3440 Commits (f1313339ac6f45bcf0afcf572d372c7e3660c0af)

Author	SHA1	Message	Date
Bagatur	d95ea3550e	langchain[patch]: Release 0.1.13 (#19351)	6 months ago
Bagatur	b58b38769d	community[patch]: Release 0.0.29 (#19350)	6 months ago
Bagatur	5d220975fc	core[patch]: Release 0.1.33 (#19348)	6 months ago
Eugene Yurtsev	aa9ccca775	langchain[patch]: Add tests for indexing (#19342) ... This PR adds tests for the indexing API	6 months ago
William FH	68298cdc82	[Feat] Accept non-dict if only 1 prompt input variable (#19156) ... For prompt templates with only 1 variable (common in e.g., MessageGraph), it's convenient to wrap the incoming object in the variable before formatting. The downside of this, of course, would be that some number of invocations will successfully format when the user may have intended to format it properly before	6 months ago
mackong	d9396bdec1	langchain[patch]: add stop for various non-openai agents (#19333) ... * Description: add stop for various non-openai agents. * Issue: N/A * Dependencies: N/A --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	6 months ago
Yudhajit Sinha	7d216ad1e1	community[patch]: Invoke callback prior to yielding token (titan_takeoff_pro) (#18624) ... ## PR title community[patch]: Invoke callback prior to yielding token ## PR message - Description: Invoke callback prior to yielding token in _stream_ method in llms/titan_takeoff_pro. - Issue: #16913 - Dependencies: None	6 months ago
Yudhajit Sinha	455a74486b	community[patch]: Invoke callback prior to yielding token (sparkllm) (#18625) ... ## PR title community[patch]: Invoke callback prior to yielding token ## PR message - Description: Invoke callback prior to yielding token in _stream_ method in llms/sparkllm. - Issue: #16913 - Dependencies: None	6 months ago
Yudhajit Sinha	5ac1860484	community[patch]: Invoke callback prior to yielding token (replicate) (#18626) ... ## PR title community[patch]: Invoke callback prior to yielding token ## PR message - Description: Invoke callback prior to yielding token in _stream_ method in llms/replicate. - Issue: #16913 - Dependencies: None	6 months ago
Yudhajit Sinha	9525e392de	community[patch]: Invoke callback prior to yielding token (pai_eas_endpoint) (#18627) ... ## PR title community[patch]: Invoke callback prior to yielding token ## PR message - Description: Invoke callback prior to yielding token in _stream_ method in llms/pai_eas_endpoint. - Issue: #16913 - Dependencies: None	6 months ago
Yudhajit Sinha	140f06e59a	community[patch]: Invoke callback prior to yielding token (openai) (#18628) ... ## PR title community[patch]: Invoke callback prior to yielding token ## PR message - Description: Invoke callback prior to yielding token in _stream_ method in llms/openai. - Issue: #16913 - Dependencies: None	6 months ago
Yudhajit Sinha	280a914920	community[patch]: Invoke callback prior to yielding token (ollama) (#18629) ... ## PR title community[patch]: Invoke callback prior to yielding token ## PR message - Description: Invoke callback prior to yielding token in _stream_ & _astream_ methods in llms/ollama. - Issue: #16913 - Dependencies: None	6 months ago
Christophe Bornet	00614f332a	community[minor]: Add InMemoryVectorStore (#19326) ... This is a basic VectorStore implementation using an in-memory dict to store the documents. It doesn't need any extra/optional dependency as it uses numpy which is already a dependency of langchain. This is useful for quick testing, demos, examples. Also it allows to write vendor-neutral tutorials, guides, etc...	6 months ago
Devesh Rahatekar	3c4529ac69	core: Updated docstring for RunnablePick (#18832) ... **Description:** : Updated the docstring for RunnablePick. Added Overview and an Example for RunnablePick class. **Issue:** : #18803	6 months ago
Leonid Ganeline	8609afbd10	core[patch]: Update `messages` namespace to fix API reference docs (#19161) ... Classes and functions defined in __init__.py are not parsed into the API Reference. For example: - libs/core/langchain_core/messages/__init__.py : AnyMessage, MessageLikeRepresentation, get_buffer_string(), messages_from_dict(), ... Opinionated: __init__.py is not a typical place to define artifacts. Moved artifacts from __init__ into utils.py. Added `MessageLikeRepresentation` to __all__ since it is used outside of `messages`, for example, in `libs/core/langchain_core/language_models/base.py` Added `_message_from_dict` to __all__ since it is used outside of `messages`(???) I would add `message_from_dict` (without underscore) as an alias. Please, advise.	6 months ago
