langchain

Commit Graph

Author	SHA1	Message	Date
Eugene Yurtsev	5dbbdcbf8e	core[patch]: Update remaining root_validators (#22829 ) This PR updates the remaining root_validators in core to either be explicit pre-init or post-init validators.	3 months ago
Eugene Yurtsev	265e650e64	community[patch]: Update root_validators embeddings: llamacpp, jina, dashscope, mosaicml, huggingface_hub, Toolkits: Connery, ChatModels: PAI_EAS, (#22828 ) This PR updates root validators for: * Embeddings: llamacpp, jina, dashscope, mosaicml, huggingface_hub * Toolkits: Connery * ChatModels: PAI_EAS Following this issue: https://github.com/langchain-ai/langchain/issues/22819	3 months ago
JonZeolla	32ba8cfab0	community[minor]: implement huggingface show_progress consistently (#22682 ) - Description: This implements `show_progress` more consistently (i.e. it is also added to the `HuggingFaceBgeEmbeddings` object). - Issue: This implements `show_progress` more consistently in the embeddings huggingface classes. Previously this could have been set via `encode_kwargs`. - Dependencies: None - Twitter handle: @jonzeolla	3 months ago
Eugene Yurtsev	74e705250f	core[patch]: update some root_validators (#22787 ) Update some of the @root_validators to be explicit pre=True or pre=False, skip_on_failure=True for pydantic 2 compatibility.	3 months ago
mrhbj	a1268d9e9a	community[patch]: fix hunyuan message include chinese signature error (#22795 ) (#22796 ) … (#22795) Thank you for contributing to LangChain! - [ ] PR title: "package: description" - 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: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.	3 months ago
Mr. Lance E Sloan «UMich»	08c466c603	community[patch]: bugfix for `YoutubeLoader`'s `LINES` format (#22815 ) - Description: A change I submitted recently introduced a bug in `YoutubeLoader`'s `LINES` output format. In those conditions, curly braces ("`{}`") creates a set, not a dictionary. This bugfix explicitly specifies that a dictionary is created. - Issue: N/A - Dependencies: N/A - Twitter: lsloan_umich - Mastodon: [lsloan@mastodon.social](https://mastodon.social/@lsloan)	3 months ago
Philippe PRADOS	23c22fcbc9	langchain[minor]: Make EmbeddingsFilters async (#22737 ) Add native async implementation for EmbeddingsFilter	3 months ago
ccurme	936aedd10c	mistral[patch]: add usage_metadata to (a)invoke and (a)stream (#22781 )	3 months ago
mrhbj	9212c9fcb8	community[patch]: fix hunyuan client json analysis (#22452 ) (#22767 ) Thank you for contributing to LangChain! - [x] PR title: "package: description" - 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" - [x] PR message: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [x] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [x] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Rohan Aggarwal	86e8224cf1	community[patch]: Support for old clients (Thin and Thick) Oracle Vector Store (#22766 ) Thank you for contributing to LangChain! - [ ] PR title: "package: description" Support for old clients (Thin and Thick) Oracle Vector Store - [ ] PR message: *Delete this entire checklist* and replace with Support for old clients (Thin and Thick) Oracle Vector Store - [ ] Add tests and docs: If you're adding a new integration, please include Have our own local tests --------- Co-authored-by: rohan.aggarwal@oracle.com <rohaagga@phoenix95642.dev3sub2phx.databasede3phx.oraclevcn.com>	3 months ago
Mr. Lance E Sloan «UMich»	84dc2dd059	community[patch]: Load YouTube transcripts (captions) as fixed-duration chunks with start times (#21710 ) - Description: Add a new format, `CHUNKS`, to `langchain_community.document_loaders.youtube.YoutubeLoader` which creates multiple `Document` objects from YouTube video transcripts (captions), each of a fixed duration. The metadata of each chunk `Document` includes the start time of each one and a URL to that time in the video on the YouTube website. I had implemented this for UMich (@umich-its-ai) in a local module, but it makes sense to contribute this to LangChain community for all to benefit and to simplify maintenance. - Issue: N/A - Dependencies: N/A - Twitter: lsloan_umich - Mastodon: [lsloan@mastodon.social](https://mastodon.social/@lsloan) With regards to tests and documentation, most existing features of the `YoutubeLoader` class are not tested. Only the `YoutubeLoader.extract_video_id()` static method had a test. However, while I was waiting for this PR to be reviewed and merged, I had time to add a test for the chunking feature I've proposed in this PR. I have added an example of using chunking to the `docs/docs/integrations/document_loaders/youtube_transcript.ipynb` notebook. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Aayush Kataria	71811e0547	community[minor]: Adds a vector store for Azure Cosmos DB for NoSQL (#21676 ) This PR add supports for Azure Cosmos DB for NoSQL vector store. Summary: Description: added vector store integration for Azure Cosmos DB for NoSQL Vector Store, Dependencies: azure-cosmos dependency, Tag maintainer: @hwchase17, @baskaryan @efriis @eyurtsev --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Mohammad Mohtashim	36cad5d25c	[Community]: Added Metadata filter support for DocumentDB Vector Store (#22777 ) - Description: As pointed out in this issue #22770, DocumentDB `similarity_search` does not support filtering through metadata which this PR adds by passing in the parameter `filter`. Also this PR fixes a minor Documentation error. - Issue: #22770 --------- Co-authored-by: Erick Friis <erickfriis@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
Dmitry Stepanov	912751e268	Ollama vision support (#22734 ) Description: Ollama vision with messages in OpenAI-style support `{ "image_url": { "url": ... } }` Issue: #22460 Added flexible solution for ChatOllama to support chat messages with images. Works when you provide either `image_url` as a string or as a dict with "url" inside (like OpenAI does). So it makes available to use tuples with `ChatPromptTemplate.from_messages()` --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Philippe PRADOS	0908b01cb2	langchain[minor]: Add native async implementation to LLMFilter, add concurrency to both sync and async paths (#22739 ) Thank you for contributing to LangChain! - [ ] PR title: "langchain: Fix chain_filter.py to be compatible with async" - [ ] PR message: - Description: chain_filter is not compatible with async. - Twitter handle: pprados - [X ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ --------- Signed-off-by: zhangwangda <zhangwangda94@163.com> Co-authored-by: Prakul <discover.prakul@gmail.com> Co-authored-by: Lei Zhang <zhanglei@apache.org> Co-authored-by: Gin <ictgtvt@gmail.com> Co-authored-by: wangda <38549158+daziz@users.noreply.github.com> Co-authored-by: Max Mulatz <klappradla@posteo.net>	3 months ago
Jaeyeon Kim(김재연)	ce4e29ae42	community[minor]: fix redis store docstring and streamline initialization code (#22730 ) Thank you for contributing to LangChain! ### Description Fix the example in the docstring of redis store. Change the initilization logic and remove redundant check, enhance error message. ### Issue The example in docstring of how to use redis store was wrong. ![image](https://github.com/langchain-ai/langchain/assets/37469330/78c5d9ce-ee66-45b3-8dfe-ea29f125e6e9) ### Dependencies Nothing - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [x] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	3 months ago
am-kinetica	ad101adec8	community[patch]: Kinetica Integrations handled error in querying; quotes in table names; updated gpudb API (#22724 ) - [ ] Miscellaneous updates and fixes: - Description: Handled error in querying; quotes in table names; updated gpudb API - Issue: Threw an error with an error message difficult to understand if a query failed or returned no records - Dependencies: Updated GPUDB API version to `7.2.0.9` @baskaryan @hwchase17	3 months ago
Mathis Joffre	ea43f40daf	community[minor]: Add support for OVHcloud AI Endpoints Embedding (#22667 ) Description: Add support for [OVHcloud AI Endpoints](https://endpoints.ai.cloud.ovh.net/) Embedding models. Inspired by: https://gist.github.com/gmasse/e1f99339e161f4830df6be5d0095349a Signed-off-by: Joffref <mariusjoffre@gmail.com>	3 months ago
Erick Friis	2aaf86ddae	core: fix mustache falsy cases (#22747 )	3 months ago
Eugene Yurtsev	5a7eac191a	core[patch]: Add missing type annotations (#22756 ) Add missing type annotations. The missing type annotations will raise exceptions with pydantic 2.	3 months ago
Eugene Yurtsev	05d31a2f00	community[patch]: Add missing type annotations (#22758 ) Add missing type annotations to objects in community. These missing type annotations will raise type errors in pydantic 2.	3 months ago
Naka Masato	3237909221	langchain[patch]: allow to use partial variables in create_sql_query_chain (#22688 ) - Description: allow to use partial variables to pass `top_k` and `table_info` - Issue: no - Dependencies: no - Twitter handle: @gymnstcs --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Bharat Ramanathan	2b5631a6be	community[patch]: fix `WandbTracer` to work with new "RunV2" API (#22673 ) - Description: This PR updates the `WandbTracer` to work with the new RunV2 API so that wandb Traces logging works correctly for new LangChain versions. Here's an example [run](https://wandb.ai/parambharat/langchain-tracing/runs/wpm99ftq) from the existing tests - Issue: https://github.com/wandb/wandb/issues/7762 - Twitter handle: @ParamBharat _If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17._	3 months ago
Oguz Vuruskaner	f0f4532579	community[patch]: fix deepinfra inference (#22680 ) This PR includes: 1. Update of default model to LLama3. 2. Handle some 400x errors with more user friendly error messages. 3. Handle user errors.	3 months ago
