135207caa3
fix initialize
2024-01-02 15:02:31 +08:00
d7ed9806ca
Merge remote-tracking branch 'origin/main' into feat_add_openai_function_agent
2023-12-30 23:39:12 +08:00
4287e72129
format agent_scratchpad and error
2023-12-30 23:38:11 +08:00
f89cec5ef9
Remove unused schema types ( #473 )
2023-12-30 06:27:44 -08:00
791e680123
Remove duplicated and unused LLMResult type from schema ( #472 )
...
It exists in the llms package already
2023-12-30 06:22:35 -08:00
536f16c12a
textsplitter: handle singular markdown tokens in markdown_splitter ( #467 )
...
The markdown splitter was not correctly handling singular markdown tokens
like Hr or Fence. These tokens do not have a corresponding close type,
which was causing issues in the indexOfCloseTag function.
To fix this, a check has been added to return the start index if the
closeType is nil, indicating a singular token. This prevents the function
from incorrectly trying to find a close tag for these tokens and running
past the end of the document.
2023-12-30 03:57:23 -08:00
eeadc49c70
agents: fixup comment
2023-12-29 13:28:17 -08:00
2e81b2bdbd
vectorstores: Add azureaisearch ( #462 )
...
* add azure ai search as vectorstore
2023-12-29 21:25:24 +00:00
85e33db166
Run go.mod tidy to make IDE happy ( #470 )
2023-12-29 13:15:43 -08:00
fc11926d0c
vectorstores: Add opensearch ( #464 )
...
* vectorstores: Add opensearch
---------
Co-authored-by: Jay Lalakiya <63226109+jaylalakiya@users.noreply.github.com >
Co-authored-by: Travis Cline <travis.cline@gmail.com >
2023-12-29 12:17:17 -08:00
130eec9f4a
Merge pull request #469 from tmc/fixup-jinja2
...
templates: Fix up gonja/jinja2 handling
2023-12-29 12:14:28 -08:00
214f551be8
templates: Fix up gonja/jinja2 handling
2023-12-29 12:11:13 -08:00
1c7cb8de41
Merge pull request #468 from tmc/langmodel
...
Refactor LanguageModel interface away
2023-12-29 11:16:30 -08:00
435467ab33
Resolve lint complaints and gofumpt
2023-12-29 09:56:26 -08:00
2ed43f054f
Remove GeneratePrompt methods as they're no longer needed
2023-12-29 09:50:06 -08:00
ab14227446
Remove mentions of the LanguageModel interface
2023-12-29 09:44:57 -08:00
93cea28bfe
Refactor usage of LanguageModel out
...
Replace it by LLM and adjust code and tests accordingly
re #465
2023-12-29 09:35:52 -08:00
eb58836512
Skip tests that are currently failing ( #415 ) ( #466 )
2023-12-28 21:02:13 -08:00
693bd1eb59
pgvector: return error directly
2023-12-28 17:28:00 -08:00
5c345a14a7
vectorstores: Add ids to the return when adding documents in any vectorstore ( #448 )
...
* Add ids to the return when adding documents in any vectorstore
* fixes lint checks
* examples: Point vectorstore examples to branch
---------
Co-authored-by: Travis Cline <travis.cline@gmail.com >
2023-12-28 17:11:54 -08:00
310afd2c66
promps: move prompts to embedded text files ( #451 )
2023-12-28 16:55:43 -08:00
a39989164e
examples: update to v0.1.2
2023-12-28 16:24:36 -08:00
d8b25bd69e
examples: Update to pre-release tag
2023-12-28 16:20:04 -08:00
59f2be62ed
callbacks: Add other handlers to CombingHandler
2023-12-28 16:18:21 -08:00
b0fbdd0023
chore: Update go.mod, go.sum
2023-12-28 16:13:48 -08:00
923373ff0c
Feat: support combine multi callbacks ( #446 )
2023-12-28 15:26:42 -08:00
affaa87bdd
memory: add ConversationWindowBuffer ( #411 )
...
Port the ConversationBufferWindowMemory class from langchain python in langchaingo
Signed-off-by: Abirdcfly <fp544037857@gmail.com >
2023-12-28 15:24:35 -08:00
0f24bf1d9f
Feat: support render prompt template with jinjia2 ( #450 )
2023-12-28 15:23:51 -08:00
1ee33af9af
vectorstores: fix weaviate not return score from SimilaritySearch ( #454 )
...
Signed-off-by: Abirdcfly <fp544037857@gmail.com >
2023-12-28 15:22:51 -08:00
534f75725e
Feat: callbacks.Handler support handle error ( #457 )
...
Feat: support HandleLLMError for llms.LLM
2023-12-28 15:22:05 -08:00
74527d34b3
add StopReason field in Generation struct. ( #458 )
2023-12-28 15:18:52 -08:00
284a853cc9
support callback handler to llm chain ( #461 )
...
* support callback handler to llm chain
* fix golint
---------
Co-authored-by: lvzhong <lvzhong@bytedance.com >
2023-12-28 15:17:37 -08:00
580395f9d4
fix: avoid panic when call openai.NewChat() and openai.New() ( #460 )
...
avoid panic when opts is nil
Co-authored-by: lvzhong <lvzhong@bytedance.com >
2023-12-28 15:17:05 -08:00
377594f85a
format
2023-12-26 18:04:57 +08:00
768d4dcd25
format
2023-12-26 18:01:29 +08:00
644afc41c8
format
2023-12-26 17:55:53 +08:00
fbc4ed6c9e
format
2023-12-26 17:54:01 +08:00
9dd6da65e6
add openai functions agent
2023-12-26 17:29:14 +08:00
99bb50d3c7
Feat: use chains callback as streaming func ( #447 )
2023-12-24 21:05:42 -08:00
e98eb1703a
vectorstores: fix chroma not return score from SimilaritySearch ( #449 )
...
Signed-off-by: Abirdcfly <fp544037857@gmail.com >
2023-12-24 18:17:23 -08:00
351b8b52b1
embeddings: Fix BatchTexts function ( #453 )
...
* Fix BatchTexts function in embeddings
* Add test cases for util func added
2023-12-23 13:47:11 -08:00
213b9dca74
examples: Update langchaingo to v0.1.1 ( #445 )
2023-12-20 21:40:03 +00:00
560f27812e
deps: Update x/crypto ( #444 )
2023-12-20 20:04:19 +00:00
55f772c21a
Docs: fix comment typo ( #442 )
...
* Docs: fix comment typo
* docs: a llm -> an LLM
---------
Co-authored-by: Travis Cline <travis.cline@gmail.com >
2023-12-20 19:57:37 +00:00
5eb184f48d
feat: read OPENAI_API_BASE env to compatible with langchain ( #437 )
2023-12-20 11:56:25 -08:00
4825e45403
feat: use WithCallback to set openai callback option ( #438 )
2023-12-20 11:56:16 -08:00
a5e1d6017c
fix: remove suffix slash from openai base url ( #436 )
2023-12-20 11:52:42 -08:00
dcae4f66a6
pgvector: Fix DropTable Function ( #441 )
...
drop embedding table before collection table
Co-authored-by: Mehul <mehul@gndctl.com >
2023-12-20 11:50:24 -08:00
6ad961ac14
pgvector: support postgres schema ( #439 )
2023-12-20 11:34:16 -08:00
eb17026117
test: fix api chain test error ( #414 ) ( #434 )
2023-12-19 13:48:48 -08:00
lujingxuan