Christophe Bornet	4c2e887276	core: Simplify astream logic in BaseChatModel and BaseLLM (#19332) ... Covered by tests in `libs/core/tests/unit_tests/language_models/chat_models/test_base.py`, `libs/core/tests/unit_tests/language_models/llms/test_base.py` and `libs/core/tests/unit_tests/runnables/test_runnable_events.py`	6 months ago
Erick Friis	69e9610f62	openai[patch]: pass message name (#17537)	6 months ago
Guangdong Liu	e5d7e455dc	splitters: Add ensure_ascii parameter (#18485) ... - **Description:** Add ensure_ascii parameter	6 months ago
Nithish Raghunandanan	7ad0a3f2a7	community: add Couchbase Vector Store (#18994) ... - **Description:** Added support for Couchbase Vector Search to LangChain. - **Dependencies:** couchbase>=4.1.12 - **Twitter handle:** @nithishr --------- Co-authored-by: Nithish Raghunandanan <nithishr@users.noreply.github.com>	6 months ago
Chris Papademetrious	305d74c67a	core: implement a batch_size parameter for CacheBackedEmbeddings (#18070) ... **Description:** Currently, `CacheBackedEmbeddings` computes vectors for *all* uncached documents before updating the store. This pull request updates the embedding computation loop to compute embeddings in batches, updating the store after each batch. I noticed this when I tried `CacheBackedEmbeddings` on our 30k document set and the cache directory hadn't appeared on disk after 30 minutes. The motivation is to minimize compute/data loss when problems occur: * If there is a transient embedding failure (e.g. a network outage at the embedding endpoint triggers an exception), at least the completed vectors are written to the store instead of being discarded. * If there is an issue with the store (e.g. no write permissions), the condition is detected early without computing (and discarding!) all the vectors. **Issue:** Implements enhancement #18026. **Testing:** I was unable to run unit tests; details in [this post](https://github.com/langchain-ai/langchain/discussions/15019#discussioncomment-8576684). --------- Signed-off-by: chrispy <chrispy@synopsys.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	6 months ago
William FH	89af30807b	Permit function eval on llm data type (#19287)	6 months ago
Jib	f8078e41e5	mongodb[patch]: Added scoring threshold to caching (#19286) ... ## Description Semantic Cache can retrieve noisy information if the score threshold for the value is too low. Adding the ability to set a `score_threshold` on cache construction can allow for less noisy scores to appear. - [x] **Add tests and docs** 1. Added tests that confirm the `score_threshold` query is valid. - [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/ --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Christophe Bornet	30e4a35d7a	community: Use langchain-astradb for AstraDB caches (#18419) ... - [x] Needs https://github.com/langchain-ai/langchain-datastax/pull/4 - [x] Needs a new release of langchain-astradb	6 months ago
Guangdong Liu	2c835baae4	code[patch]: Add in code documentation to core Runnable with_retry method (docs only) (#19192) ... - **Description:** Add in code documentation to core Runnable with_retry method (docs only) - **Issue:** #18804 @baskaryan @eyurtsev PTAL --------- Co-authored-by: ccurme <chester.curme@gmail.com>	6 months ago
Eugene Yurtsev	4b3dd34544	core[patch]: Pass sync run manager for sync stream fallback in astream (#19280) ... This PR patches the fallback in chat models and language models to pass in the appropriate version of the run manager (sync vs. async)	6 months ago
Leonid Ganeline	d314acb2d5	core[patch]: Move `globals` to a module instead of a package (non breaking change) (#19159) ... Classes and functions defined in __init__.py are not parsed into the API Reference. For example: libs/core/langchain_core/globals/__init__.py : `set_verbose` `get_llm_cache`, `set_llm_cache`, ... And the whole `langchain_core.globals` namespace is not visible in the API Reference. The refactoring is just file renaming.	6 months ago
Al-Ekram Elahee Hridoy	50f93d86ec	core[minor]: Enhance cache flexibility in BaseChatModel (#17386) ... - **Description:** Enhanced the `BaseChatModel` to support an `Optional[Union[bool, BaseCache]]` type for the `cache` attribute, allowing for both boolean flags and custom cache implementations. Implemented logic within chat model methods to utilize the provided custom cache implementation effectively. This change aims to provide more flexibility in caching strategies for chat models. - **Issue:** Implements enhancement request #17242. - **Dependencies:** No additional dependencies required for this change. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	6 months ago