Lucas Tucker	cb79e80b0b	docs: standardize ChatHuggingFace (#22693 ) Updated ChatHuggingFace doc string as per issue #22296: "langchain_huggingface: updated docstring for ChatHuggingFace in langchain_huggingface to match that of the description (in the appendix) provided in issue #22296. " Issue: This PR is in response to issue #22296, and more specifically ChatHuggingFace model. In particular, this PR updates the docstring for langchain/libs/partners/hugging_face/langchain_huggingface/chat_models/huggingface.py by adding the following sections: Instantiate, Invoke, Stream, Async, Tool calling, and Response metadata. I used the template from the Anthropic implementation and referenced the Appendix of the original issue post. I also noted that: langchain_community hugging face llms do not work with langchain_huggingface's ChatHuggingFace model (at least for me); the .stream(messages) functionality of ChatHuggingFace only returned a block of response. --------- Co-authored-by: lucast2021 <lucast2021@headroyce.org> Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Tomaz Bratanic	76a193decc	community[patch]: Add function response to graph cypher qa chain (#22690 ) LLMs struggle with Graph RAG, because it's different from vector RAG in a way that you don't provide the whole context, only the answer and the LLM has to believe. However, that doesn't really work a lot of the time. However, if you wrap the context as function response the accuracy is much better. btw... `union[LLMChain, Runnable]` is linting fun, that's why so many ignores	3 months ago
X-HAN	34edfe4a16	community[minor]: add Volcengine Rerank (#22700 ) Description: this PR adds Volcengine Rerank capability to Langchain, you can find Volcengine Rerank API from [here](https://www.volcengine.com/docs/84313/1254474) & [here](https://www.volcengine.com/docs/84313/1254605). [Volcengine](https://www.volcengine.com/) is a cloud service platform developed by ByteDance, the parent company of TikTok. You can obtain Volcengine API AK/SK from [here](https://www.volcengine.com/docs/84313/1254553). Dependencies: VolcengineRerank depends on `volcengine` python package. Twitter handle: my twitter/x account is https://x.com/LastMonopoly and I'd like a mention, thank you! Tests and docs 1. integration test: `test_volcengine_rerank.py` 2. example notebook: `volcengine_rerank.ipynb` Lint and test: I have run `make format`, `make lint` and `make test` from the root of the package I've modified.	3 months ago
Mohammad Mohtashim	c3cce98d86	community[patch]: Small Fix in OutlookMessageLoader (Close the Message once Open) (#22744 ) - Description: A very small fix where we close the message when it opened - Issue: #22729	3 months ago
ccurme	f9fdca6cc2	openai: add `parallel_tool_calls` to api ref (#22746 ) ![Screenshot 2024-06-10 at 1 41 24 PM](https://github.com/langchain-ai/langchain/assets/26529506/2626bf9c-41c6-4431-b2e1-f59de1e4e468)	3 months ago
Max Mulatz	058a64c563	Community[minor]: Add language parser for Elixir (#22742 ) Hi 👋 First off, thanks a ton for your work on this 💚 Really appreciate what you're providing here for the community. ## Description This PR adds a basic language parser for the [Elixir](https://elixir-lang.org/) programming language. The parser code is based upon the approach outlined in https://github.com/langchain-ai/langchain/pull/13318: it's using `tree-sitter` under the hood and aligns with all the other `tree-sitter` based parses added that PR. The `CHUNK_QUERY` I'm using here is probably not the most sophisticated one, but it worked for my application. It's a starting point to provide "core" parsing support for Elixir in LangChain. It enables people to use the language parser out in real world applications which may then lead to further tweaking of the queries. I consider this PR just the ground work. - Dependencies: requires `tree-sitter` and `tree-sitter-languages` from the extended dependencies - Twitter handle:`@bitcrowd` ## Checklist - [x] PR title: "package: description" - [x] Add tests and docs - [x] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. <!-- If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. -->	3 months ago
Philippe PRADOS	2d4689d721	langchain[minor]: Add pgvector to list of supported vectorstores in self query retriever (#22678 ) The fact that we outsourced pgvector to another project has an unintended effect. The mapping dictionary found by `_get_builtin_translator()` cannot recognize the new version of pgvector because it comes from another package. `SelfQueryRetriever` no longer knows `PGVector`. I propose to fix this by creating a global dictionary that can be populated by various database implementations. Thus, importing `langchain_postgres` will allow the registration of the `PGvector` mapping. But for the moment I'm just adding a lazy import Furthermore, the implementation of _get_builtin_translator() reconstructs the BUILTIN_TRANSLATORS variable with each invocation, which is not very efficient. A global map would be an optimization. - Twitter handle: pprados @eyurtsev, can you review this PR? And unlock the PR [Add async mode for pgvector](https://github.com/langchain-ai/langchain-postgres/pull/32) and PR [community[minor]: Add SQL storage implementation](https://github.com/langchain-ai/langchain/pull/22207)? Are you in favour of a global dictionary-based implementation of Translator?	3 months ago
Enzo Poggio	8f019e91d7	community[patch]: Use Custom Logger Instead of Root Logger in get_user_agent Function (#22691 ) ## Description This PR addresses a logging inconsistency in the `get_user_agent` function. Previously, the function was using the root logger to log a warning message when the "USER_AGENT" environment variable was not set. This bypassed the custom logger `log` that was created at the start of the module, leading to potential inconsistencies in logging behavior. Changes: - Replaced `logging.warning` with `log.warning` in the `get_user_agent` function to ensure that the custom logger is used. This change ensures that all logging in the `get_user_agent` function respects the configurations of the custom logger, leading to more consistent and predictable logging behavior. ## Dependencies None ## Issue None ## Tests and docs ☝🏻 see description ## `make format`, `make lint` & `cd libs/community; make test` ```shell > make format poetry run ruff format docs templates cookbook 1417 files left unchanged poetry run ruff check --select I --fix docs templates cookbook All checks passed! ``` ```shell > make lint poetry run ruff check docs templates cookbook All checks passed! poetry run ruff format docs templates cookbook --diff 1417 files already formatted poetry run ruff check --select I docs templates cookbook All checks passed! git grep 'from langchain import' docs/docs templates cookbook \| grep -vE 'from langchain import (hub)' && exit 1 \|\| exit 0 ``` ~cd libs/community; make test~ too much dependencies for integration ... ```shell > poetry run pytest tests/unit_tests .... ==== 884 passed, 466 skipped, 4447 warnings in 15.93s ==== ``` I choose you randomly : @ccurme	3 months ago
Philippe PRADOS	9aabb446c5	community[minor]: Add SQL storage implementation (#22207 ) Hello @eyurtsev - package: langchain-comminity - Description: Add SQL implementation for docstore. A new implementation, in line with my other PR ([async PGVector](https://github.com/langchain-ai/langchain-postgres/pull/32), [SQLChatMessageMemory](https://github.com/langchain-ai/langchain/pull/22065)) - Twitter handler: pprados --------- Signed-off-by: ChengZi <chen.zhang@zilliz.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Piotr Mardziel <piotrm@gmail.com> Co-authored-by: ChengZi <chen.zhang@zilliz.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	3 months ago
Nithish Raghunandanan	f2f0e0e13d	couchbase: Add the initial version of Couchbase partner package (#22087 ) Co-authored-by: Nithish Raghunandanan <nithishr@users.noreply.github.com> Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
Cahid Arda Öz	6c07eb0c12	community[minor]: Add UpstashRatelimitHandler (#21885 ) Adding `UpstashRatelimitHandler` callback for rate limiting based on number of chain invocations or LLM token usage. For more details, see [upstash/ratelimit-py repository](https://github.com/upstash/ratelimit-py) or the notebook guide included in this PR. Twitter handle: @cahidarda --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	3 months ago
Erick Friis	9e03864d64	core: add error message for non-structured llm to StructuredPrompt (#22684 ) previously was the blank `NotImplementedError` from `BaseLanguageModel.with_structured_output`	3 months ago
ccurme	f32d57f6f0	anthropic: refactor streaming to use events api; add streaming usage metadata (#22628 ) - Refactor streaming to use raw events; - Add `stream_usage` class attribute and kwarg to stream methods that, if True, will include separate chunks in the stream containing usage metadata. There are two ways to implement streaming with anthropic's python sdk. They have slight differences in how they surface usage metadata. 1. [Use helper functions](https://github.com/anthropics/anthropic-sdk-python?tab=readme-ov-file#streaming-helpers). This is what we are doing now. ```python count = 1 with client.messages.stream(params) as stream: for text in stream.text_stream: snapshot = stream.current_message_snapshot print(f"{count}: {snapshot.usage} -- {text}") count = count + 1 final_snapshot = stream.get_final_message() print(f"{count}: {final_snapshot.usage}") ``` ``` 1: Usage(input_tokens=8, output_tokens=1) -- Hello 2: Usage(input_tokens=8, output_tokens=1) -- ! 3: Usage(input_tokens=8, output_tokens=1) -- How 4: Usage(input_tokens=8, output_tokens=1) -- can 5: Usage(input_tokens=8, output_tokens=1) -- I 6: Usage(input_tokens=8, output_tokens=1) -- assist 7: Usage(input_tokens=8, output_tokens=1) -- you 8: Usage(input_tokens=8, output_tokens=1) -- today 9: Usage(input_tokens=8, output_tokens=1) -- ? 10: Usage(input_tokens=8, output_tokens=12) ``` To do this correctly, we need to emit a new chunk at the end of the stream containing the usage metadata. 