعية على أداة QueryEngineTool، والتي كما تخمن هي أداة لتشغيل استعلامات على محرك الاستعلام. يتيح لنا ذلك إعطاء النموذج خيارًا للاستعلام عن وثائق مختلفة لأسئلة مختلفة على سبيل المثال. يمكنك أيضًا أن تتخيل أن محرك الاستعلام للأسئلة الفرعية يمكنه استخدام أداة تبحث عن شيء ما على الويب أو تحصل على إجابة باستخدام Wolfram Alpha.
يمكنك معرفة المزيد عن الأدوات من خلال الاطلاع على وثائق LlamaIndex Python https://gpt-index.readthedocs.io/en/latest/core_modules/agent_modules/tools/root.html
"
## مرجع واجهة برمجة التطبيق (API)
- [محرك استعلام الاسترجاع (RetrieverQueryEngine)](../../api/classes/RetrieverQueryEngine.md)
- [محرك استعلام السؤال الفرعي (SubQuestionQueryEngine)](../../api/classes/SubQuestionQueryEngine.md)
- [أداة محرك الاستعلام (QueryEngineTool)](../../api/interfaces/QueryEngineTool.md)
@@ -1,33 +0,0 @@
# الوحدات الأساسية
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
يوفر LlamaIndex.TS عدة وحدات أساسية، مقسمة إلى وحدات عالية المستوى للبدء السريع ووحدات منخفضة المستوى لتخصيص المكونات الرئيسية حسب الحاجة.
## وحدات عالية المستوى
- [**المستند**](./high_level/documents_and_nodes.md): يمثل المستند ملف نصي أو ملف PDF أو قطعة بيانات متتابعة أخرى.
- [**العقدة**](./high_level/documents_and_nodes.md): هو البناء الأساسي للبيانات. في أغلب الأحيان، تكون هذه أجزاء من المستند المقسمة إلى قطع قابلة للإدارة وصغيرة بما يكفي ليتم تغذيتها إلى نموذج التضمين و LLM.
- [**القارئ/المحمل**](./high_level/data_loader.md): القارئ أو المحمل هو شيء يأخذ المستند في العالم الحقيقي ويحوله إلى فئة المستند التي يمكن استخدامها في الفهرس الخاص بك والاستعلامات. ندعم حاليًا ملفات النص العادي وملفات PDF والمزيد الكثير.
- [**الفهارس**](./high_level/data_index.md): تخزن الفهارس العقد وتضمينات تلك العقد.
- [**محرك الاستعلامات**](./high_level/query_engine.md): محركات الاستعلامات هي التي تولد الاستعلام الذي تدخله وتعيد لك النتيجة. عمومًا، تجمع محركات الاستعلامات بين تعليمة مسبقة مبنية مع العقد المحددة من الفهرس الخاص بك لتعطي LLM السياق الذي يحتاجه للإجابة على استعلامك.
- [**محرك الدردشة**](./high_level/chat_engine.md): يساعدك محرك الدردشة على بناء روبوت دردشة سيتفاعل مع فهرسك.
## وحدة منخفضة المستوى
- [**LLM**](./low_level/llm.md): فئة LLM هي واجهة موحدة فوق مزود نموذج لغة كبير مثل OpenAI GPT-4 أو Anthropic Claude أو Meta LLaMA. يمكنك توريثها لكتابة موصل إلى نموذج اللغة الخاص بك.
- [**Embedding**](./low_level/embedding.md): يتم تمثيل التضمين كمتجه من الأرقام العائمة. نموذج التضمين الافتراضي لدينا هو text-embedding-ada-002 من OpenAI ويتكون كل تضمين يولده من 1,536 رقمًا عائمًا. نموذج التضمين الشائع الآخر هو BERT الذي يستخدم 768 رقمًا عائمًا لتمثيل كل عقدة. نوفر عددًا من الأدوات للعمل مع التضمين بما في ذلك 3 خيارات لحساب التشابه و Maximum Marginal Relevance.
- [**TextSplitter/NodeParser**](./low_level/node_parser.md): تعتبر استراتيجيات تقسيم النصوص مهمة للغاية لفعالية البحث في التضمين. حاليًا، على الرغم من أن لدينا قيمة افتراضية، إلا أنه لا يوجد حلاً مناسبًا للجميع. اعتمادًا على وثائق المصدر، قد ترغب في استخدام أحجام واستراتيجيات تقسيم مختلفة. حاليًا، ندعم التقسيم حسب الحجم الثابت، التقسيم حسب الحجم الثابت مع أجزاء تتداخل، التقسيم حسب الجملة، والتقسيم حسب الفقرة. يتم استخدام مقسم النصوص بواسطة NodeParser عند تقسيم `Document` إلى `Node`.
