github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-27 22:37:46 +00:00
Code Issues Packages Projects Releases Wiki Activity
11,422 Commits 996 Branches 983 Tags
langchain-mongodb==0.2.0.dev1
Commit Graph

5699 Commits

Author SHA1 Message Date
ZhangShenao
4255a30f20 Improvement[Community] Improve api doc for SingleFileFacebookMessengerChatLoader (#25536) 
Delete redundant args in api doc
 2024-08-19 09:00:21 -04:00
Bagatur
49dea06af1 docs: fix Agent deprecation msg (#25464) 2024-08-18 19:15:52 +00:00
Hassan El Mghari
937b3904eb together[patch]: update base url (#25524) 
Updated the Together base URL from `.ai` to `.xyz` since some customers
have reported problems with `.ai`.
 2024-08-18 10:48:30 -07:00
Isaac Francisco
a2e90a5a43 add embeddings integration tests (#25508) 2024-08-16 13:20:37 -07:00
Bagatur
a06818a654 openai[patch]: update core dep (#25502) 2024-08-16 18:30:17 +00:00
Bagatur
df98552b6f core[patch]: Release 0.2.33 (#25498) 2024-08-16 11:18:54 -07:00
ccurme
b83f1eb0d5 core, partners: implement standard tracing params for LLMs (#25410) 2024-08-16 13:18:09 -04:00
Bagatur
9f0c76bf89 openai[patch]: Release 0.1.22 (#25496) 2024-08-16 16:53:04 +00:00
ccurme
01ecd0acba openai[patch]: fix json mode for Azure (#25488) 
https://github.com/langchain-ai/langchain/issues/25479
https://github.com/langchain-ai/langchain/issues/25485

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
 2024-08-16 09:50:50 -07:00
Bagatur
253ceca76a docs: fix mimetype parser docstring (#25463) 2024-08-15 16:16:52 -07:00
Eugene Yurtsev
e18511bb22 core[minor], anthropic[patch]: Upgrade @root_validator usage to be consistent with pydantic 2 (#25457) 
anthropic: Upgrade `@root_validator` usage to be consistent with
pydantic 2
core: support looking up multiple keys from env in from_env factory
 2024-08-15 20:09:34 +00:00
Eugene Yurtsev
34da8be60b pinecone[patch]: Upgrade @root_validators to be consistent with pydantic 2 (#25453) 
Upgrade root validators for pydantic 2 migration
 2024-08-15 19:45:14 +00:00
Eugene Yurtsev
b297af5482 voyageai[patch]: Upgrade root validators for pydantic 2 (#25455) 
Update @root_validators to be consistent with pydantic 2 semantics
 2024-08-15 15:30:41 -04:00
Eugene Yurtsev
4cdaca67dc ai21[patch]: Upgrade @root_validators for pydantic 2 migration (#25454) 
Upgrade @root_validators usage to match pydantic 2 semantics
 2024-08-15 14:54:08 -04:00
Eugene Yurtsev
d72a08a60d groq[patch]: Update root validators for pydantic 2 migration (#25402) 2024-08-15 18:46:52 +00:00
Isaac Francisco
5150ec3a04 [experimental]: minor fix to open assistants code (#24682) 2024-08-15 17:50:57 +00:00
Bagatur
2b4fbcb4b4 docs: format oai embeddings docstring (#25448) 2024-08-15 16:57:54 +00:00
Eugene Yurtsev
eb3870e9d8 fireworks[patch]: Upgrade @root_validators to be pydantic 2 compliant (#25443) 
Update @root_validators to be pydantic 2 compliant
 2024-08-15 16:56:48 +00:00
William FH
75ae585deb Merge support for group manager (#25360) 2024-08-15 09:56:31 -07:00
Eugene Yurtsev
2ef9d12372 mistralai[patch]: Update more @root_validators for pydantic 2 compatibility (#25446) 
Update @root_validators in mistralai integration for pydantic 2 compatibility
 2024-08-15 12:44:42 -04:00
Eugene Yurtsev
831708beb7 together[patch]: Update @root_validator for pydantic 2 compatibility (#25423) 
This PR updates usage of @root_validator to be compatible with pydantic 2.
 2024-08-15 11:27:42 -04:00
Eugene Yurtsev
a114255b82 ai21[patch]: Update @root_validators for pydantic2 migration (#25401) 
Update @root_validators for pydantic 2 migration.
 2024-08-15 11:26:44 -04:00
Eugene Yurtsev
6f68c8d6ab mistralai[patch]: Update root validator for compatibility with pydantic 2 (#25403) 2024-08-15 11:26:24 -04:00
ccurme
8afbab4cf6 langchain[patch]: deprecate various chains (#25310) 
- [x] NatbotChain: move to community, deprecate langchain version.
Update to use `prompt | llm | output_parser` instead of LLMChain.
- [x] LLMMathChain: deprecate + add langgraph replacement example to API
ref
- [x] HypotheticalDocumentEmbedder (retriever): update to use `prompt |
llm | output_parser` instead of LLMChain
- [x] FlareChain: update to use `prompt | llm | output_parser` instead
of LLMChain
- [x] ConstitutionalChain: deprecate + add langgraph replacement example
to API ref
- [x] LLMChainExtractor (document compressor): update to use `prompt |
llm | output_parser` instead of LLMChain
- [x] LLMChainFilter (document compressor): update to use `prompt | llm
| output_parser` instead of LLMChain
- [x] RePhraseQueryRetriever (retriever): update to use `prompt | llm |
output_parser` instead of LLMChain
 2024-08-15 10:49:26 -04:00
Luke
66e30efa61 experimental: Fix divide by 0 error (#25439) 
Within the semantic chunker, when calling `_threshold_from_clusters`
there is the possibility for a divide by 0 error if the
`number_of_chunks` is equal to the length of `distances`.