Zihong	ff31cc1648	experimental: update the notebook link of semantic chunk. (#19253) ... update the notebook link of semantic chunk.	6 months ago
Frederico Wu	f36418a5b0	langchain: creating assistants with file_ids (#19199) ... Changing OpenAIAssistantRunnable.create_assistant to send the `file_ids` parameter to openai.beta.assistants.create Co-authored-by: Frederico Wu <fred.diaswu@coxautoinc.com>	6 months ago
Vittorio Rigamonti	9b2f9ee952	community: VectorStore Infinispan, adding autoconfiguration (#18967) ... **Description**: this PR enable VectorStore autoconfiguration for Infinispan: if metadatas are only of basic types, protobuf config will be automatically generated for the user.	6 months ago
Max Jakob	6f544a6a25	elasticsearch: check for deployed models (#18973) ... When creating a new index, if we use a retrieval strategy that expects a model to be deployed in Elasticsearch, check if a model with this name is indeed deployed before creating an index. This lowers the probability to get into a state in which an index was created with a faulty model ID, which cannot be overwritten any more (the index has to manually be deleted).	6 months ago
gonvee	b82644078e	community: Add `keep_alive` parameter to control how long the model w… (#19005) ... Add `keep_alive` parameter to control how long the model will stay loaded into memory with Ollama。 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Roshan Santhosh	7afecec280	core: update _rm_titles to account for title argument name bug (#19036) ... Issue : For functions which have an argument with the name 'title', the convert_pydantic_to_openai_function generates an incorrect output and omits the argument all together. This is because the _rm_titles function removes all instances of the the key 'title' from the output. Description : Updates the _rm_titles function to check the presence of the 'type' key as well before removing the 'title' key. As the title key that we wish to omit always has a type key along with it. Potential gap if there is a function defined which has both title and key as argument names, in which case this would fail. Maybe we could set a filter on the function argument names and reject those with keyword argument names. No dependencies. Passed all tests. - [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, hwchase17. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	6 months ago
Harrison Chase	efcdf54edd	Josha91 fix docstring (#19249) ... Co-authored-by: Josha van Houdt <josha.van.houdt@sap.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Simon Stone	58c7687174	langchain: preserve document metadata in `FlashrankRerank` (#19148) ... **Description:** Preserves document metadata in `FlashrankRerank` - **Issue:** #19142 - **Dependencies:** None - **Twitter handle:** n/a --------- Co-authored-by: Simon Stone <simon.stone@dartmouth.edu>	6 months ago
Aaron Jimenez	bc648f6cfc	core: Updated docstring for Context class (#19079) ... - **Description:** Improves the docstring for `class Context` by providing an overview and an example. - **Issue:** #18803	6 months ago
Taqi Jaffri	044bc22acc	Community: Add mistral oss model support to azureml endpoints, plus configurable timeout (#19123) ... - **Description:** There was no formatter for mistral models for Azure ML endpoints. Adding that, plus a configurable timeout (it was hard coded before) - **Dependencies:** none - **Twitter handle:** @tjaffri @docugami	6 months ago
Kangmoon Seo	07de4abe70	core: Fix Exception handling in XMLOutputParser (#19126) ... - **Description:** - Exception handling in `XMLOutputParser` 1. Add Exception handling at `root = ET.fromstring(text)` // raises `ET.ParseError` 2. Fix Exception class (commonly uses in `BaseOutputParser` class) - AS-IS: raise `ValueError`, `ET.ParserError` without handling ```python # langchain_core/output_parsers/xml.py text = text.strip() if (text.startswith("<") or text.startswith("\n<")) and ( text.endswith(">") or text.endswith(">\n") ): root = ET.fromstring(text) return self._root_to_dict(root) else: raise ValueError(f"Could not parse output: {text}") ``` - TO-BE: raise `OutputParserException` ```python # langchain_core/output_parsers/xml.py text = text.strip() if (text.startswith("<") or text.startswith("\n<")) and ( text.endswith(">") or text.endswith(">\n") ): try: root = ET.fromstring(text) return self._root_to_dict(root) except ET.ParseError: raise OutputParserException(f"Could not parse output: {text}") else: raise OutputParserException(f"Could not parse output: {text}") ``` - **Issue:** #19107 - **Dependencies:** None	6 months ago