2. [Handle raw events](https://github.com/anthropics/anthropic-sdk-python?tab=readme-ov-file#streaming-responses) ```python stream = client.messages.create(params, stream=True) count = 1 for event in stream: print(f"{count}: {event}") count = count + 1 ``` ``` 1: RawMessageStartEvent(message=Message(id='msg_01Vdyov2kADZTXqSKkfNJXcS', content=[], model='claude-3-haiku-20240307', role='assistant', stop_reason=None, stop_sequence=None, type='message', usage=Usage(input_tokens=8, output_tokens=1)), type='message_start') 2: RawContentBlockStartEvent(content_block=TextBlock(text='', type='text'), index=0, type='content_block_start') 3: RawContentBlockDeltaEvent(delta=TextDelta(text='Hello', type='text_delta'), index=0, type='content_block_delta') 4: RawContentBlockDeltaEvent(delta=TextDelta(text='!', type='text_delta'), index=0, type='content_block_delta') 5: RawContentBlockDeltaEvent(delta=TextDelta(text=' How', type='text_delta'), index=0, type='content_block_delta') 6: RawContentBlockDeltaEvent(delta=TextDelta(text=' can', type='text_delta'), index=0, type='content_block_delta') 7: RawContentBlockDeltaEvent(delta=TextDelta(text=' I', type='text_delta'), index=0, type='content_block_delta') 8: RawContentBlockDeltaEvent(delta=TextDelta(text=' assist', type='text_delta'), index=0, type='content_block_delta') 9: RawContentBlockDeltaEvent(delta=TextDelta(text=' you', type='text_delta'), index=0, type='content_block_delta') 10: RawContentBlockDeltaEvent(delta=TextDelta(text=' today', type='text_delta'), index=0, type='content_block_delta') 11: RawContentBlockDeltaEvent(delta=TextDelta(text='?', type='text_delta'), index=0, type='content_block_delta') 12: RawContentBlockStopEvent(index=0, type='content_block_stop') 13: RawMessageDeltaEvent(delta=Delta(stop_reason='end_turn', stop_sequence=None), type='message_delta', usage=MessageDeltaUsage(output_tokens=12)) 14: RawMessageStopEvent(type='message_stop') ``` Here we implement the second option, in part because it should make things easier when implementing streaming tool calls in the near future. This would add two new chunks to the stream-- one at the beginning and one at the end-- with blank content and containing usage metadata. We add kwargs to the stream methods and a class attribute allowing for this behavior to be toggled. I enabled it by default. If we merge this we can add the same kwargs / attribute to OpenAI. Usage: ```python from langchain_anthropic import ChatAnthropic model = ChatAnthropic( model="claude-3-haiku-20240307", temperature=0 ) full = None for chunk in model.stream("hi"): full = chunk if full is None else full + chunk print(chunk) print(f"\nFull: {full}") ``` ``` content='' id='run-8a20843f-25c7-4025-ad72-9add395899e3' usage_metadata={'input_tokens': 8, 'output_tokens': 0, 'total_tokens': 8} content='Hello' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content='!' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' How' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' can' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' I' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' assist' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' you' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content=' today' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content='?' id='run-8a20843f-25c7-4025-ad72-9add395899e3' content='' id='run-8a20843f-25c7-4025-ad72-9add395899e3' usage_metadata={'input_tokens': 0, 'output_tokens': 12, 'total_tokens': 12} Full: content='Hello! How can I assist you today?' id='run-8a20843f-25c7-4025-ad72-9add395899e3' usage_metadata={'input_tokens': 8, 'output_tokens': 12, 'total_tokens': 20} ```	3 months ago
Bagatur	235d91940d	community[patch]: Release 0.2.4 (#22643 )	3 months ago
William FH	be79ce9336	[Core] Unified Enable/Disable Tracing (#22576 )	3 months ago
Bagatur	fe2e5a3b74	langchain[patch]: Release 0.2.3 (#22644 )	3 months ago
Erick Friis	a24a9c6427	multiple: get rid of pyproject extras (#22581 ) They cause `poetry lock` to take a ton of time, and `uv pip install` can resolve the constraints from these toml files in trivial time (addressing problem with #19153) This allows us to properly upgrade lockfile dependencies moving forward, which revealed some issues that were either fixed or type-ignored (see file comments)	3 months ago
Bagatur	4367e89c9a	core[patch]: Release 0.2.5 (#22642 )	3 months ago
Eugene Yurtsev	28f744c1f5	core[patch]: Correctly order parent ids in astream events (from root to immediate parent), add defensive check for cycles (#22637 ) This PR makes two changes: 1. Fixes the order of parent IDs to be from root to immediate parent 2. Adds a simple defensive check for cycles	3 months ago
Eugene Yurtsev	035a9c9609	core[minor]: Add parent_ids to astream_events API (#22563 ) Include a list of parent ids for each event in astream events.	3 months ago
Nicolas Nkiere	51005e2776	core[minor]: Add an async root listener and with_alisteners method (#22151 ) - [x] Adding AsyncRootListener: "langchain_core: Adding AsyncRootListener" - Description: Adding an AsyncBaseTracer, AsyncRootListener and `with_alistener` function. This is to enable binding async root listener to runnables. This currently only supported for sync listeners. - Issue: None - Dependencies: None - [x] Add tests and docs: Added units tests and example snippet code within the function description of `with_alistener` - [x] Lint and test: Run make format_diff, make lint_diff and make test	3 months ago
seyf97	2904c50cd5	openai[patch]: correct grammar in exception message in embeddings/base.py (#22629 ) Correct the grammar error for missing transformers package ValueError	3 months ago
Anush	80560419b0	qdrant[patch]: Make path optional in from_existing_collection() (#21875 ) ## Description The `path` param is used to specify the local persistence directory, which isn't required if using Qdrant server. This is a breaking but necessary change.	3 months ago
ccurme	b57aa89f34	multiple: implement ls_params (#22621 ) implement ls_params for ai21, fireworks, groq.	3 months ago
Xiangrui Meng	f26ab93df8	community: support Databricks Unity Catalog functions as LangChain tools (#22555 ) This PR adds support for using Databricks Unity Catalog functions as LangChain tools, which runs inside a Databricks SQL warehouse. * An example notebook is provided.	3 months ago
ccurme	c1ef731503	anthropic: update attribute name and alias (#22625 ) update name to `stop_sequences` and alias to `stop` (instead of the other way around), since `stop_sequences` is the name used by anthropic.	3 months ago
lucasiscovici	05bf98b2f9	community[patch]: pgvector replace nin_ by not_in (#22619 ) - [ ] community: "pgvector: replace nin_ by not_in" - [ ] PR message: nin_ do not exist in sqlalchemy orm, it's not_in	3 months ago
ccurme	3999761201	multiple: add `stop` attribute (#22573 )	3 months ago
ccurme	e08879147b	Revert "anthropic: stream token usage" (#22624 ) Reverts langchain-ai/langchain#20180	3 months ago
Bagatur	0d495f3f63	anthropic: stream token usage (#20180 ) open to other ideas <img width="1181" alt="Screenshot 2024-04-08 at 5 34 08 PM" src="https://github.com/langchain-ai/langchain/assets/22008038/03eb11c4-5eb5-43e3-9109-a13f76098fa4"> --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	3 months ago
Satyam Kumar	17b486a37b	openai, azure: update model_name in ChatResult to use name from API response (#22569 ) The response.get("model", self.model_name) checks if the model key exists in the response dictionary. If it does, it uses that value; otherwise, it uses self.model_name. Thank you for contributing to LangChain! - [ ] PR title: "package: description" - 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: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Christophe Bornet	12ddb4fc6f	core[patch]: Use explicit classes for InMemoryByteStore and InMemoryStore (#22608 ) The current implementation doesn't work well with type checking. Instead replace with class definition that correctly works with type checking.	3 months ago
andyjessen	cfed68e06f	docs: Fix description (#22611 ) This commit fixes the description of the hair_color field.	3 months ago
ccurme	1925bde32e	together: bump langchain-core (#22616 ) langchain-together depends on langchain-openai ^0.1.8 langchain-openai 0.1.8 has langchain-core >= 0.2.2 Here we bump langchain-core to 0.2.2, just to pass minimum dependency version tests.	3 months ago
ccurme	35f4aa927b	together[patch]: Release 0.1.3 (#22615 )	3 months ago
andyjessen	8b40428f58	docs: Fix typo (#22603 ) This commit changes minor typo in the field description.	3 months ago
Isaac Francisco	ba3e219d83	community[patch]: recursive url loader fix and unit tests (#22521 ) Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Jeffrey Mak	5fc5ed463c	community[patch]:Support filter for AzureAISearchRetriever (#22303 ) Description: The AzureAISearchRetriever does not support the "$filter" argument offered in the AISearch API: https://learn.microsoft.com/en-us/rest/api/searchservice/documents/search-get?view=rest-searchservice-2023-11-01&tabs=HTTP The $filter allows filtering of indexes based on values in metadata. Issue: https://github.com/langchain-ai/langchain/issues/19885 Dependencies: No Twitter handle: @Jeffreym9M - [ ] Add tests and docs: Not relevant - [x] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/	3 months ago
Isaac Francisco	148088a588	docs: duckduckgosearch options listed (#22568 ) Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
X-HAN	62f13f95e4	community[minor]: add DashScope Rerank (#22403 ) Description: this PR adds DashScope Rerank capability to Langchain, you can find DashScope Rerank API from [here](https://help.aliyun.com/document_detail/2780058.html?spm=a2c4g.2780059.0.0.6d995024FlrJ12) & [here](https://help.aliyun.com/document_detail/2780059.html?spm=a2c4g.2780058.0.0.63f75024cr11N9). [DashScope](https://dashscope.aliyun.com/) is the generative AI service from Alibaba Cloud (Aliyun). You can create DashScope API key from [here](https://bailian.console.aliyun.com/?apiKey=1#/api-key). Dependencies: DashScopeRerank depends on `dashscope` python package. Twitter handle: my twitter/x account is https://x.com/LastMonopoly and I'd like a mention, thanks you! Tests and docs 1. integration test: `test_dashscope_rerank.py` 2. example notebook: `dashscope_rerank.ipynb` Lint and test: I have run `make format`, `make lint` and `make test` from the root of the package I've modified. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Ethan Yang	29064848f9	[Community]add option to delete the prompt from HF output (#22225 ) This will help to solve pattern mismatching issue when parsing the output in Agent. https://github.com/langchain-ai/langchain/issues/21912	3 months ago
Bagatur	584a1e30ac	community[patch]: AzureSearch async functions (#22075 )	3 months ago
Bagatur	1a911018bc	langchain[minor]: add universal init_model (#22039 ) decisions to discuss - only chat models - model_provider isn't based on any existing values like llm-type, package names, class names - implemented as function not as a wrapper ChatModel - function name (init_model) - in langchain as opposed to community or core - marked beta	3 months ago
ccurme	af129974a3	community: update how OpenAIAssistantV2Runnable creates threads with tool_resources (#22549 ) https://github.com/langchain-ai/langchain/issues/22503	3 months ago
Bagatur	51a0d4574e	community[patch]: Release 0.2.3 (#22562 )	3 months ago
Bagatur	b2daba37c7	nomic[patch]: Release 0.1.2 (#22561 )	3 months ago
