langchain

Commit Graph

Author	SHA1	Message	Date
Rodrigo Nogueira	e64cf1aba4	community: Add model argument for maritalk models and better error handling (#19187 )	6 months ago
samanhappy	ff94f86ce1	docs: fix link to interface TextSplitter (#19177 )	6 months ago
Sergey Kozlov	1a55e950aa	community[patch]: support fastembed v1 and v2 (#19125 ) Description: #18040 forces `fastembed>2.0`, and this causes dependency conflicts with the new `unstructured` package (different `onnxruntime`). There may be other dependency conflicts.. The only way to use `langchain-community>=0.0.28` is rollback to `unstructured 0.10.X`. But new `unstructured` contains many fixes. This PR allows to use both `fastembed` `v1` and `v2`. How to reproduce: `pyproject.toml`: ```toml [tool.poetry] name = "depstest" version = "0.0.0" description = "test" authors = ["<dev@example.org>"] [tool.poetry.dependencies] python = ">=3.10,<3.12" langchain-community = "^0.0.28" fastembed = "^0.2.0" unstructured = {extras = ["pdf"], version = "^0.12"} ``` ```bash $ poetry lock ``` Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>	6 months ago
six17	fd4f536c77	text-splitters[patch]: fix json split of RecursiveJsonSplitter (#19119 ) - Description: This modification addresses the issue of mutable default parameters in functions. In the original code, the `chunks` parameter is defaulted to a list containing an empty dictionary, which is mutable. Since default parameters in Python are evaluated only once at function definition time, modifications to the parameter would persist across future calls. By changing the default to `None` and checking/initializing within the function, a new list is created for each call, thus avoiding potential issues. --------- Co-authored-by: sixiang <sixiang@lixiang.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
aditya thomas	05008c4f94	docs: update stale links in Together AI documentation (#19011 ) Description: Update stales link in Together AI documentation Issue: Some links pointed to legacy webpages on the Together AI website Dependencies: None Lint and test: `make format`, `make lint` were run	6 months ago
aditya thomas	80eb510a7b	docs: update docstring of Together class (#19008 ) Description: Update docstring of Together class to show example and update API URL Issue: Improves usability Dependencies: None Lint and test: `make format`, `make lint` and `make test` were run	6 months ago
高远	ef9813dae6	docs: add vikingdb docstrings(#19016 ) Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>	6 months ago
wulixuan	0e0030f494	community[patch]: fix yuan2 chat model errors while invoke. (#19015 ) 1. fix yuan2 chat model errors while invoke. 2. update related tests. 3. fix some deprecationWarning.	6 months ago
Shuai Liu	c244e1a50b	community[patch]: Fixed bug in merging `generation_info` during chunk concatenation in Tongyi and ChatTongyi (#19014 ) - Description: In #16218 , during the `GenerationChunk` and `ChatGenerationChunk` concatenation, the `generation_info` merging changed from simple keys & values replacement to using the util method [`merge_dicts`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py): ![image](https://github.com/langchain-ai/langchain/assets/2098020/10f315bf-7fe0-43a7-a0ce-6a3834b99a15) The `merge_dicts` method could not handle merging values of `int` or some other types, and would raise a [`TypeError`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py#L55). This PR fixes this issue in the Tongyi and ChatTongyi Model by adopting the `generation_info` of the last chunk and discarding the `generation_info` of the intermediate chunks, ensuring that `stream` and `astream` function correctly. - Issue: - Related issues or PRs about Tongyi & ChatTongyi: #16605, #17105 - Other models or cases: #18441, #17376 - Dependencies: No new dependencies	6 months ago
wulixuan	f79d0cb9fb	docs: update docs for yuan2 in LLMs and Chat models integration. (#19028 ) update yuan2.0 notebook in LLMs and Chat models. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	6 months ago