Hamza Muhammad Farooqi	24a0a4472a	Add docstrings for Clickhouse class methods (#19195) ... 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. - [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.	6 months ago
Rohit Gupta	785f8ab174	[langchain_community] milvus vectorstores upsert: add **kwargs to make it use for other argument also (#19193) ... add **kwargs in add_documents for upsert, to make it use for other argument also. Lets use this, it was unused as of now. - [ ] **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, hwchase17. Co-authored-by: Rohit Gupta <rohit.gupta2@walmart.com>	6 months ago
Cycle	77868b1974	experimental: add buffer_size hyperparameter to SemanticChunker as in source video (#19208) ... add buffer_size hyperparameter which used in combine_sentences function	6 months ago
Shotaro Sano	ca9c8c58ea	text-splitters, infra: fix `libs/langchain/dev.Dockerfile` so that the `text-splitter` directory is copied before poetry installation (#19214) ... ## Description This PR modifies the settings in `libs/langchain/dev.Dockerfile` to ensure that the `text-splitters` directory is copied before the poetry installation process begins. Without this modification, the `docker build` command fails for `dev.Dockerfile`, preventing the setup of some development environments, including `.devcontainer`. ## Bug Details ### Repro Run the following command: ```bash docker build -f libs/langchain/dev.Dockerfile . ``` ### Current Behavior The docker build command fails, raising the following error: ``` ... => [langchain-dev-dependencies 4/5] COPY libs/community/ ../community/ 0.4s => ERROR [langchain-dev-dependencies 5/5] RUN poetry install --no-interaction --no-ansi --with dev,test,docs 1.1s ------ > [langchain-dev-dependencies 5/5] RUN poetry install --no-interaction --no-ansi --with dev,test,docs: #13 0.970 #13 0.970 Directory ../text-splitters does not exist ------ executor failed running [/bin/sh -c poetry install --no-interaction --no-ansi --with dev,test,docs]: exit code: 1 ``` ### Expected Behavior The `docker build` command successfully completes without the poetry error. ### Analysis The error occurs because the `text-splitters` directory is not copied into the build environment, unlike the other packages under the `libs` directory. I suspect that the `COPY` setting was overlooked since `text-splitters` was separated in a recent PR. ## Fix Add the following lines to the `libs/langchain/dev.Dockerfile`: ```dockerfile # Copy the text-splitters library for installation COPY libs/text-splitters/ ../text-splitters/ ```	6 months ago
Guangdong Liu	c3310c5e7f	community: Fix Milvus got multiple values for keyword argument 'timeout' (#19232) ... - **Description:** Fix Milvus got multiple values for keyword argument 'timeout' - **Issue:** fix #18580 - @baskaryan @eyurtsev PTAL	6 months ago
Erick Friis	95904fe443	langchain[patch]: update base imports to core (#19248) ... still deprecated, but was misleading before	6 months ago
Asaf Joseph Gardin	21c45475c5	ai21[patch]: AI21 Labs bump SDK version (#19114) ... Description: Added support AI21 SDK version 2.1.2 Twitter handle: https://github.com/AI21Labs --------- Co-authored-by: Asaf Gardin <asafg@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Jib	516cc44b3f	langchain-mongodb: [test-fix] add explicit index_name setting on test vector creation (#19245) ... - **Description:** Tests fail to do value lookup because it does not specify the index name - **Issue:** the issue # Failing integration test - [x] **Add tests and docs**: Tests now pass - [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/	6 months ago
William FH	780337488e	[Enhancement] Add support for directly providing a run_id (#18990) ... The root run id (~trace id's) is useful for assigning feedback, but the current recommended approach is to use callbacks to retrieve it, which has some drawbacks: 1. Doesn't work for streaming until after the first event 2. Doesn't let you call other endpoints with the same trace ID in parallel (since you have to wait until the call is completed/started to use This PR lets you provide = "run_id" in the runnable config. Couple considerations: 1. For batch calls, we split the trace up into separate trees (to permit better rendering). We keep the provided run ID for the first one and generate a unique one for other elements of the batch. 2. For nested calls, the provided ID is ONLY used on the top root/trace. ### Example Usage ``` chain.invoke("foo", {"run_id": uuid.uuid4()}) ```	6 months ago