Zach Nussbaum	14f3014cce	embeddings: nomic embed vision (#22482 ) Thank you for contributing to LangChain! Description: Adds Langchain support for Nomic Embed Vision Twitter handle: nomic_ai,zach_nussbaum - [x] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Lance Martin <122662504+rlancemartin@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
leila-messallem	3280a5b49b	community[patch]: improve test setup to accurately test filtering of labels in neo4j (#22531 ) Description: This PR addresses an issue with an existing test that was not effectively testing the intended functionality. The previous test setup did not adequately validate the filtering of the labels in neo4j, because the nodes and relationship in the test data did not have any properties set. Without properties these labels would not have been returned, regardless of the filtering. --------- Co-authored-by: Oskar Hane <oh@oskarhane.com>	3 months ago
Mohammad Mohtashim	7fcef2556c	[Experimental]: Async agenerate method ollama functions (#21682 ) - Description: : Added Async method for Generate for OllamaFunctions which was missing and was raising errors for the users. - Issue: #21422	3 months ago
Stefano Lottini	328d0c99f2	community[minor]: Add support for metadata indexing policy in Cassandra vector store (#22548 ) This PR adds a constructor `metadata_indexing` parameter to the Cassandra vector store to allow optional fine-tuning of which fields of the metadata are to be indexed. This is a feature supported by the underlying CassIO library. Indexing mode of "all", "none" or deny- and allow-list based choices are available. The rationale is, in some cases it's advisable to programmatically exclude some portions of the metadata from the index if one knows in advance they won't ever be used at search-time. this keeps the index more lightweight and performant and avoids limitations on the length of _indexed_ strings. I added a integration test of the feature. I also added the possibility of running the integration test with Cassandra on an arbitrary IP address (e.g. Dockerized), via `CASSANDRA_CONTACT_POINTS=10.1.1.5,10.1.1.6 poetry run pytest [...]` or similar. While I was at it, I added a line to the `.gitignore` since the mypy _test_ cache was not ignored yet. My X (Twitter) handle: @rsprrs.	3 months ago
Emilien Chauvet	c3d4126eb1	community[minor]: add user agent for web scraping loaders (#22480 ) Description: This PR adds a `USER_AGENT` env variable that is to be used for web scraping. It creates a util to get that user agent and uses it in the classes used for scraping in [this piece of doc](https://python.langchain.com/v0.1/docs/use_cases/web_scraping/). Identifying your scraper is considered a good politeness practice, this PR aims at easing it. Issue: `None` Dependencies: `None` Twitter handle: `None`	3 months ago
Philippe PRADOS	8250c177de	community[minor]: Add native async support to SQLChatMessageHistory (#22065 ) # package community: Fix SQLChatMessageHistory ## Description Here is a rewrite of `SQLChatMessageHistory` to properly implement the asynchronous approach. The code circumvents [issue 22021](https://github.com/langchain-ai/langchain/issues/22021) by accepting a synchronous call to `def add_messages()` in an asynchronous scenario. This bypasses the bug. For the same reasons as in [PR 22](https://github.com/langchain-ai/langchain-postgres/pull/32) of `langchain-postgres`, we use a lazy strategy for table creation. Indeed, the promise of the constructor cannot be fulfilled without this. It is not possible to invoke a synchronous call in a constructor. We compensate for this by waiting for the next asynchronous method call to create the table. The goal of the `PostgresChatMessageHistory` class (in `langchain-postgres`) is, among other things, to be able to recycle database connections. The implementation of the class is problematic, as we have demonstrated in [issue 22021](https://github.com/langchain-ai/langchain/issues/22021). Our new implementation of `SQLChatMessageHistory` achieves this by using a singleton of type (`Async`)`Engine` for the database connection. The connection pool is managed by this singleton, and the code is then reentrant. We also accept the type `str` (optionally complemented by `async_mode`. I know you don't like this much, but it's the only way to allow an asynchronous connection string). In order to unify the different classes handling database connections, we have renamed `connection_string` to `connection`, and `Session` to `session_maker`. Now, a single transaction is used to add a list of messages. Thus, a crash during this write operation will not leave the database in an unstable state with a partially added message list. This makes the code resilient. We believe that the `PostgresChatMessageHistory` class is no longer necessary and can be replaced by: ``` PostgresChatMessageHistory = SQLChatMessageHistory ``` This also fixes the bug. ## Issue - [issue 22021](https://github.com/langchain-ai/langchain/issues/22021) - Bug in _exit_history() - Bugs in PostgresChatMessageHistory and sync usage - Bugs in PostgresChatMessageHistory and async usage - [issue 36](https://github.com/langchain-ai/langchain-postgres/issues/36) ## Twitter handle: pprados ## Tests - libs/community/tests/unit_tests/chat_message_histories/test_sql.py (add async test) @baskaryan, @eyurtsev or @hwchase17 can you check this PR ? And, I've been waiting a long time for validation from other PRs. Can you take a look? - [PR 32](https://github.com/langchain-ai/langchain-postgres/pull/32) - [PR 15575](https://github.com/langchain-ai/langchain/pull/15575) - [PR 13200](https://github.com/langchain-ai/langchain/pull/13200) --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	3 months ago
Vincent Min	59bef31997	community[minor]: Improve InMemoryVectorStore with ability to persist to disk and filter on metadata. (#22186 ) - Description: The InMemoryVectorStore is a nice and simple vector store implementation for quick development and debugging. The current implementation is quite limited in its functionalities. This PR extends the functionalities by adding utility function to persist the vector store to a json file and to load it from a json file. We choose the json file format because it allows inspection of the database contents in a text editor, which is great for debugging. Furthermore, it adds a `filter` keyword that can be used to filter out documents on their `page_content` or `metadata`. - Issue: - - Dependencies: - - Twitter handle: @Vincent_Min	3 months ago
Christophe Bornet	c34ad8c163	core[patch]: Improve VectorStore API doc (#22547 )	3 months ago
maang-h	89128b7a49	community[patch]: add detailed paragraph and example for BaichuanTextEmbeddings (#22031 ) - Description: add detailed paragraph and example for BaichuanTextEmbeddings - Issue: the issue #21983	3 months ago
Anthony Bernabeu	4e676a63b8	community[minor]: Added filter search for LanceDB (#22461 ) - [ ] community: "vectorstore: added filtering support for LanceDB vector store" - [ ] This PR adds filtering capabilities to LanceDB: - Description: In LanceDB filtering can be applied when searching for data into the vectorstore. It is using the SQL language as mentioned in the LanceDB documentation. - Issue: #18235 - Dependencies: No - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/	3 months ago
Erick Friis	4050d6ea2b	huggingface: remove text-generation dep (#22543 )	3 months ago
Erick Friis	a6fc74f379	ai21: fix core version (#22544 )	3 months ago
Asaf Joseph Gardin	75cba742e5	ai21: fix ai21 unittests (#22526 ) Co-authored-by: Asaf Gardin <asafg@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	3 months ago
Erick Friis	58192d617f	community: fix huggingface deprecations (#22522 )	3 months ago
Christophe Bornet	8ba868d3b0	core[patch]: Add similarity_score_threshold to VectorStore search types (#22477 )	3 months ago
Eugene Yurtsev	9120cf5df2	core[patch]: Deduplicate of callback handlers in merge_configs (#22478 ) This PR adds deduplication of callback handlers in merge_configs. Fix for this issue: https://github.com/langchain-ai/langchain/issues/22227 The issue appears when the code is: 1) running python >=3.11 2) invokes a runnable from within a runnable 3) binds the callbacks to the child runnable from the parent runnable using with_config In this case, the same callbacks end up appearing twice: (1) the first time from with_config, (2) the second time with langchain automatically propagating them on behalf of the user. Prior to this PR this will emit duplicate events: ```python @tool async def get_items(question: str, callbacks: Callbacks): # <--- Accept callbacks """Ask question""" template = ChatPromptTemplate.from_messages( [ ( "human", "'{question}" ) ] ) chain = template \| chat_model.with_config( { "callbacks": callbacks, # <-- Propagate callbacks } ) return await chain.ainvoke({"question": question}) ``` Prior to this PR this will work work correctly (no duplicate events): ```python @tool async def get_items(question: str, callbacks: Callbacks): # <--- Accept callbacks """Ask question""" template = ChatPromptTemplate.from_messages( [ ( "human", "'{question}" ) ] ) chain = template \| chat_model return await chain.ainvoke({"question": question}, {"callbacks": callbacks}) ``` This will also work (as long as the user is using python >= 3.11) -- as langchain will automatically propagate callbacks ```python @tool async def get_items(question: str,): """Ask question""" template = ChatPromptTemplate.from_messages( [ ( "human", "'{question}" ) ] ) chain = template \| chat_model return await chain.ainvoke({"question": question}) ```	3 months ago
Ofer Mendelevitch	ad502e8d50	community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334 ) Thank you for contributing to LangChain! Description: update to the Vectara / Langchain integration to integrate new Vectara capabilities: - Full RAG implemented as a Runnable with as_rag() - Vectara chat supported with as_chat() - Both support streaming response - Updated documentation and example notebook to reflect all the changes - Updated Vectara templates Twitter handle: ofermend Add tests and docs: no new tests or docs, but updated both existing tests and existing docs	3 months ago
Bagatur	cb183a9bf1	docs: update anthropic chat model (#22483 ) Related to #22296 And update anthropic to accept base_url	3 months ago
Erick Friis	d700ce8545	robocorp: typo (#22509 )	3 months ago
Erick Friis	39fd44579a	robocorp: release 0.0.9.post1 (#22507 )	3 months ago