- [**Retriever**](./low_level/retriever.md): يقوم Retriever بتحديد العقد التي يتم استردادها من الفهرس. هنا، قد ترغب في محاولة استرداد عدد أكبر أو أقل من العقد لكل استعلام، تغيير وظيفة التشابه الخاصة بك، أو إنشاء استرداد خاص بك لكل حالة استخدام فردية في تطبيقك. على سبيل المثال، قد ترغب في وجود استرداد منفصل لمحتوى الشفرة مقابل محتوى النص.
- [**ResponseSynthesizer**](./low_level/response_synthesizer.md): يتحمل ResponseSynthesizer مسؤولية أخذ سلسلة استعلام واستخدام قائمة من العقد لإنشاء استجابة. يمكن أن يأخذ هذا الشكل العديد من الأشكال، مثل التكرار عبر جميع السياق وتحسين الإجابة، أو بناء شجرة من الملخصات وإرجاع الملخص الجذري.
- [**Storage**](./low_level/storage.md): في نقطة ما، سترغب في تخزين الفهارس والبيانات والمتجهات بدلاً من إعادة تشغيل نماذج التضمين في كل مرة. IndexStore و DocStore و VectorStore و KVStore هي تجريدات تتيح لك ذلك. مجتمعة، تشكل هذه التجريدات سياق التخزين. حاليًا، نسمح لك بالاحتفاظ بالتضمينات الخاصة بك في ملفات على نظام الملفات (أو نظام ملفات افتراضي في الذاكرة)، ولكننا نضيف أيضًا تكاملات مع قواعد بيانات المتجهات.
@@ -1,26 +0,0 @@
---
sidebar_position: 1
---
# تضمين
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
يتولى النموذج المضمن في LlamaIndex إنشاء تمثيلات رقمية للنص. بشكل افتراضي ، ستستخدم LlamaIndex نموذج `text-embedding-ada-002` من OpenAI.
يمكن تعيين ذلك بشكل صريح في كائن `ServiceContext`.
```typescript
import { OpenAIEmbedding, serviceContextFromDefaults } from "llamaindex";
const openaiEmbeds = new OpenAIEmbedding();
const serviceContext = serviceContextFromDefaults({ embedModel: openaiEmbeds });
```
## مرجع الواجهة البرمجية
- [OpenAIEmbedding](../../api/classes/OpenAIEmbedding.md)
- [ServiceContext](../../api/interfaces/ServiceContext.md)
"
@@ -1,26 +0,0 @@
---
sidebar_position: 0
---
# LLM
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
يتولى LLM قراءة النص وتوليد استجابات لغوية طبيعية للاستفسارات. بشكل افتراضي ، يستخدم LlamaIndex.TS `gpt-3.5-turbo`.
يمكن تعيين LLM بشكل صريح في كائن `ServiceContext`.
```typescript
import { OpenAI, serviceContextFromDefaults } from "llamaindex";
const openaiLLM = new OpenAI({ model: "gpt-3.5-turbo", temperature: 0 });
const serviceContext = serviceContextFromDefaults({ llm: openaiLLM });
```
## مرجع الواجهة البرمجية
- [OpenAI](../../api/classes/OpenAI.md)
- [ServiceContext](../../api/interfaces/ServiceContext.md)
"
@@ -1,37 +0,0 @@
---
sidebar_position: 3
---
# NodeParser (محلل العقدة)
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
`NodeParser` في LlamaIndex مسؤول عن تقسيم كائنات `Document` إلى كائنات `Node` أكثر إدارة. عند استدعاء `.fromDocuments()`, يتم استخدام `NodeParser` من `ServiceContext` للقيام بذلك تلقائيًا بالنسبة لك. بدلاً من ذلك ، يمكنك استخدامه لتقسيم المستندات مسبقًا.
```typescript
import { Document, SimpleNodeParser } from "llamaindex";
const nodeParser = new SimpleNodeParser();
const nodes = nodeParser.getNodesFromDocuments([
new Document({ text: "أنا عمري 10 سنوات. جون عمره 20 سنة." }),
]);
```
## TextSplitter (مقسم النص)
سيقوم مقسم النص الأساسي بتقسيم النص إلى جمل. يمكن أيضًا استخدامه كوحدة مستقلة لتقسيم النص الخام.
