According to the docs there is more than ChatOpenAi model only --> ChatAnthropic etc...
What was removed:
"Note: Currently, the only chat-based model we support is ChatOpenAI (with gpt-4 and gpt-3.5-turbo), but anticipate adding more in the future."
* wip figma file loader
* add figma env to .env.sample
* update FigmaFile ts
* fix format
* add figma to entry-points
* add figma doc and example
* include figma files in .gitignore
* add figma to tsconfig.json
* little refactor
* rename md to mdx
* add FIGMA_ACCESS_TOKEN to .env.example
* update figma example and int test
* Update Figma loader args, test case, examples, and docs
---------
Co-authored-by: jacoblee93 <jacoblee93@gmail.com>
* Google Vertex AI Chat model
* Simplify Google Vertex AI chat class, use more LangChain conventions
* Adds chat_models/googlevertexai to optional dependencies
* Fix example, fix build
* Clarify docs
* Formatting
* Docs styling
---------
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
* adding initial API chain code
* lint fix
* add docs and example
* Update file structure, move around parameters and TS types
* Slightly shorten APIChain example for consistency
---------
Co-authored-by: Larry Anderson <larryboymi@hotmail.com>
* installed @upstash/redis
* updating .env.example with upstash redis vars
* feat: created RedisUpstashChatMessageHistory based on RedisChatMessageHistory
* test: adding tests based on redis tests
* docs: adding docs with examples for upstash redis
* adding @upstash/redis as examples dependency
* adding stores/message/redis_upstash to langchain .gitignore
* adding stores/message/redis_upstash to langchain package.json files, peerDependenciesMeta and exports
* adding stores/message/redis_upstash to langchain tsconfig.json
* adding stores/message/redis_upstash to create-entrypoint.js
* adding @upstash/redis to examples yarn.lock
* moving @upstash/redis peerDependenciesMeta to correct order
* updating main yarn.lock with @upstash/redis
* lint: adding missing semicolon to import
* adding eslint-disable lines to redis_upstash int test file
* moving typedocOptions redis_upstash to the correct place
* docs: improvements to redis_upstash docs
* Change Upstash Redis naming, update docs
* Fix Upstash Redis constructor config types
---------
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
* Added google custom search as a tool
* Google Custom Search API tool docs, test, small parameter change
* Make Google custom search tool read from environment variables if possible, change param names
* Fix typo
---------
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
* Fix type definition of an array
* Impement GoogleVertexAIEmbeddings
* GoogleVertexAIEmbeddings documentation and examples
* Create entrypoints, minor renaming and docs update
* Make response nullable for more graceful failures
* Format
---------
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
* improvement: add the option to add headers to chunks so to help LLMs and vector stores better understand linked chunks
* docs: update text splitters docs to reference `chunkHeader`, `chunkOverlapHeader`, and `showChunkOverlapHeader`
* fix: formatting
* Move contextual headers for each chunk out of the TextSplitter constructor and into individual methods
* Fix typo
* Adds example result
---------
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
* Initial work implementing access to the Google Vertex AI API and the LLM models available through it.
* Refactor into a base class
* Prettier
* Add chat version of Google Vertex AI LLM.
* Add Google Vertex AI classes
* Example for Google Vertex AI LLM
* Add Google Vertex AI LLM
* Documentation
* Google Vertex AI Chat example
* Fix capitalization typo
* Make Google's SDK a peer dependency, move out of main entrypoint
* Add convenience method for type equality.
* Extensive refactoring to make the Google Vertex AI Chat implementation compliant
* Legacy prettier cleanup
* Prettier cleanup of refactored code
* Refactor to move connection and common types into separate modules.
* Refactor to move connection and common types into separate modules.
* Refactor to move connection and common types into separate modules.
* Change maxTokens to maxOutputTokens.
Change configuration for the connection object.
Prettier
* ChatGoogleVertexAi entry point
* GoogleVertexAi tests
* GoogleVertexAi example refactoring
* Example for ChatGoogleVertexAi
Fix and test for determining context and examples.
* Documentation for Google VertexAI text and chat models.
* Refactor some of ChatGoogleVertexAi to break out some components to be better unit tested.
Add unit tests.
Fix bugs with context and example generation.
Formatting.
* Descope PR to just GoogleVertexAI LLM, normalize class names
* Small fixes and renames, increase default max token output size
* Fix typo in documentation import from examples. I think.