Fix simply implements a check if these values match to prevent the error
and enable chunking to continue.
 2024-08-15 14:46:30 +00:00
ccurme
ba167dc158 community[patch]: update connection string in azure cosmos integration test (#25438) 2024-08-15 14:07:54 +00:00
Isaac Francisco
966b408634 [docs]: doc loader changes (#25417) 2024-08-14 19:46:33 -07:00
ccurme
bd261456f6 langchain: bump core to 0.2.32 (#25421) 2024-08-15 00:00:42 +00:00
Bagatur
ec8ffc8f40 core[patch]: Release 0.2.32 (#25420) 2024-08-14 15:56:56 -07:00
Bagatur
2494cecabf core[patch]: tool import fix (#25419) 2024-08-14 22:54:13 +00:00
ccurme
df632b8cde langchain: bump min core version (#25418) 2024-08-14 22:51:35 +00:00
ccurme
1050e890c6 langchain: release 0.2.14 (#25416) 
Fixes https://github.com/langchain-ai/langchain/issues/25413
 2024-08-14 22:29:39 +00:00
gbaian10
0a99935794 docs: remove the extra period in docstring (#25414) 
Remove the period after the hyperlink in the docstring of
BaseChatOpenAI.with_structured_output.

I have repeatedly copied the extra period at the end of the hyperlink,
which results in a "Page not found" page when pasted into the browser.
 2024-08-14 18:07:15 -04:00
Werner van der Merwe
1d3f7231b8 fix: typo where github should be gitlab (#25397) 
**PR title**: "GitLabToolkit: fix typo"
    - **Description:** fix typo where GitHub should have been GitLab
    - **Dependencies:** None
 2024-08-14 18:36:25 +00:00
Bagatur
a58d4ba340 core[patch]: Release 0.2.31 (#25388) 2024-08-14 11:26:49 -07:00
Bagatur
414154fa59 experimental[patch]: refactor rl chain structure (#25398) 
can't have a class and function with same name but different
capitalization in same file for api reference building
 2024-08-14 17:09:43 +00:00
Bagatur
63c483ea01 standard-tests: import fix (#25395) 2024-08-14 09:13:56 -07:00
Bagatur
eec7bb4f51 anthropic[patch]: Release 0.1.23 (#25394) 2024-08-14 09:03:39 -07:00
Eugene Yurtsev
f4196f1fb8 ollama[patch]: Update extra in ollama package (#25383) 
Backwards compatible change that converts pydantic extras to literals
which is consistent with pydantic 2 usage.
 2024-08-14 10:30:01 -04:00
Chengyu Yan
d0ad713937 core: fix issue#24660, slove error messages about ValueError when use model with history (#25183) 
- **Description:**
This PR will slove error messages about `ValueError` when use model with
history.
Detail in #24660.
#22933 causes that
`langchain_core.runnables.history.RunnableWithMessageHistory._get_output_messages`
miss type check of `output_val` if `output_val` is `False`. After
running `RunnableWithMessageHistory._is_not_async`, `output` is `False`.

249945a572/libs/core/langchain_core/runnables/history.py (L323-L334)

15a36dd0a2/libs/core/langchain_core/runnables/history.py (L461-L471)
~~I suggest that `_get_output_messages` return empty list when
`output_val == False`.~~

- **Issue**:
  - #24660

- **Dependencies:**: No Change.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
 2024-08-14 14:26:22 +00:00
Bagatur
493e474063 docs: udpated api reference (#25172) 
- Move the API reference into the vercel build
- Update api reference organization and styling
 2024-08-14 07:00:17 -07:00
Eugene Yurtsev
5f5e8c9a60 huggingface[patch], pinecone[patch], fireworks[patch], mistralai[patch], voyageai[patch], togetherai[path]: convert Pydantic extras to literals (#25384) 
Backwards compatible change that converts pydantic extras to literals
which is consistent with pydantic 2 usage.

- fireworks
- voyage ai
- mistralai
- mistral ai
- together ai
- huggigng face
- pinecone
 2024-08-14 09:55:30 -04:00
Eugene Yurtsev
d00176e523 openai[patch]: Update extra to match pydantic 2 (#25382) 
Backwards compatible change that converts pydantic extras to literals
which is consistent with pydantic 2 usage.
 2024-08-14 09:55:18 -04:00
Eugene Yurtsev
dc51cc5690 core[minor]: Prevent PydanticOutputParser from encoding schema as ASCII (#25386) 
This allows users to provide parameter descriptions in the pydantic
models in other languages.

Continuing this PR: https://github.com/langchain-ai/langchain/pull/24809
 2024-08-14 13:54:31 +00:00
ccurme
27690506d0 multiple: update removal targets (#25361) 2024-08-14 09:50:39 -04:00
Harrison Chase
967b6f21f6 docs: improve document loaders index (#25365) 
Co-authored-by: Erick Friis <erick@langchain.dev>
 2024-08-14 01:48:48 +00:00
Isaac Francisco
f4ffd692a3 [docs]: standardize doc loader doc strings (#25325) 2024-08-13 23:18:56 +00:00
Isaac Francisco
e0bbb81d04 [docs]: standardize tool docstrings (#25351) 2024-08-13 16:10:00 -07:00
Erick Friis
d5b548b4ce docs: index pages, sidebars (#25316) 2024-08-13 15:52:51 -07:00
Isaac Francisco
0478f7f5e4 [docs]: LLM integration pages (#25005) 2024-08-13 14:50:45 -07:00