Jacob Lee	bd329e9aad	core[patch]: Add LLM output to message response_metadata (#19158) ... This will more easily expose token usage information. CC @baskaryan --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Erick Friis	6fa1438334	mongodb[patch]: release 0.1.2 (#19243)	6 months ago
Leonid Ganeline	7de1d9acfd	community: `llms` imports fixes (#18943) ... Classes are missed in __all__ and in different places of __init__.py - BaichuanLLM - ChatDatabricks - ChatMlflow - Llamafile - Mlflow - Together Added classes to __all__. I also sorted __all__ list. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Kenzie Mihardja	21f75991d4	deprecate community docugami loader (#19230) ... Thank you for contributing to LangChain! - [x] **PR title**: "community: deprecate DocugamiLoader" - [x] **PR message**: Deprecate the langchain_community and use the docugami_langchain DocugamiLoader --------- Co-authored-by: Kenzie Mihardja <kenzie28@cs.washington.edu>	6 months ago
Jib	ec026004cb	mongodb[patch]: Remove in-memory cache from cache abstractions (#18987) ... ## Description * In memory cache easily gets out of sync with the server cache, so we will remove it entirely to reduce the issues around invalidated caches. ## Dependencies None - [x] 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/ Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Jib	866d6408af	mongodb[patch]: Remove embedding retrieval from mongodb payload (#19035) ... ## Description Returning the embedding is not necessary in the vector search functionality unless specified as a debugging step. This change defaults the behavior such that the server _only_ returns the embedding key if explicitly requested, such as in the case of `max_marginal_relevance_search`. - [x] **Add tests and docs**: If you're adding a new integration, please include * Added `test_from_documents_no_embedding_return` - [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/ --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Leonid Kuligin	366ba77459	core[minor]: moved fake llms and embeddings to core (#19226) ... - [ ] **PR title**: "core: moved fake llms and embeddings to core" - [ ] **PR message**: - **Description:** moved fake llms and embeddings to core"	6 months ago
Pengfei Jiang	514fe80778	community[patch]: add stop parameter support to volcengine maas (#19052) ... - **Description:** add stop parameter to volcengine maas model - **Dependencies:** no --------- Co-authored-by: 江鹏飞 <jiangpengfei.jiangpf@bytedance.com>	6 months ago
htaoruan	bcc771e37c	docs: ChatTongyi example error (#19013)	6 months ago
primate88	5aa68936e0	community: Fix import path for StreamingStdOutCallbackHandler example (#19170) ... - Description: - Updated the import path for `StreamingStdOutCallbackHandler` in the streaming response example within `huggingface_endpoint.py`. This change corrects the import statement to reflect the actual location of `StreamingStdOutCallbackHandler` in `langchain_core.callbacks.streaming_stdout`. - Issue: - None - Dependencies: - No additional dependencies are required for this change. - Twitter handle: - None ## Note: I have tested this change locally and confirmed that the `StreamingStdOutCallbackHandler` works as expected with the updated import path. This PR does not require the addition of new tests since it is a correction to documentation/examples rather than functional code.	6 months ago
Bagatur	611d5a1618	openai[patch]: fix async http client (#19164) ... Fix #19116	6 months ago
Nikhil Kumar	635b3372bd	community[minor]: Add support for translation in HuggingFacePipeline (#19190) ... - [x] **Support for translation**: "community: Add support for translation in `HuggingFacePipeline`" - [x] **Add support for translation in `HuggingFacePipeline`**: - **Description:** Add support for translation in `HuggingFacePipeline`, which earlier used to support only text summarization and generation. - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** None	6 months ago