Taraka Nithin Vankala	eec023766e	docs: Corrected error (#19030 ) - [ ] PR title: "docs: correction in "https://github.com/langchain-ai/langchain/blob/master/docs/docs/get_started/quickstart.mdx", line 289". - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes. - Example: "community: add foobar LLM" - [ ] PR message: - Corrected the spelling mistake - #18981	6 months ago
Christophe Bornet	f2a7dda4bd	community[patch]: Use langchain-astradb for AstraDB doc loader (#19071 ) Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Leonid Ganeline	a49ac55964	docs: `providers` update 8 (#19053 ) Added missed providers. Added missed integrations. Fixed format.	6 months ago
Holt Skinner	cee03630d9	community[patch]: Add Blended Search Support to `GoogleVertexAISearchRetriever` (#19082 ) https://cloud.google.com/generative-ai-app-builder/docs/create-data-store-es#multi-data-stores --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Eugene Yurtsev	0ddfe7fc9d	langchain[patch]: make hub work with older langchainhub versions (#19076 ) Make it work with older clients	6 months ago
William W Wang	0a784074d1	docs: Update llm_caching.ipynb (#19085 )	6 months ago
William W Wang	6327be9048	docsUpdate azure_cosmos_db.ipynb (#19087 ) Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Anubhav Madhav	553a520ab6	docs: Fixed Grammar in Considerations of Model I/O Concepts (#19091 ) Fixed Grammar in Considerations of Model I/O Concepts documentation page - Update concepts.mdx Page Link: https://python.langchain.com/docs/modules/model_io/concepts#considerations - Description: Fixed Grammar in Considerations of Model I/O Documentation Page - Issue: "to work well with the model are you using" # "to work well with the model you are using" - Dependencies: None - Twitter handle: @Anubhav_Madhav (https://twitter.com/Anubhav_Madhav) If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17. Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Shotaro Sano	d647ff1a9a	docs: Fix execution results of `docs/docs/modules/data_connection/indexing.ipynb` (#19112 ) ## Description This PR addresses a documentation issue in the [Indexing](https://python.langchain.com/docs/modules/data_connection/indexing) page. Specifically, it corrects the execution results of the Jupyter notebook under the [Source](https://python.langchain.com/docs/modules/data_connection/indexing#source) section, which were broken as detailed below. ## Problem The execution results following the statement, `This should delete the old versions of documents associated with doggy.txt source and replace them with the new versions.`, appear to be incorrect, as described below. ### Current Behavior - For some reason, the `index` function fails to add the new content of `doggy.txt`. Although it deletes the document objects associated with the `doggy.txt` source, it does not add the objects in `changed_doggy_docs`. Consequently, the execution result displays `num_added: 0`. - This unexpected behavior also impacts the results of `vectorstore.similarity_search("dog", k=30)`, showing only the contents of `kitty.txt`. It appears as though the contents of `doggy.txt` have been completely removed from the index: ``` Document(page_content='tty kitty', metadata={'source': 'kitty.txt'}), Document(page_content='tty kitty ki', metadata={'source': 'kitty.txt'}), Document(page_content='kitty kit', metadata={'source': 'kitty.txt'})] ``` ### Expected Behavior - The `index` function should successfully add the objects in `changed_doggy_docs` after removing the old content of `doggy.txt`. The anticipated execution result is `num_added: 2`. - Subsequently, the modified content of `doggy.txt` should appear in the results of `vectorstore.similarity_search("dog", k=30)` as follows: ``` [Document(page_content='woof woof', metadata={'source': 'doggy.txt'}), Document(page_content='woof woof woof', metadata={'source': 'doggy.txt'}), Document(page_content='tty kitty', metadata={'source': 'kitty.txt'}), Document(page_content='tty kitty ki', metadata={'source': 'kitty.txt'}), Document(page_content='kitty kit', metadata={'source': 'kitty.txt'})] ``` ## Fix I reran `docs/docs/modules/data_connection/indexing.ipynb` and have included the diff in this PR.	6 months ago