Erick Friis	339e3b7f55	ai21: release 0.1.6 (#22508 )	3 months ago
ccurme	3c53cea760	together, upstage: bump minimum langchain-openai version (#22505 )	3 months ago
Bagatur	efcb04f84b	mongodb[patch]: Release 0.1.6 (#22501 )	3 months ago
Bagatur	222b1ba112	groq[patch]: Release 0.1.5 (#22500 )	3 months ago
Bagatur	f021be510e	milvus[patch]: Release 0.1.1 (#22499 )	3 months ago
Bagatur	64d68c17cd	upstage[patch]: Release 0.1.6 (#22498 )	3 months ago
Bagatur	48fba40fce	experimental[patch]: Release 0.0.60 (#22497 )	3 months ago
Bagatur	e60f88ccdd	community[patch]: Release 0.2.2 (#22496 )	3 months ago
Bagatur	85aa218564	langchain[patch]: Release 0.2.2 (#22495 )	3 months ago
Bagatur	8e86080def	mistralai[patch]: Release 0.1.8 (#22494 )	3 months ago
Bagatur	e850de2422	huggingface[patch]: release 0.0.2 (#22493 )	3 months ago
Bagatur	99a3cad258	text-splitters[patch]: Release 0.2.1 (#22490 )	3 months ago
Bagatur	161b02a8be	core[patch]: Release 0.2.4 (#22489 )	3 months ago
Joydeep Banik Roy	3796672c67	community, milvus, pinecone, qdrant, mongo: Broadcast operation failure while using simsimd beyond v3.7.7 (#22271 ) - [ ] Packages affected: - community: fix `cosine_similarity` to support simsimd beyond 3.7.7 - partners/milvus: fix `cosine_similarity` to support simsimd beyond 3.7.7 - partners/mongodb: fix `cosine_similarity` to support simsimd beyond 3.7.7 - partners/pinecone: fix `cosine_similarity` to support simsimd beyond 3.7.7 - partners/qdrant: fix `cosine_similarity` to support simsimd beyond 3.7.7 - [ ] Broadcast operation failure while using simsimd beyond v3.7.7: - Description: I was using simsimd 4.3.1 and the unsupported operand type issue popped up. When I checked out the repo and ran the tests, they failed as well (have attached a screenshot for that). Looks like it is a variant of https://github.com/langchain-ai/langchain/issues/18022 . Prior to 3.7.7, simd.cdist returned an ndarray but now it returns simsimd.DistancesTensor which is ineligible for a broadcast operation with numpy. With this change, it also remove the need to explicitly cast `Z` to numpy array - Issue: #19905 - Dependencies: No - Twitter handle: https://x.com/GetzJoydeep <img width="1622" alt="Screenshot 2024-05-29 at 2 50 00 PM" src="https://github.com/langchain-ai/langchain/assets/31132555/fb27b383-a9ae-4a6f-b355-6d503b72db56"> - [ ] Considerations: 1. I started with community but since similar changes were there in Milvus, MongoDB, Pinecone, and QDrant so I modified their files as well. If touching multiple packages in one PR is not the norm, then I can remove them from this PR and raise separate ones 2. I have run and verified that the tests work. Since, only MongoDB had tests, I ran theirs and verified it works as well. Screenshots attached : <img width="1573" alt="Screenshot 2024-05-29 at 2 52 13 PM" src="https://github.com/langchain-ai/langchain/assets/31132555/ce87d1ea-19b6-4900-9384-61fbc1a30de9"> <img width="1614" alt="Screenshot 2024-05-29 at 3 33 51 PM" src="https://github.com/langchain-ai/langchain/assets/31132555/6ce1d679-db4c-4291-8453-01028ab2dca5"> I have added a test for simsimd. I feel it may not go well with the CI/CD setup as installing simsimd is not a dependency requirement. I have just imported simsimd to ensure simsimd cosine similarity is invoked. However, its not a good approach. Suggestions are welcome and I can make the required changes on the PR. Please provide guidance on the same as I am new to the community. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
KyrianC	03178ee74f	community[minor]: Add tools calls to `ChatEdenAI` (#22320 ) ### Description Add tools implementation to `ChatEdenAI`: - `bind_tools()` - `with_structured_output()` ### Documentation Updated `docs/docs/integrations/chat/edenai.ipynb` ### Notes We don´t support stream with tools as of yet. If stream is called with tools we directly yield the whole message from `generate` (implemented the same way as Anthropic did).	3 months ago
pranavvuppala	9d4350e69a	docs : Update docstrings for OpenAI base.py (#22221 ) - [x] PR title: Update docstrings for OpenAI base.py -Description: Updated the docstring of few OpenAI functions for a better understanding of the function. - Issue: #21983 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	3 months ago
Anindyadeep	7a197539aa	communty[patch]: Native RAG Support in Prem AI langchain (#22238 ) This PR adds native RAG support in langchain premai package. The same has been added in the docs too.	3 months ago
Rahul Triptahi	77ad857934	community[minor]: Enable retrieval api calls in PebbloRetrievalQA (#21958 ) Description: Enable app discovery and Prompt/Response apis in PebbloSafeRetrieval Documentation: NA Unit test: N/A --------- Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com> Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>	3 months ago
liugz18	8fd231086e	experimental[patch]: Fix graph_transformers llms #21482 (#22417 ) Fix AttributeError on calling LLMGraphTransformer.convert_to_graph_documents #21482 since raw_schema is always a str @baskaryan	3 months ago
ccurme	6db25b4e31	core[patch]: bump langsmith (#22476 ) Noticing errors logged in some situations when tracing with Langsmith: ```python from langchain_core.pydantic_v1 import BaseModel from langchain_anthropic import ChatAnthropic class AnswerWithJustification(BaseModel): """An answer to the user question along with justification for the answer.""" answer: str justification: str llm = ChatAnthropic(model="claude-3-haiku-20240307") structured_llm = llm.with_structured_output(AnswerWithJustification) list(structured_llm.stream("What weighs more a pound of bricks or a pound of feathers")) ``` ``` Error in LangChainTracer.on_chain_end callback: AttributeError("'NoneType' object has no attribute 'append'") [AnswerWithJustification(answer='A pound of bricks and a pound of feathers weigh the same amount.', justification='This is because a pound is a unit of mass, not volume. By definition, a pound of any material, whether bricks or feathers, will weigh the same - one pound. The physical size or volume of the materials does not matter when measuring by mass. So a pound of bricks and a pound of feathers both weigh exactly one pound.')] ```	3 months ago
Bagatur	17c127531a	community[patch]: deprecate all HF classes (#22444 )	3 months ago
Nuno Campos	58b118544e	Use immutable sequence type for batch/batch_as_completed types (#22433 ) Thank you for contributing to LangChain! - [ ] PR title: "package: description" - 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: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.	3 months ago
Christophe Bornet	9a8fe58ebe	community[minor]: Improve Cassandra VectorStore as_retriever (#22465 ) The Vectorstore's API `as_retriever` doesn't expose explicitly the parameters `search_type` and `search_kwargs` and so these are not well documented. This PR improves `as_retriever` for the Cassandra VectorStore by making these parameters explicit. NB: An alternative would have been to modify `as_retriever` in `Vectorstore`. But there's probably a good reason these were not exposed in the first place ? Is it because implementations may decide to not support them and have fixed values when creating the VectorStoreRetriever ?	3 months ago
Christophe Bornet	23bba18f92	core[patch]: Fix VectorStore's as_retriever mutating tags param (#22470 ) The current VectorStore `as_retriever` implementation mutates the `tags` param when it's passed in kwargs. This fix ensures that a copy is done.	3 months ago
Michal Gregor	98b2e7b195	huggingface[patch]: Support for HuggingFacePipeline in ChatHuggingFace. (#22194 ) - Description: Added support for using HuggingFacePipeline in ChatHuggingFace (previously it was only usable with API endpoints, probably by oversight). - Issue: #19997 - Dependencies: none - Twitter handle: none --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Fahreddin Özcan	0061ded002	community[patch]: Upstash Vector Store Namespace Support (#22251 ) This PR introduces namespace support for Upstash Vector Store, which would allow users to partition their data in the vector index. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Guangdong Liu	bc7e32f315	core(patch):fix partial_variables not working with SystemMessagePromptTemplate (#20711 ) - Issue: close #17560 - @baskaryan, @eyurtsev	3 months ago
Dristy Srivastava	ef3df45d9d	community[minor]: Updating payload for pebblo discover API (#22309 ) Description: Updating response for pebblo discover API. Also updating filed name case type Documentation: N/A Unit tests: N/A	3 months ago
Miroslav	cbd5720011	huggingface[patch]: Skip Login to HuggingFaceHub when token is not set (#22365 )	3 months ago
bhardwaj-vipul	f397a84a59	langchain[patch]: Fix MongoDBAtlasVectorSearch reference in self query retriever (#22401 ) Description: SelfQuery Retriever with MongoDBAtlasVectorSearch (from langchain_mongodb import MongoDBAtlasVectorSearch) and Chroma (from langchain_chroma import Chroma) is not supported. The imports in the [builtin translators](`8cbce684d4/libs/langchain/langchain/retrievers/self_query/base.py (L73)`) points to the [deprecated](`acaf214a45/libs/community/langchain_community/vectorstores/mongodb_atlas.py (L36)`) vectorstore. Issue: #22272 --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
ccurme	afe89a1411	community: add standard chat model params to Ollama (#22446 )	3 months ago
Ethan Yang	52da6a160d	community[patch]: Update OpenVINO embedding and reranker to support static input shape (#22171 ) It can help to deploy embedding models on NPU device	3 months ago
Tom Clelford	c599732e1a	text-splitters[patch]: fix HTMLSectionSplitter parsing of xslt paths (#22176 ) ## Description This PR allows passing the HTMLSectionSplitter paths to xslt files. It does so by fixing two trivial bugs with how passed paths were being handled. It also changes the default value of the param `xslt_path` to `None` so the special case where the file was part of the langchain package could be handled. ## Issue #22175	3 months ago
maang-h	01352bb55f	community[minor]: Implement MiniMaxChat interface (#22391 ) - Description: Implement MiniMaxChat interface, include: - No longer inherits the LLM class (like other chat model) - Update request parameters (v1 -> v2) - update `base url` - update message role (system, user, assistant) - add `stream` function - no longer use `group id` - Implement the `_stream`, `_agenerate`, and `_astream` interfaces [minimax v2 api document](https://platform.minimaxi.com/document/guides/chat-model/V2?id=65e0736ab2845de20908e2dd)	3 months ago