Nikhil Kumar	a1b26dd9b6	docs: Add docs for RouterRunnable (#19191) ... - [x] **Docs for `RouterRunnable`**: core: Add docs for `RouterRunnable` - [x] **Add docs for `RouterRunnable`**: - **Description:** Add docs for `RouterRunnable`, which was previously missing documentation - **Issue:** #18803 - **Dependencies:** N/A - **Twitter handle:** None	6 months ago
k.muto	8d2c34e655	community: Fix all page numbers were the same for _BaseGoogleVertexAISearchRetriever (#19175) ... - Description: - This pull request is to fix a bug where page numbers were not set correctly. In the current code, all chunks share the same metadata object doc_metadata, so the page number is set with the same value for all documents. To fix this, I changed to using separate metadata objects for each chunk. - Issue: - None - Dependencies: - No additional dependencies are required for this change. - Twitter handle: - @eycjur - Test - Even if it's not a bug, there are cases where everything ends up with the same number of pages, so it's very difficult for me to write integration tests.	6 months ago
Cailin Wang	7cd87d2f6a	community: Add `partition` parameter to DashVector (#19023) ... **Description**: DashVector Add partition parameter **Twitter handle**: @CailinWang_ --------- Co-authored-by: root <root@Bluedot-AI>	6 months ago
Rodrigo Nogueira	e64cf1aba4	community: Add model argument for maritalk models and better error handling (#19187)	6 months ago
Sergey Kozlov	1a55e950aa	community[patch]: support fastembed v1 and v2 (#19125) ... **Description:** #18040 forces `fastembed>2.0`, and this causes dependency conflicts with the new `unstructured` package (different `onnxruntime`). There may be other dependency conflicts.. The only way to use `langchain-community>=0.0.28` is rollback to `unstructured 0.10.X`. But new `unstructured` contains many fixes. This PR allows to use both `fastembed` `v1` and `v2`. How to reproduce: `pyproject.toml`: ```toml [tool.poetry] name = "depstest" version = "0.0.0" description = "test" authors = ["<dev@example.org>"] [tool.poetry.dependencies] python = ">=3.10,<3.12" langchain-community = "^0.0.28" fastembed = "^0.2.0" unstructured = {extras = ["pdf"], version = "^0.12"} ``` ```bash $ poetry lock ``` Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>	6 months ago
six17	fd4f536c77	text-splitters[patch]: fix json split of RecursiveJsonSplitter (#19119) ... - **Description:** This modification addresses the issue of mutable default parameters in functions. In the original code, the `chunks` parameter is defaulted to a list containing an empty dictionary, which is mutable. Since default parameters in Python are evaluated only once at function definition time, modifications to the parameter would persist across future calls. By changing the default to `None` and checking/initializing within the function, a new list is created for each call, thus avoiding potential issues. --------- Co-authored-by: sixiang <sixiang@lixiang.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
aditya thomas	80eb510a7b	docs: update docstring of Together class (#19008) ... **Description:** Update docstring of Together class to show example and update API URL **Issue:** Improves usability **Dependencies:** None **Lint and test**: `make format`, `make lint` and `make test` were run	6 months ago
高远	ef9813dae6	docs: add vikingdb docstrings(#19016) ... Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>	6 months ago
wulixuan	0e0030f494	community[patch]: fix yuan2 chat model errors while invoke. (#19015) ... 1. fix yuan2 chat model errors while invoke. 2. update related tests. 3. fix some deprecationWarning.	6 months ago
Shuai Liu	c244e1a50b	community[patch]: Fixed bug in merging `generation_info` during chunk concatenation in Tongyi and ChatTongyi (#19014) ... - **Description:** In #16218 , during the `GenerationChunk` and `ChatGenerationChunk` concatenation, the `generation_info` merging changed from simple keys & values replacement to using the util method [`merge_dicts`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py):  The `merge_dicts` method could not handle merging values of `int` or some other types, and would raise a [`TypeError`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/utils/_merge.py#L55). This PR fixes this issue in the **Tongyi and ChatTongyi Model** by adopting the `generation_info` of the last chunk and discarding the `generation_info` of the intermediate chunks, ensuring that `stream` and `astream` function correctly. - **Issue:** - Related issues or PRs about Tongyi & ChatTongyi: #16605, #17105 - Other models or cases: #18441, #17376 - **Dependencies:** No new dependencies	6 months ago