case-k	ebc4a64f9e	docs: fix databricks document url (#19096 ) Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Guangdong Liu	4468e5bdbe	docs: Add in code documentation to core Runnable with_fallbacks method (docs only) (#19104 ) - Description: [a description of the change] Add in code documentation to core Runnable with_fallbacks method (docs only) - Issue: the issue #18804 @eyurtsev PTAL	6 months ago
Guangdong Liu	cced3eb9bc	community[patch]: Fix sparkllm embeddings api bug. (#19122 ) - Description: Fix sparkllm embeddings api bug. @baskaryan PTAL	6 months ago
samanhappy	b9c62fb905	docs: fix API link for BaseLoader (#19128 ) The link to the BaseLoader API requires an update as it has been moved into the `langchain_core` package.	6 months ago
kaijietti	c20aeef79a	community[patch]: implement qdrant _aembed_query and use it in other async funcs (#19155 ) `amax_marginal_relevance_search ` and `asimilarity_search_with_score ` should use an async version of `_embed_query `.	6 months ago
Kostas Botsas	527676a753	docs: Fix source column xata.ipynb (#19137 ) Docs fix: replace column name search with source. The Xata integration expects metadata column named "source". The docs suggest the name "search", which if used, yields the following error: ``` File "/usr/local/lib/python3.11/site-packages/langchain_community/vectorstores/xata.py", line 95, in _add_vectors raise Exception(f"Error adding vectors to Xata: {r.status_code} {r}") Exception: Error adding vectors to Xata: 400 {'errors': [{'status': 400, 'message': 'invalid record: column [source]: column not found'}]} ```	6 months ago
Barun Amalkumar Halder	34d6f0557d	community[patch] : publishes duration as milliseconds to Fiddler (#19166 ) Description: Many LLM steps complete in sub-second duration, which can lead to non-collection of duration field for Fiddler. This PR updates duration from seconds to milliseconds. Issue: [INTERNAL] FDL-17568 Dependencies: NA Twitter handle: behalder Co-authored-by: Barun Halder <barun@fiddler.ai>	6 months ago
Eugene Yurtsev	745d2476a2	langchain: upgrade mypy (#19163 ) Update mypy in langchain	6 months ago
Maxime Perrin	aa785fa6ec	core[minor]: allow LLMs async streaming to fallback on sync streaming (#18960 ) - Description: Handling fallbacks when calling async streaming for a LLM that doesn't support it. - Issue: #18920 - Twitter handle:@maximeperrin_ --------- Co-authored-by: Maxime Perrin <mperrin@doing.fr>	6 months ago
Erick Friis	caf47ab666	infra: run min version ci before integration tests (#18945 )	6 months ago
Barun Amalkumar Halder	b551d49cf5	community[patch] : adds feedback and status for Fiddler callback handler events (#19157 ) Description: This PR adds updates the fiddler events schema to also pass user feedback, and llm status to fiddler Tickets: [INTERNAL] FDL-17559 Dependencies: NA Twitter handle: behalder Co-authored-by: Barun Halder <barun@fiddler.ai>	6 months ago
Juan Felipe Arias	f5b9aedc48	community[patch]: add args_schema to sql_database tools for langGraph integration (#18595 ) - Description: This modification adds pydantic input definition for sql_database tools. This helps for function calling capability in LangGraph. Since actions nodes will usually check for the args_schema attribute on tools, This update should make these tools compatible with it (only implemented on the InfoSQLDatabaseTool) - Issue: N/A - Dependencies: N/A - Twitter handle: juanfe8881	6 months ago
fengjial	c922ea36cb	community[minor]: Add Baidu VectorDB as vector store (#17997 ) Co-authored-by: fengjialin <fengjialin@MacBook-Pro.local>	6 months ago