* Fix docs
---------
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
* ignore like .gitignore in GithubLoader
* set ignore as optional depenency
* Make ignore an optional import for GithubRepoLoader, refactor shouldIgnore method
* Formatting
* Remove conditional import, remove GitHubRepoLoader from index.ts file
---------
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
* add faiss
* add pickle support
* replace pickle.js with pickleparser package
* yarn install
* update pickleparser
* fix code review
* fix metadata in loadFromPython
* add docs
* add test cases
* port form python
* Save mapping into JSON file.
* upgrader pickleparser
* upgrade pickleparser
* make loadFromPython work
* upgrade pickleparser
* upgrade pickleparser and use reduce function
* update demo and docs
* fix doc build
* update docs
* add more ut and fix import of pickleparser
* update docs
* add int test for loadFromPython
* add more int test for loadFromPython
* fix merge error
* upgrade pickleparser
* upgrade pickleparser and fix code review
* yarn install
* port #1142
* use chained register
* fix lint
* fix format
* Update examples, update imports, remove extraneous deps from merge
* Undo change to imports
---------
Co-authored-by: Nuno Campos <nuno@boringbits.io>
* self-query with meriyah
* removed builtin translators so end-user needs to specify their own translator, but a basic translator that can be used with pinecone and chroma is included and can be imported
* fixed class name typo
* moved meriyah to main dependency so expression parser can work in test-exports-*
* added back self_query to entrypoints
* moved meriyah to dev/peer dep, fixed unused parser types, minor fixes
* renaming expression type to reflect meriyah better
* removed unused lint disable on self_query/base.ts
* Use a rewritten tiktoken for token counting
* Fix lint, add test
* Fix type import, typo
* Remove @dqbd/tiktoken as "weak" dependency
* Move JS implementation of tiktoken into a separate package
* Upgrade to js-tiktoken@1.0.2
* Replace all occurrences of @dqbd/tiktoken
* Avoid bundling ranks, fix test with CRA
* Use AsyncCaller, cache promises
* Remove WASM configuration changes
* Upgrade to 1.0.6 for CRA fixes, mark js-tiktoken/lite as an external dependency
* Remove next.config.js
* init entity_memory
* init tests
* added test
* fixed test
* updated prompts usage
* fixed import
* added test for pre loaded messages
* updated import
* Use object without prototype for safer exists check
* move entity store to its own file, make it async
* Add example, not giving great results for now
* Prompt updates to support reflexive pronouns, keep entity summaries unchanged, support chat models, add docs
* Remove merge artifact
* Fix test
* Format fix
---------
Co-authored-by: Nuno Campos <nuno@boringbits.io>
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
* feat: add Redis vectorstore with tests
* fix linting and formatting problems
* docs: add redis vector store
* fix: remove export from deprecated vectorstores index
* docs: add node.js-only compatibility tip to redis vectorstore
* Update types, add more optional config, move examples out of md file
* Use more recent chain in example
* Update tests
* Mark entrypoint as optional dep
* Fix import
* Fix build error
---------
Co-authored-by: Nuno Campos <nuno@boringbits.io>
* Merge post upstream sync (#1)
* Added RedisMemory with tests and docs
* fixed Redis test file name
* TODOs for quick refactor
* updated memory to accept a client
* Added TODOS
* ongoing testing
* Updated tests
* Updated tests for memory return option
* finalized tests + updated docs
* Adding docs
* Readded init and cleaned up func
* fixed test typing
* redo yarn lock
* remove yarn.lock
* updated yarn lock and namespaced redis
* fix merge conflict
* updated BaseChatMemoryInput
* Updated with lint fixes
* Fixed docs to match memory instantiation
* yarn format docs
* Merging fixes to address ForkPR comments (#2)
* updating for pr
* Removed redis_memory in favor of chat memory
* Fixed tests and updated docs
* Bump docs
* lint results
* fixes from lint and format
---------
Co-authored-by: Chris Toomey <ctoomey@fb.com>
* Update RedisChatMessageHistory class to initialize a client internally
* Update Redis chat message history docs to reflect the fact that Redis is a peer dependency, allow direct passing of Redis client
* Patch typing issues with passing node-redis client directly into a RedisChatMessageHistory instance
---------
Co-authored-by: Chris Toomey <ctoomey@fb.com>
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
* Implement cancellation and timeout for all LLMs, allow passing LLM call options via LLMChain (like was already possible for stop)
* Update example
* Add declared ParsedCallOptions type for BaseLanguageModels, add signal support for chat models, add tests
* Update docs for chat models
* Update llm and chat examples to remove `run` func
* Add more examples for LLMChain
* Reorganise agent docs, add Additional Functionality doc for Agents
* Add toc in llm chain docs
* Format
---------
Co-authored-by: Jacob Lee <jacoblee93@gmail.com>
jacoblee93