```typescript
import { SentenceSplitter } from "llamaindex";
const splitter = new SentenceSplitter({ chunkSize: 1 });
const textSplits = splitter.splitText("مرحبًا بالعالم");
```
## مرجع الواجهة البرمجية
- [SimpleNodeParser (محلل العقدة البسيط)](../../api/classes/SimpleNodeParser.md)
- [SentenceSplitter (مقسم الجمل)](../../api/classes/SentenceSplitter.md)
"
@@ -1,45 +0,0 @@
---
sidebar_position: 6
---
# مركب الاستجابة (ResponseSynthesizer)
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
مركب الاستجابة (ResponseSynthesizer) مسؤول عن إرسال الاستعلام والعقد وقوالب الاستفسار إلى LLM لتوليد استجابة. هناك بعض وسائط رئيسية لتوليد استجابة:
- `تحسين`: "إنشاء وتحسين" إجابة عن طريق المرور تتاليًا عبر كل قطعة نص مُسترجعة. يتم إجراء استدعاء LLM منفصل لكل عقدة. جيد للإجابات المفصلة.
- `مضغوط وتحسين` (الافتراضي): "ضغط" الاستفسار أثناء كل استدعاء LLM عن طريق حشو أكبر عدد ممكن من قطع النص التي يمكن أن تتناسب مع حجم الاستفسار الأقصى. إذا كان هناك الكثير من القطع لتعبئتها في استفسار واحد، "إنشاء وتحسين" إجابة عن طريق المرور بعدة استفسارات مضغوطة. نفس العملية كـ `تحسين`، ولكن يجب أن تؤدي إلى مزيد من استدعاءات LLM أقل.
- `ملخص الشجرة`: بناء شجرة بشكل متكرر بناءً على مجموعة من قطع النص والاستعلام، وإرجاع العقدة الجذرية كاستجابة. جيد لأغراض التلخيص.
- `منشئ الاستجابة البسيط`: تطبيق الاستعلام على كل قطعة نص وتجميع الاستجابات في مصفوفة. يعيد سلسلة متصلة من جميع الاستجابات. جيد عندما تحتاج إلى تشغيل نفس الاستعلام بشكل منفصل على كل قطعة نص.
```typescript
import { NodeWithScore, ResponseSynthesizer, TextNode } from "llamaindex";
const responseSynthesizer = new ResponseSynthesizer();
const nodesWithScore: NodeWithScore[] = [
{
node: new TextNode({ text: "أنا عمري 10 سنوات." }),
score: 1,
},
{
node: new TextNode({ text: "جون عمره 20 سنة." }),
score: 0.5,
},
];
const response = await responseSynthesizer.synthesize(
"ما هو عمري؟",
nodesWithScore,
);
console.log(response.response);
```
## مرجع الواجهة البرمجية
- [مركب الاستجابة (ResponseSynthesizer)](../../api/classes/ResponseSynthesizer.md)
- [تحسين (Refine)](../../api/classes/Refine.md)
- [مضغوط وتحسين (CompactAndRefine)](../../api/classes/CompactAndRefine.md)
- [ملخص الشجرة (TreeSummarize)](../../api/classes/TreeSummarize.md)
- [منشئ الاستجابة البسيط (SimpleResponseBuilder)](../../api/classes/SimpleResponseBuilder.md)
@@ -1,23 +0,0 @@
---
sidebar_position: 5
---
# الباحث (Retriever)
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
الباحث في LlamaIndex هو ما يُستخدم لاسترداد العقد (`Node`) من فهرس باستخدام سلسلة الاستعلام. سيقوم الباحث `VectorIndexRetriever` بجلب أعلى k عقد مشابهة. بينما سيقوم الباحث `SummaryIndexRetriever` بجلب جميع العقد بغض النظر عن الاستعلام.
```typescript
const retriever = vector_index.asRetriever();
retriever.similarityTopK = 3;
// جلب العقد!
const nodesWithScore = await retriever.retrieve("سلسلة الاستعلام");
```
## مرجع الواجهة البرمجية (API Reference)
- [SummaryIndexRetriever](../../api/classes/SummaryIndexRetriever.md)
- [SummaryIndexLLMRetriever](../../api/classes/SummaryIndexLLMRetriever.md)
- [VectorIndexRetriever](../../api/classes/VectorIndexRetriever.md)
@@ -1,30 +0,0 @@
---
sidebar_position: 7
---
# التخزين
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
يعمل التخزين في LlamaIndex.TS تلقائيًا بمجرد تكوين كائن `StorageContext`. قم بتكوين `persistDir` وربطه بفهرس.
في الوقت الحالي ، يتم دعم حفظ وتحميل البيانات من القرص فقط ، مع وجود تكاملات مستقبلية مخططة!