Brandon Sharp	56e5aa4dd9	community[patch]: Airtable to allow for addtl params (#22092 ) - [X] PR title: "community: added optional params to Airtable table.all()" - [X] PR message: - Description: Add's kwargs to AirtableLoader to allow for kwargs: https://pyairtable.readthedocs.io/en/latest/api.html#pyairtable.Table.all - Issue: N/A - Dependencies: N/A - Twitter handle: parakoopa88 - [X] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [X] Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	3 months ago
Harichandan Roy	1f751343e2	community[patch]: update embeddings/oracleai.py (#22240 ) Thank you for contributing to LangChain! - [ ] PR title: "package: description" - 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" "community/embeddings: update oracleai.py" - [ ] PR message: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! Adding oracle VECTOR_ARRAY_T support. - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. Tests are not impacted. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Done. Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.	3 months ago
maang-h	13140dc4ff	community[patch]: Update the default api_url and reqeust_body of sparkllm embedding (#22136 ) - Description: When I was running the SparkLLMTextEmbeddings, app_id, api_key and api_secret are all correct, but it cannot run normally using the current URL. ```python # example from langchain_community.embeddings import SparkLLMTextEmbeddings embedding= SparkLLMTextEmbeddings( spark_app_id="my-app-id", spark_api_key="my-api-key", spark_api_secret="my-api-secret" ) embedding= "hello" print(spark.embed_query(text1)) ``` ![sparkembedding](https://github.com/langchain-ai/langchain/assets/55082429/11daa853-4f67-45b2-aae2-c95caa14e38c) So I updated the url and request body parameters according to [Embedding_api](https://www.xfyun.cn/doc/spark/Embedding_api.html), now it is runnable.	3 months ago
Yuwen Hu	ba0dca46d7	community[minor]: Add IPEX-LLM BGE embedding support on both Intel CPU and GPU (#22226 ) Description: [IPEX-LLM](https://github.com/intel-analytics/ipex-llm) is a PyTorch library for running LLM on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max) with very low latency. This PR adds ipex-llm integrations to langchain for BGE embedding support on both Intel CPU and GPU. Dependencies: `ipex-llm`, `sentence-transformers` Contribution maintainer: @Oscilloscope98 tests and docs: - langchain/docs/docs/integrations/text_embedding/ipex_llm.ipynb - langchain/docs/docs/integrations/text_embedding/ipex_llm_gpu.ipynb - langchain/libs/community/tests/integration_tests/embeddings/test_ipex_llm.py --------- Co-authored-by: Shengsheng Huang <shannie.huang@gmail.com>	3 months ago
Jacob Lee	c01467b1f4	core[patch]: RFC: Allow concatenation of messages with multi part content (#22002 ) Anthropic's streaming treats tool calls as different content parts (streamed back with a different index) from normal content in the `content`. This means that we need to update our chunk-merging logic to handle chunks with multi-part content. The alternative is coerceing Anthropic's responses into a string, but we generally like to preserve model provider responses faithfully when we can. This will also likely be useful for multimodal outputs in the future. This current PR does unfortunately make `index` a magic field within content parts, but Anthropic and OpenAI both use it at the moment to determine order anyway. To avoid cases where we have content arrays with holes and to simplify the logic, I've also restricted merging to chunks in order. TODO: tests CC @baskaryan @ccurme @efriis	3 months ago
Dan	86509161b0	community: fix AzureSearch delete documents (#22315 ) Description Fix AzureSearch delete documents method by using FIELDS_ID variable instead of the hard coded "id" value Issue: This is linked to this issue: https://github.com/langchain-ai/langchain/issues/22314 Co-authored-by: dseban <dan.seban@neoxia.com>	3 months ago
Harrison Chase	8fad2e209a	fix error message (#22437 ) Was confusing when language is in Enum but not implemented	3 months ago
Bagatur	678a19a5f7	infra: bump anthropic mypy 1 (#22373 )	3 months ago
Nuno Campos	ceb73ad06f	core: In BaseRetriever make get_relevant_docs delegate to invoke (#22434 ) - This fixes all the tracing issues with people still using get_relevant_docs, and a change we need for 0.3 anyway Thank you for contributing to LangChain! - [ ] PR title: "package: description" - 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: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.	3 months ago
Charles John	2d81a72884	community: fix missing `apify_api_token` field in ApifyWrapper (#22421 ) - Description: The `ApifyWrapper` class expects `apify_api_token` to be passed as a named parameter or set as an environment variable. But the corresponding field was missing in the class definition causing the argument to be ignored when passed as a named param. This patch fixes that.	3 months ago
Joan Fontanals	a7ae16f912	add `embed_image` API to JinaEmbedding (#22416 ) - Description: Add `embed_image` to JinaEmbedding to embed images - Twitter handle: https://x.com/JinaAI_	3 months ago
Nuno Campos	ed8e9c437a	core: In RunnableSequence pass kwargs to the first step (#22393 ) - This is a pattern that shows up occasionally in langgraph questions, people chain a graph to something else after, and want to pass the graph some kwargs (eg. stream_mode)	3 months ago
Bagatur	a8098f5ddb	anthropic[patch]: Release 0.1.15, fix sdk tools break (#22369 )	4 months ago
Erick Friis	6ffa0acf32	ai21: fix text-splitters version (#22366 )	4 months ago
Bagatur	2b9f1469d8	core[patch]: Release 0.2.3 (#22329 )	4 months ago
Harrison Chase	ee32369265	core[patch]: fix runnable history and add docs (#22283 )	4 months ago
William FH	dcec133b85	[Core] Update Tracing Interops (#22318 ) LangSmith and LangChain context var handling evolved in parallel since originally we didn't expect people to want to interweave the decorator and langchain code. Once we get a new langsmith release, this PR will let you seemlessly hand off between @traceable context and runnable config context so you can arbitrarily nest code. It's expected that this fails right now until we get another release of the SDK	4 months ago
ccurme	f34337447f	openai: update ChatOpenAI api ref (#22324 ) Update to reflect that token usage is no longer default in streaming mode. Add detail for streaming context under Token Usage section.	4 months ago
ChengZi	2443e85533	docs: fix milvus import and update template (#22306 ) docs: fix milvus import problem update milvus-rag template with milvus-lite Signed-off-by: ChengZi <chen.zhang@zilliz.com>	4 months ago
WU LIFU	86698b02a9	doc: fix wrong documentation on FAISS load_local function (#22310 ) ### Issue: #22299 ### descriptions The documentation appears to be wrong. When the user actually sets this parameter "asynchronous" to be True, it fails because the __init__ function of FAISS class doesn't allow this parameter. In fact, most of the class/instance functions of this class have both the sync/async version, so it looks like what we need is just to remove this parameter from the doc. Thank you for contributing to LangChain! - [x] PR title: "package: description" - 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" - [x] PR message: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. Co-authored-by: Lifu Wu <lifu@nextbillion.ai>	4 months ago
maang-h	596c062cba	community[patch]: Standardize qianfan model init args name (#22322 ) - Description: - Standardize qianfan chat model intialization arguments name - qianfan_ak (qianfan api key) -> api_key - qianfan_sk (qianfan secret key) -> secret_key - Delete unuse variable - Issue: #20085	4 months ago
Dobiichi-Origami	10b12e1c08	community: adding tool_call_id for every ToolCall (#22323 ) - Description: This PR contains a bugfix which result in malfunction of multi-turn conversation in QianfanChatEndpoint and adaption for ToolCall and ToolMessage	4 months ago
ccurme	f39e1a2288	community, docs: update token usage tracking callback + how-to guides (#22145 )	4 months ago
Bagatur	2bc50fb895	docs, cli[patch]: chat model template nit (#22294 )	4 months ago
Bagatur	aa6c31df53	cli[patch]: Release 0.0.24 (#22293 )	4 months ago
Bagatur	627a337887	docs, cli[patch]: chat model doc template (#22290 ) Update ChatModel integration doc template, integration docstring, and adds langchain-cli command to easily create just doc (for updating existing integrations): ```bash langchain-cli integration create-doc --name "foo-bar" ```	4 months ago
ccurme	6e1df72a88	openai[patch]: Release 0.1.8 (#22291 )	4 months ago
ccurme	e71b0b5827	core[patch]: Release 0.2.2 (#22289 )	4 months ago
Bagatur	6dd0f095c3	docs: revamp ChatOpenAI (#22253 ) Can build API ref docs by running ```bash make api_docs_clean; make api_docs_quick_preview API_PKG=openai ``` only builds openai ref, takes ~20 sec	4 months ago
Erick Friis	00c70d98c2	robocorp: release 0.0.9 (#22282 )	4 months ago
Mikko Korpela	fc5909ad6f	langchain-robocorp: Fix parsing of Union types (such as Optional). (#22277 )	4 months ago
ccurme	af1f723ada	openai: don't override stream_options default (#22242 ) ChatOpenAI supports a kwarg `stream_options` which can take values `{"include_usage": True}` and `{"include_usage": False}`. Setting include_usage to True adds a message chunk to the end of the stream with usage_metadata populated. In this case the final chunk no longer includes `"finish_reason"` in the `response_metadata`. This is the current default and is not yet released. Because this could be disruptive to workflows, here we remove this default. The default will now be consistent with OpenAI's API (see parameter [here](https://platform.openai.com/docs/api-reference/chat/create#chat-create-stream_options)). Examples: ```python from langchain_openai import ChatOpenAI llm = ChatOpenAI() for chunk in llm.stream("hi"): print(chunk) ``` ``` content='' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' content='Hello' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' content='!' id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' content='' response_metadata={'finish_reason': 'stop'} id='run-8cff4721-2acd-4551-9bf7-1911dae46b92' ``` ```python for chunk in llm.stream("hi", stream_options={"include_usage": True}): print(chunk) ``` ``` content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='Hello' id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='!' id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='' response_metadata={'finish_reason': 'stop'} id='run-39ab349b-f954-464d-af6e-72a0927daa27' content='' id='run-39ab349b-f954-464d-af6e-72a0927daa27' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17} ``` ```python llm = ChatOpenAI().bind(stream_options={"include_usage": True}) for chunk in llm.stream("hi"): print(chunk) ``` ``` content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='Hello' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='!' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='' response_metadata={'finish_reason': 'stop'} id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' content='' id='run-59918845-04b2-41a6-8d90-f75fb4506e0d' usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17} ```	4 months ago