aditya thomas	190887c5cd	docs: update the list of providers (#19012 ) Description: Update the list of LangChain providers Issue: Make the list of LangChain providers current Dependencies: None	6 months ago
Erick Friis	bbe164ad28	docs: voyageai as provider (#19154 )	6 months ago
Erick Friis	781aee0068	community, langchain, infra: revert store extended test deps outside of poetry (#19153 ) Reverts langchain-ai/langchain#18995 Because it makes installing dependencies in python 3.11 extended testing take 80 minutes	6 months ago
Leonid Kuligin	e3ff107e4f	docs: updated google integration related imports in the documentation (#19131 ) updated imports in the documentation for google vertex	6 months ago
Erick Friis	9e569d85a4	community, langchain, infra: store extended test deps outside of poetry (#18995 ) poetry can't reliably handle resolving the number of optional "extended test" dependencies we have. If we instead just rely on pip to install extended test deps in CI, this isn't an issue.	6 months ago
Bagatur	191ddbc77e	core[patch]: rc release 0.1.33-rc.1 (#19103 )	6 months ago
Nuno Campos	508f75853c	core[patch]: Change structured prompt lc id to match js (#19099 )	6 months ago
Erick Friis	7ce81eb6f4	voyageai[patch]: init package (#19098 ) Co-authored-by: fodizoltan <zoltan@conway.expert> Co-authored-by: Yujie Qian <thomasq0809@gmail.com> Co-authored-by: fzowl <160063452+fzowl@users.noreply.github.com>	6 months ago
Brace Sproul	5157b15446	ci[patch]: Set root dir to ./docs (#19102 )	6 months ago
Brace Sproul	98cd8f673b	docs[minor]ci[minor]: Add script & CI to check recurring links daily (#19100 )	6 months ago
Asaf Joseph Gardin	4d7f6fa968	ai21[patch]: AI21 Labs Batch Support in Embeddings (#18633 ) Description: Added support for batching when using AI21 Embeddings model Twitter handle: https://github.com/AI21Labs --------- Co-authored-by: Asaf Gardin <asafg@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Tomaz Bratanic	321db89e87	templates: Switch neo4j generation template to LLMGraphTransformer (#19024 )	6 months ago
Erick Friis	d5cf360329	ibm[patch]: release 0.1.3 (#19094 )	6 months ago
Mateusz Szewczyk	b15d150d22	ibm[patch]: add async tests, add tokenize support (#18898 ) - Description: add async tests, add tokenize support - Dependencies: [ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/), - Tag maintainer: Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally -> ✅ Please make sure integration_tests passing locally -> ✅ --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
billytrend-cohere	7253b816cc	community: Add support for cohere SDK v5 (keeps v4 backwards compatibility) (#19084 ) - Description: Add support for cohere SDK v5 (keeps v4 backwards compatibility) --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Eugene Yurtsev	06165efb5b	core[patch]: RunnablePassthrough transform to autoupgrade to AddableDict (#19051 ) Follow up on https://github.com/langchain-ai/langchain/pull/18743 which missed RunnablePassthrough Issues: https://github.com/langchain-ai/langchain/issues/18741 https://github.com/langchain-ai/langgraph/issues/136 https://github.com/langchain-ai/langserve/issues/504	6 months ago
Eugene Yurtsev	41e2f60cd2	Updated security policy (#19089 ) Updated security policy	6 months ago
Eugene Yurtsev	6cdca4355d	community[minor]: Revamp PGVector Filtering (#18992 ) This PR makes the following updates in the pgvector database: 1. Use JSONB field for metadata instead of JSON 2. Update operator syntax to include required `$` prefix before the operators (otherwise there will be name collisions with fields) 3. The change is non-breaking, old functionality is still the default, but it will emit a deprecation warning 4. Previous functionality has bugs associated with comparisons due to casting to text (so lexical ordering is used incorrectly for numeric fields) 5. Adds an a GIN index on the JSONB field for more efficient querying	6 months ago

1 2 3 4 5 ...

8149 Commits (e64cf1aba473dd87121135ed511df4f52343b9b4) All Branches Search

8149 Commits (e64cf1aba473dd87121135ed511df4f52343b9b4)

All Branches