```typescript
import { Document, VectorStoreIndex, storageContextFromDefaults } from "./src";
const storageContext = await storageContextFromDefaults({
persistDir: "./storage",
});
const document = new Document({ text: "نص اختبار" });
const index = await VectorStoreIndex.fromDocuments([document], {
storageContext,
});
```
## مرجع الواجهة البرمجية
- [StorageContext](../../api/interfaces/StorageContext.md)
"
@@ -1,58 +0,0 @@
---
sidebar_position: 2
---
# دليل البداية
`تمت ترجمة هذه الوثيقة تلقائيًا وقد تحتوي على أخطاء. لا تتردد في فتح طلب سحب لاقتراح تغييرات.`
بمجرد [تثبيت LlamaIndex.TS باستخدام NPM](installation) وإعداد مفتاح OpenAI الخاص بك، أنت الآن جاهز لبدء تطبيقك الأول:
في مجلد جديد:
```bash npm2yarn
npm install typescript
npm install @types/node
npx tsc --init # إذا لزم الأمر
```
أنشئ ملف `example.ts`. سيقوم هذا الكود بتحميل بعض البيانات المثالية، وإنشاء وثيقة، وفهرسة الوثيقة (مما ينشئ تضمينات باستخدام OpenAI)، ثم إنشاء محرك الاستعلام للإجابة على الأسئلة حول البيانات.
```ts
// example.ts
import fs from "fs/promises";
import { Document, VectorStoreIndex } from "llamaindex";
async function main() {
// تحميل المقالة من abramov.txt في Node
const essay = await fs.readFile(
"node_modules/llamaindex/examples/abramov.txt",
"utf-8",
);
// إنشاء كائن Document بواسطة المقالة
const document = new Document({ text: essay });
// تقسيم النص وإنشاء التضمينات. تخزينها في VectorStoreIndex
const index = await VectorStoreIndex.fromDocuments([document]);
// استعلام الفهرس
const queryEngine = index.asQueryEngine();
const response = await queryEngine.query("ماذا فعل الكاتب في الكلية؟");
// إخراج الاستجابة
console.log(response.toString());
}
main();
```
ثم يمكنك تشغيله باستخدام
```bash
npx ts-node example.ts
```
هل أنت مستعد للمزيد من التعلم؟ تفضل بزيارة منصة NextJS الخاصة بنا على https://llama-playground.vercel.app/. يمكنك العثور على المصدر على https://github.com/run-llama/ts-playground
"
Binary file not shown.

Before

Width:  |  Height:  |  Size: 27 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 49 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 36 KiB

@@ -1 +0,0 @@
../../../../docs/api
@@ -1,86 +0,0 @@
---
sidebar_position: 3
---
# Високо ниво на концепции
`Тази документация е преведена автоматично и може да съдържа грешки. Не се колебайте да отворите Pull Request, за да предложите промени.`
LlamaIndex.TS ви помага да създавате приложения, базирани на LLM (например Q&A, чатбот) върху персонализирани данни.
В това ръководство за високо ниво на концепции ще научите:
- как LLM може да отговори на въпроси, използвайки вашите собствени данни.
- ключови концепции и модули в LlamaIndex.TS за създаване на ваша собствена заявка.
## Отговаряне на въпроси върху вашите данни
LlamaIndex използва двустепенен метод при използване на LLM с вашите данни:
1. **стъпка за индексиране**: подготовка на база от знания и
2. **стъпка за заявка**: извличане на съответния контекст от знанията, за да помогне на LLM да отговори на въпрос
![](./_static/concepts/rag.jpg)
Този процес е известен също като Retrieval Augmented Generation (RAG).
LlamaIndex.TS предоставя основния инструментариум, който прави и двете стъпки изключително лесни.
Нека изследваме всяка стъпка подробно.
### Стъпка на индексиране
LlamaIndex.TS ви помага да подготвите базата от знания с помощта на набор от конектори за данни и индекси.
![](./_static/concepts/indexing.jpg)
[**Data Loaders**](./modules/high_level/data_loader.md):
Конектор за данни (т.е. `Reader`) поема данни от различни източници на данни и формати на данни и ги превръща в просто представяне на `Document` (текст и прости метаданни).
[**Documents / Nodes**](./modules/high_level/documents_and_nodes.md): `Document` е общ контейнер за всякакъв вид данни - например PDF, изход от API или извлечени данни от база данни. `Node` е атомарната единица от данни в LlamaIndex и представлява "част" от източниковия `Document`. Това е богато представяне, което включва метаданни и връзки (към други възли), за да позволи точни и изразителни операции за извличане.
[**Data Indexes**](./modules/high_level/data_index.md):
След като сте поели данните си, LlamaIndex ви помага да индексирате данните във формат, който е лесен за извличане.