Christophe Bornet	f2a7dda4bd	community[patch]: Use langchain-astradb for AstraDB doc loader (#19071) ... Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Holt Skinner	cee03630d9	community[patch]: Add Blended Search Support to `GoogleVertexAISearchRetriever` (#19082) ... https://cloud.google.com/generative-ai-app-builder/docs/create-data-store-es#multi-data-stores --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Eugene Yurtsev	0ddfe7fc9d	langchain[patch]: make hub work with older langchainhub versions (#19076) ... Make it work with older clients	6 months ago
case-k	ebc4a64f9e	docs: fix databricks document url (#19096) ... Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Guangdong Liu	4468e5bdbe	docs: Add in code documentation to core Runnable with_fallbacks method (docs only) (#19104) ... - Description: [a description of the change] Add in code documentation to core Runnable with_fallbacks method (docs only) - Issue: the issue #18804 @eyurtsev PTAL	6 months ago
Guangdong Liu	cced3eb9bc	community[patch]: Fix sparkllm embeddings api bug. (#19122) ... - **Description:** Fix sparkllm embeddings api bug. @baskaryan PTAL	6 months ago
kaijietti	c20aeef79a	community[patch]: implement qdrant _aembed_query and use it in other async funcs (#19155) ... `amax_marginal_relevance_search ` and `asimilarity_search_with_score ` should use an async version of `_embed_query `.	6 months ago
Barun Amalkumar Halder	34d6f0557d	community[patch] : publishes duration as milliseconds to Fiddler (#19166) ... **Description:** Many LLM steps complete in sub-second duration, which can lead to non-collection of duration field for Fiddler. This PR updates duration from seconds to milliseconds. **Issue:** [INTERNAL] FDL-17568 **Dependencies:** NA **Twitter handle:** behalder Co-authored-by: Barun Halder <barun@fiddler.ai>	6 months ago
Eugene Yurtsev	745d2476a2	langchain: upgrade mypy (#19163) ... Update mypy in langchain	6 months ago
Maxime Perrin	aa785fa6ec	core[minor]: allow LLMs async streaming to fallback on sync streaming (#18960) ... - **Description:** Handling fallbacks when calling async streaming for a LLM that doesn't support it. - **Issue:** #18920 - **Twitter handle:**@maximeperrin_ --------- Co-authored-by: Maxime Perrin <mperrin@doing.fr>	6 months ago
Barun Amalkumar Halder	b551d49cf5	community[patch] : adds feedback and status for Fiddler callback handler events (#19157) ... **Description:** This PR adds updates the fiddler events schema to also pass user feedback, and llm status to fiddler **Tickets:** [INTERNAL] FDL-17559 **Dependencies:** NA **Twitter handle:** behalder Co-authored-by: Barun Halder <barun@fiddler.ai>	6 months ago
Juan Felipe Arias	f5b9aedc48	community[patch]: add args_schema to sql_database tools for langGraph integration (#18595) ... - **Description:** This modification adds pydantic input definition for sql_database tools. This helps for function calling capability in LangGraph. Since actions nodes will usually check for the args_schema attribute on tools, This update should make these tools compatible with it (only implemented on the InfoSQLDatabaseTool) - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** juanfe8881	6 months ago
fengjial	c922ea36cb	community[minor]: Add Baidu VectorDB as vector store (#17997) ... Co-authored-by: fengjialin <fengjialin@MacBook-Pro.local>	6 months ago
Erick Friis	781aee0068	community, langchain, infra: revert store extended test deps outside of poetry (#19153) ... Reverts langchain-ai/langchain#18995 Because it makes installing dependencies in python 3.11 extended testing take 80 minutes	6 months ago
Erick Friis	9e569d85a4	community, langchain, infra: store extended test deps outside of poetry (#18995) ... poetry can't reliably handle resolving the number of optional "extended test" dependencies we have. If we instead just rely on pip to install extended test deps in CI, this isn't an issue.	6 months ago
Bagatur	191ddbc77e	core[patch]: rc release 0.1.33-rc.1 (#19103)	6 months ago
Nuno Campos	508f75853c	core[patch]: Change structured prompt lc id to match js (#19099)	6 months ago
Erick Friis	7ce81eb6f4	voyageai[patch]: init package (#19098) ... Co-authored-by: fodizoltan <zoltan@conway.expert> Co-authored-by: Yujie Qian <thomasq0809@gmail.com> Co-authored-by: fzowl <160063452+fzowl@users.noreply.github.com>	6 months ago