Karim Lalani	a1899439fc	[experimental][llms][ollama_functions] Update OllamaFunctions to send `tool_calls` attribute (#21625 ) Update OllamaFunctions to return `tool_calls` for AIMessages when used for tool calling.	4 months ago
Bagatur	d61bdeba25	core[patch]: allow access RunnableWithFallbacks.runnable attrs (#22139 ) RFC, candidate fix for #13095 #22134	4 months ago
SteveLiao	7496fe2b16	Update parent_document_retriever.py about kwargs (#22219 ) Add kwargs in add_documents function langchain: Add kwargs in parent_document_retriever" - Add kwargs for `add_document` in `parent_document_retriever.py` If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.	4 months ago
Erick Friis	93240fac68	milvus: fix core dep (#22239 )	4 months ago
ChengZi	404d92ded0	milvus: New langchain_milvus package and new milvus features (#21077 ) New features: - New langchain_milvus package in partner - Milvus collection hybrid search retriever - Zilliz cloud pipeline retriever - Milvus Local guid - Rag-milvus template --------- Signed-off-by: ChengZi <chen.zhang@zilliz.com> Signed-off-by: Jael Gu <mengjia.gu@zilliz.com> Co-authored-by: Jael Gu <mengjia.gu@zilliz.com> Co-authored-by: Jackson <jacksonxie612@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Erick Friis <erickfriis@gmail.com>	4 months ago
Leonid Ganeline	d6995e814b	ai21[patch]: added `license` (#22153 ) The `pyproject.toml` missed the `license` parameter. I've added it as `MIT`	4 months ago
Maddy Adams	8332a36f69	infra: update langchainhub and add integration test (#22154 ) Description: Update langchainhub integration test dependency and add an integration test for pulling private prompt Dependencies: langchainhub 0.1.16	4 months ago
Will Higgins	83d10df78d	community[patch]: Update firecrawl api key name (#22183 ) Change 'FIREWALL' to 'FIRECRAWL' as I believe this may have been in error. Other docs refer to 'FIRECRAWL_API_KEY'. Thank you for contributing to LangChain! - [ ] PR title: "package: description" - 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: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago
hmasdev	bbd7015b5d	core[patch]: Add `TypeError` handler into `get_graph` of `Runnable` (#19856 ) # Description ## Problem `Runnable.get_graph` fails when `InputType` or `OutputType` property raises `TypeError`. - `003c98e5b4/libs/core/langchain_core/runnables/base.py (L250-L274)` - `003c98e5b4/libs/core/langchain_core/runnables/base.py (L394-L396)` This problem prevents getting a graph of `Runnable` objects whose `InputType` or `OutputType` property raises `TypeError` but whose `invoke` works well, such as `langchain.output_parsers.RegexParser`, which I have already pointed out in #19792 that a `TypeError` would occur. ## Solution - Add `try-except` syntax to handle `TypeError` to the codes which get `input_node` and `output_node`. # Issue - #19801 # Twitter Handle - [hmdev3](https://twitter.com/hmdev3) --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago
Mohammad Mohtashim	577ed68b59	mistralai[patch]: Added Json Mode for ChatMistralAI (#22213 ) - Description: Powered [ChatMistralAI.with_structured_output](`fbfed65fb1/libs/partners/mistralai/langchain_mistralai/chat_models.py (L609)`) via json mode - Issue: #22081 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago
Pavlo Paliychuk	342df7cf83	community[minor]: Add Zep Cloud components + docs + examples (#21671 ) Thank you for contributing to LangChain! - [x] PR title: community: Add Zep Cloud components + docs + examples - [x] PR message: We have recently released our new zep-cloud sdks that are compatible with Zep Cloud (not Zep Open Source). We have also maintained our Cloud version of langchain components (ChatMessageHistory, VectorStore) as part of our sdks. This PRs goal is to port these components to langchain community repo, and close the gap with the existing Zep Open Source components already present in community repo (added ZepCloudMemory,ZepCloudVectorStore,ZepCloudRetriever). Also added a ZepCloudChatMessageHistory components together with an expression language example ported from our repo. We have left the original open source components intact on purpose as to not introduce any breaking changes. - Issue: - - Dependencies: Added optional dependency of our new cloud sdk `zep-cloud` - Twitter handle: @paulpaliychuk51 - [x] Add tests and docs - [x] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.	4 months ago
Jan Soubusta	cccc8fbe2f	community[patch]: DuckDB VS - expose similarity, improve performance of from_texts (#20971 ) 3 fixes of DuckDB vector store: - unify defaults in constructor and from_texts (users no longer have to specify `vector_key`). - include search similarity into output metadata (fixes #20969) - significantly improve performance of `from_documents` Dependencies: added Pandas to speed up `from_documents`. I was thinking about CSV and JSON options, but I expect trouble loading JSON values this way and also CSV and JSON options require storing data to disk. Anyway, the poetry file for langchain-community already contains a dependency on Pandas. --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: ccurme <chester.curme@gmail.com>	4 months ago
Erick Friis	42ffcb2ff1	anthropic: release 0.1.14rc2, test release note gen (#22147 )	4 months ago
Ameya Shenoy	8ba492ed6a	community[minor]: clickhouse -- ability to use secure connection (#22108 ) - Description: this PR gives clickhouse client the ability to use a secure connection to the clickhosue server - Issue: fixes #22082 - Dependencies: - - Twitter handle: `_codingcoffee_` Signed-off-by: Ameya Shenoy <shenoy.ameya@gmail.com> Co-authored-by: Shresth Rana <shresth@grapevine.in>	4 months ago
ccurme	9a010fb761	openai: read stream_options (#21548 ) OpenAI recently added a `stream_options` parameter to its chat completions API (see [release notes](https://platform.openai.com/docs/changelog/added-chat-completions-stream-usage)). When this parameter is set to `{"usage": True}`, an extra "empty" message is added to the end of a stream containing token usage. Here we propagate token usage to `AIMessage.usage_metadata`. We enable this feature by default. Streams would now include an extra chunk at the end, after the chunk with `response_metadata={'finish_reason': 'stop'}`. New behavior: ``` [AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'), AIMessageChunk(content='Hello', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'), AIMessageChunk(content='!', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'), AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde'), AIMessageChunk(content='', id='run-4b20dbe0-3817-4f62-b89d-03ef76f25bde', usage_metadata={'input_tokens': 8, 'output_tokens': 9, 'total_tokens': 17})] ``` Old behavior (accessible by passing `stream_options={"include_usage": False}` into (a)stream: ``` [AIMessageChunk(content='', id='run-1312b971-c5ea-4d92-9015-e6604535f339'), AIMessageChunk(content='Hello', id='run-1312b971-c5ea-4d92-9015-e6604535f339'), AIMessageChunk(content='!', id='run-1312b971-c5ea-4d92-9015-e6604535f339'), AIMessageChunk(content='', response_metadata={'finish_reason': 'stop'}, id='run-1312b971-c5ea-4d92-9015-e6604535f339')] ``` From what I can tell this is not yet implemented in Azure, so we enable only for ChatOpenAI.	4 months ago
Rahul Triptahi	1a485f59b9	community[patch]: Put authorized identities behind a feature flag in SharepointLoader (#22125 ) Description: Put authorised identities behind a feature flag, load_auth. Documentation: N/A Unit tests: N/A --------- Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com> Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>	4 months ago
sasha	1c9ceff503	community: add metadata to chain logging; (#22122 ) Hey, I'm Sasha. The SDK engineer from [Comet](https://comet.com). This PR updates the CometTracer class. Added metadata to CometTracerr. From now on, both chains and spans will send it.	4 months ago
Jirka Lhotka	7c0459faf2	community: Update costs of openai finetuned models (#22124 ) - Description: Update costs of finetuned models and add gpt-3-turbo-0125. Source: https://openai.com/api/pricing/ - Issue: N/A - Dependencies: None	4 months ago
Eugene Yurtsev	d3db83abe3	community[major]: lint for usage of xml library (#22132 ) * Lint for usage of standard xml library * Add forced opt-in for quip client * Actual security issue is with underlying QuipClient not LangChain integration (since the client is doing the parsing), but adding enforcement at the LangChain level.	4 months ago
Bagatur	baa3c975cb	anthropic[patch]: allow tool call mutation (#22130 ) If tool_use blocks and tool_calls with overlapping IDs are present, prefer the values of the tool_calls. Allows for mutating AIMessages just via tool_calls.	4 months ago
Christophe Bornet	c838de5027	doc: Add doc for CassandraByteStore (#22126 ) Preview: https://langchain-git-fork-cbornet-doc-cassandrabytestore-langchain.vercel.app/v0.2/docs/integrations/stores/cassandra/	4 months ago
ccurme	0ea1e89b2c	groq: read tool calls from .tool_calls attribute (#22096 )	4 months ago
Eugene Yurtsev	2d693c484e	docs: fix some spelling mistakes caught by newest version of code spell (#22090 ) Going to merge this even though it doesn't pass all tests, and open a separate PR for the remaining spelling mistakes.	4 months ago
Pavel Zloi	fe26f937e4	community[minor]: ManticoreSearch engine added to vectorstore (#19117 ) Description: ManticoreSearch engine added to vectorstores Issue: no issue, just a new feature Dependencies: https://pypi.org/project/manticoresearch-dev/ Twitter handle: @EvilFreelancer - Example notebook with test integration: https://github.com/EvilFreelancer/langchain/blob/manticore-search-vectorstore/docs/docs/integrations/vectorstores/manticore_search.ipynb --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Chester Curme <chester.curme@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago
Erick Friis	95c3e5f85f	cli: model name substitution fix, release 0.0.23 (#22089 )	4 months ago
ccurme	152c8cac33	anthropic, openai: cut pre-releases (#22083 )	4 months ago
ccurme	cd07521170	core: bump to 0.2.1rc (#22080 )	4 months ago
ccurme	fbfed65fb1	core, partners: add token usage attribute to AIMessage (#21944 ) ```python class UsageMetadata(TypedDict): """Usage metadata for a message, such as token counts. Attributes: input_tokens: (int) count of input (or prompt) tokens output_tokens: (int) count of output (or completion) tokens total_tokens: (int) total token count """ input_tokens: int output_tokens: int total_tokens: int ``` ```python class AIMessage(BaseMessage): ... usage_metadata: Optional[UsageMetadata] = None """If provided, token usage information associated with the message.""" ... ```	4 months ago
Bagatur	3d26807b92	community[patch]: Release. 0.2.1 (#22073 )	4 months ago
Bagatur	2d968213d7	langchain[patch]: Release 0.2.1 (#22074 )	4 months ago
maang-h	9aba9e3e33	community[patch]: Update the default “API URL” and “MODEL” of sparkllm (#22070 ) - Description: When I was running the sparkllm, I found that the default parameters currently used could no longer run correctly. - original parameters & values: - spark_api_url: "wss://spark-api.xf-yun.com/v3.1/chat" - spark_llm_domain: "generalv3" ```python # example from langchain_community.chat_models import ChatSparkLLM spark = ChatSparkLLM(spark_app_id="my_app_id", spark_api_key="my_api_key", spark_api_secret="my_api_secret") spark.invoke("hello") ``` ![sparkllm](https://github.com/langchain-ai/langchain/assets/55082429/5369bfdf-4305-496a-bcf5-2d3f59d39414) So I updated them to 3.5 (same as sparkllm official website). After the update, they can be used normally. - new parameters & values: - spark_api_url: "wss://spark-api.xf-yun.com/v3.5/chat" - spark_llm_domain: "generalv3.5"	4 months ago
junkeon	4fda7bf4f2	upstage[patch] : fix error handling in Layout Analysis parser (#22054 ) This pull request addresses and fixes exception handling in the UpstageLayoutAnalysisParser and enhances the test coverage by adding error exception tests for the document loader. These improvements ensure robust error handling and increase the reliability of the system when dealing with external API calls and JSON responses. ### Changes Made 1. Fix Request Exception Handling: - Issue: The existing implementation of UpstageLayoutAnalysisParser did not properly handle exceptions thrown by the requests library, which could lead to unhandled exceptions and potential crashes. - Solution: Added comprehensive exception handling for requests.RequestException to catch any request-related errors. This includes logging the error details and raising a ValueError with a meaningful error message. 2. Add Error Exception Tests for Document Loader: - New Tests: Introduced new test cases to verify the robustness of the UpstageLayoutAnalysisLoader against various error scenarios. The tests ensure that the loader gracefully handles: - RequestException: Simulates network issues or invalid API requests to ensure appropriate error handling and user feedback. - JSONDecodeError: Simulates scenarios where the API response is not a valid JSON, ensuring the system does not crash and provides clear error messaging.	4 months ago
JuHyung Son	d9eff44400	partner-upstage[patch]: embeddings empty list bug (#22057 ) Fixed an error in `embed_documents` when the input was given as an empty list. And I have revised the document.	4 months ago
Martin Triska	2df8ac402a	community[minor]: Added propagation of document metadata from O365BaseLoader (#20663 ) Description: - Added propagation of document metadata from O365BaseLoader to FileSystemBlobLoader (O365BaseLoader uses FileSystemBlobLoader under the hood). - This is done by passing dictionary `metadata_dict`: key=filename and value=dictionary containing document's metadata - Modified `FileSystemBlobLoader` to accept the `metadata_dict`, use `mimetype` from it (if available) and pass metadata further into blob loader. Issue: - `O365BaseLoader` under the hood downloads documents to temp folder and then uses `FileSystemBlobLoader` on it. - However metadata about the document in question is lost in this process. In particular: - `mime_type`: `FileSystemBlobLoader` guesses `mime_type` from the file extension, but that does not work 100% of the time. - `web_url`: this is useful to keep around since in RAG LLM we might want to provide link to the source document. In order to work well with document parsers, we pass the `web_url` as `source` (`web_url` is ignored by parsers, `source` is preserved) Dependencies: None Twitter handle: @martintriska1 Please review @baskaryan --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	4 months ago
Eugene Yurtsev	e5541d1da7	community[patch]: Update doc-string in CloudBlobLoader (#22069 ) Update doc-string	4 months ago
Philippe PRADOS	6dd621d636	community[minor]: Add CloudBlobLoader that supports loading data from cloud buckets (#21957 ) Thank you for contributing to LangChain! - [ ] PR title: "Add CloudBlobLoader" - community: Add CloudBlobLoader - [ ] PR message: Add cloud blob loader - Description: Langchain provides several approaches to read different file formats: Specific loaders (`CVSLoader`) or blob-compatible loaders (`FileSystemBlobLoader`). The only implementation proposed for BlobLoader is `FileSystemBlobLoader`. Many projects retrieve files from cloud storage. We propose a new implementation of `BlobLoader` to read files from the three cloud storage systems. The interface is strictly identical to `FileSystemBlobLoader`. The only difference is the constructor, which takes a cloud "url" object such as `s3://my-bucket`, `az://my-bucket`, or `gs://my-bucket`. By streamlining the process, this novel implementation eliminates the requirement to pre-download files from cloud storage to local temporary files (which are seldom removed). The code relies on the [CloudPathLib](https://cloudpathlib.drivendata.org/stable/) library to interpret cloud URLs. This has been added as an optional dependency. ```Python loader = CloudBlobLoader("s3://mybucket/id") for blob in loader.yield_blobs(): print(blob) ``` - [X] Dependencies: CloudPathLib - [X] Twitter handle: pprados - [X] Add tests and docs: Add unit test, but it's easy to convert to integration test, with some files in a cloud storage (see `test_cloud_blob_loader.py`) - [X] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. Hello from Paris @hwchase17. Can you review this PR? --------- Co-authored-by: Eugene Yurtsev <eugene@langchain.dev>	4 months ago
Christophe Bornet	74947ec894	community[minor]: Add Cassandra ByteStore (#22064 )	4 months ago
Christophe Bornet	fea6b99b16	community[minor]: Add async methods to CassandraChatMessageHistory (#21975 )	4 months ago
Sky	12d65f17ff	community[patch]: surrealdb provide functions for MMR (Maximal Marginal Relevance) (#21185 ) This PR contains 4 added functions: - max_marginal_relevance_search_by_vector - amax_marginal_relevance_search_by_vector - max_marginal_relevance_search - amax_marginal_relevance_search I'm no langchain expert, but tried do inspect other vectorstore sources like chroma, to build these functions for SurrealDB. If someone has some changes for me, please let me know. Otherwise I would be happy, if these changes are added to the repository, so that I can use the orignal repo and not my local monkey patched version. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago
Bruno Alvisio	5eabe90494	community[patch]: Adding HEADER to the list of supported locations (#21946 ) Description: adds headers to the list of supported locations when generating the openai function schema	4 months ago
Bagatur	50186da0a1	infra: rm unused # noqa violations (#22049 ) Updating #21137	4 months ago
acho98	45ed5f3f51	community[minor]: Add Clova Embeddings for LangChain Community (#21890 ) - [ ] PR title: "Add Naver ClovaX embedding to LangChain community" - HyperClovaX is a large language model developed by [Naver](https://clova-x.naver.com/welcome). It's a powerful and purpose-trained LLM. - You can visit the embedding service provided by [ClovaX](https://www.ncloud.com/product/aiService/clovaStudio) - You may get CLOVA_EMB_API_KEY, CLOVA_EMB_APIGW_API_KEY, CLOVA_EMB_APP_ID From https://www.ncloud.com/product/aiService/clovaStudio --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago
arpitkumar980	444c2a3d9f	community[patch]: sharepoint loader identity enabled (#21176 ) Thank you for contributing to LangChain! - [ ] PR title: "package: description" - 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: *Delete this entire checklist* and replace with - Description: a description of the change - Issue: the issue # it fixes, if applicable - Dependencies: any dependencies required for this change - Twitter handle: if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [ ] Add tests and docs: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [ ] Lint and test: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines:https://github.com/arpitkumar980/langchain.git - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. - If you are adding something to community, do not re-import it in langchain. If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	4 months ago
HuiyuanYan	bf3aefce93	community[patch]: Update tongyi.py to support MultimodalConversation in dashscope. (#21249 ) Add the support of multimodal conversation in dashscope,now we can use multimodal language model "qwen-vl-v1", "qwen-vl-chat-v1", "qwen-audio-turbo" to processing picture an audio. :) - [ ] PR title: "community: add multimodal conversation support in dashscope" - [ ] PR message: *Delete this entire checklist* and replace with - Description: add multimodal conversation support in dashscope - Issue: - Dependencies: dashscope≥1.18.0 - Twitter handle: none :) - [ ] How to use it?: - ```python Tongyi_chat = ChatTongyi( top_p=0.5, dashscope_api_key=api_key, model="qwen-vl-v1" ) response= Tongyi_chat.invoke( input = [ { "role": "user", "content": [ {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"}, {"text": "这是什么?"} ] } ] ) ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago

... 2 3 4 5 6 ...

4648 Commits (9ac302cb97cbf9392ab8c37309873b069e277176)