Под капака, LlamaIndex анализира суровите документи в промеждинни представяния, изчислява векторни вложения и съхранява данните в паметта или на диска.
"
### Стъпка за заявка
В стъпката за заявка, конвейерът за заявки извлича най-съответния контекст, даден на потребителска заявка,
и го предава на LLM (заедно със заявката), за да синтезира отговор.
Това дава на LLM актуални познания, които не са в неговите оригинални обучаващи данни,
(също така намалява халюцинацията).
Основното предизвикателство в стъпката за заявка е извличането, организирането и резонирането върху (потенциално много) бази от знания.
LlamaIndex предоставя модули, които могат да се комбинират и помагат за създаването и интегрирането на RAG конвейери за Q&A (заявки), чатбот (чат двигател) или като част от агент.
Тези строителни блокове могат да бъдат персонализирани, за да отразяват предпочитанията за ранжиране, както и да бъдат комбинирани, за да резонират върху множество бази от знания по структуриран начин.
![](./_static/concepts/querying.jpg)
#### Строителни блокове
[**Извличатели**](./modules/low_level/retriever.md):
Извличател дефинира как да се извлича ефективно съответния контекст от база от знания (т.е. индекс), когато се предостави заявка.
Конкретната логика за извличане се различава за различни индекси, като най-популярното е плътно извличане срещу векторен индекс.
[**Синтезатори на отговори**](./modules/low_level/response_synthesizer.md):
Синтезаторът на отговор генерира отговор от LLM, използвайки потребителска заявка и даден набор от извлечени текстови части.
"
#### Конвейери
[**Заявки**](./modules/high_level/query_engine.md):
Заявката е цялостен конвейер, който ви позволява да задавате въпроси относно вашите данни.
Тя приема заявка на естествен език и връща отговор, заедно с извлечения контекст, предаден на LLM.
[**Чат двигатели**](./modules/high_level/chat_engine.md):
Чат двигателът е цялостен конвейер за провеждане на разговор с вашите данни
(множество въпроси и отговори вместо единичен въпрос и отговор).
"
@@ -1,57 +0,0 @@
---
sidebar_position: 4
---
# Примери от начало до край
`Тази документация е преведена автоматично и може да съдържа грешки. Не се колебайте да отворите Pull Request, за да предложите промени.`
Включени са няколко примера от начало до край, използвайки LlamaIndex.TS в хранилището
Разгледайте примерите по-долу или ги опитайте и завършете за минути с интерактивни уроци на Github Codespace, предоставени от Dev-Docs [тук](https://codespaces.new/team-dev-docs/lits-dev-docs-playground?devcontainer_path=.devcontainer%2Fjavascript_ltsquickstart%2Fdevcontainer.json):
## [Чат двигател (Chat Engine)](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/chatEngine.ts)
Прочетете файл и обсъждайте го с LLM.
## [Векторен индекс](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/vectorIndex.ts)
Създайте векторен индекс и го запитайте. Векторният индекс ще използва вграждания, за да извлече най-релевантните k върха. По подразбиране, k е 2.
"
## [Summary Index](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/summaryIndex.ts)
Създайте списъчен индекс и го заявете. Този пример също използва `LLMRetriever`, който използва LLM, за да избере най-добрите възли за използване при генериране на отговор.
"
## [Запазване / Зареждане на индекс](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/storageContext.ts)
Създайте и заредете векторен индекс. Запазването на диска в LlamaIndex.TS става автоматично, веднага след като е създаден обект за контекст на съхранение.
## [Персонализиран векторен индекс](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/vectorIndexCustomize.ts)
Създайте векторен индекс и го заявете, като конфигурирате `LLM`, `ServiceContext` и `similarity_top_k`.
"
## [OpenAI LLM](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/openai.ts)
Създайте OpenAI LLM и го използвайте директно за чат.
## [Llama2 DeuceLLM](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/llamadeuce.ts)
Създайте Llama-2 LLM и го използвайте директно за чат.
## [SubQuestionQueryEngine](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/subquestion.ts)
Използва `SubQuestionQueryEngine`, който разбива сложни заявки на множество въпроси и след това агрегира отговорите на всички под-въпроси.
"
## [Модули с ниско ниво](https://github.com/run-llama/LlamaIndexTS/blob/main/examples/lowlevel.ts)
Този пример използва няколко компонента с ниско ниво, които премахват нуждата от реален двигател за заявки. Тези компоненти могат да се използват навсякъде, във всяко приложение или да бъдат персонализирани и подкласирани, за да отговарят на вашите нужди.
"

Some files were not shown because too many files have changed in this diff Show More