Asaf Joseph Gardin	4d7f6fa968	ai21[patch]: AI21 Labs Batch Support in Embeddings (#18633) ... Description: Added support for batching when using AI21 Embeddings model Twitter handle: https://github.com/AI21Labs --------- Co-authored-by: Asaf Gardin <asafg@ai21.com> Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Erick Friis	d5cf360329	ibm[patch]: release 0.1.3 (#19094)	6 months ago
Mateusz Szewczyk	b15d150d22	ibm[patch]: add async tests, add tokenize support (#18898) ... - **Description:** add async tests, add tokenize support - **Dependencies:** [ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/), - **Tag maintainer:** Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally -> ✅ Please make sure integration_tests passing locally -> ✅ --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
billytrend-cohere	7253b816cc	community: Add support for cohere SDK v5 (keeps v4 backwards compatibility) (#19084) ... - **Description:** Add support for cohere SDK v5 (keeps v4 backwards compatibility) --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Eugene Yurtsev	06165efb5b	core[patch]: RunnablePassthrough transform to autoupgrade to AddableDict (#19051) ... Follow up on https://github.com/langchain-ai/langchain/pull/18743 which missed RunnablePassthrough Issues: https://github.com/langchain-ai/langchain/issues/18741 https://github.com/langchain-ai/langgraph/issues/136 https://github.com/langchain-ai/langserve/issues/504	6 months ago
Eugene Yurtsev	6cdca4355d	community[minor]: Revamp PGVector Filtering (#18992) ... This PR makes the following updates in the pgvector database: 1. Use JSONB field for metadata instead of JSON 2. Update operator syntax to include required `$` prefix before the operators (otherwise there will be name collisions with fields) 3. The change is non-breaking, old functionality is still the default, but it will emit a deprecation warning 4. Previous functionality has bugs associated with comparisons due to casting to text (so lexical ordering is used incorrectly for numeric fields) 5. Adds an a GIN index on the JSONB field for more efficient querying	6 months ago
Guangdong Liu	d4b025c812	code[patch]: Add in code documentation to core Runnable assign method (docs only) (#18951) ... **PR message**: ***Delete this entire checklist*** and replace with - **Description:** [a description of the change](docs: Add in code documentation to core Runnable assign method) - **Issue:** the issue #18804	6 months ago
Bagatur	573f48e34d	core[patch]: Release 0.1.32 (#19088)	6 months ago
YHW	69a8ef2693	core: Runnable pass kwargs to _astream_log_implementation in astream_log (#19055) ... - **Description:** When calling the `_stream_log_implementation` from the `astream_log` method in the `Runnable` class, it is not handing over the `kwargs` argument. Therefore, even if i want to customize APIHandler and implement additional features with additional arguments, it is not possible. Conversely, the `astream_events` method normally handing over the `kwargs` argument. - **Issue:** https://github.com/langchain-ai/langchain/issues/19054 - **Dependencies:** - **Twitter handle:** if your PR gets announced, and you'd like a mention, we'll gladly shout you out! Co-authored-by: hyungwookyang <hyungwookyang@worksmobile.com>	6 months ago
Nuno Campos	751fb7de20	Add new beta StructuredPrompt (#19080) ... 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, hwchase17.	6 months ago
Anton Parkhomenko	ae73b9d839	community[patch]: Fix NotionDBLoader 400 Error by conditionally adding filter parameter (#19075) ... - **Description:** This change fixes a bug where attempts to load data from Notion using the NotionDBLoader resulted in a 400 Bad Request error. The issue was traced to the unconditional addition of an empty 'filter' object in the request payload, which Notion's API does not accept. The modification ensures that the 'filter' object is only included in the payload when it is explicitly provided and not empty, thus preventing the 400 error from occurring. - **Issue:** Fixes [#18009](https://github.com/langchain-ai/langchain/issues/18009) - **Dependencies:** None - **Twitter handle:** @gunnzolder Co-authored-by: Anton Parkhomenko <anton@merge.rocks>	6 months ago
Nuno Campos	2b7c3c548d	core[minor]: Add Runnable.batch_as_completed (#17603) ... This PR adds `batch as completed` method to the standard Runnable interface. It takes in a list of inputs and yields the corresponding outputs as the inputs are completed.	6 months ago
Erick Friis	74b2c0aa01	templates, cli: more security deps (#19006)	6 months ago