3049 Commits (c53aa5cd37da7a2b6c6630097b813064247c460c)

Author	SHA1	Message	Date
Bagatur	c53aa5cd37	core[patch]: support JS message serial namespaces (#18151)	4 months ago
Max Jakob	5ab69f907f	partners: add Elasticsearch package (#17467) ... ### Description This PR moves the Elasticsearch classes to a partners package. Note that we will not move (and later remove) `ElasticKnnSearch`. It were previously deprecated. `ElasticVectorSearch` is going to stay in the community package since it is used quite a lot still. Also note that I left the `ElasticsearchTranslator` for self query untouched because it resides in main `langchain` package. ### Dependencies There will be another PR that updates the notebooks (potentially pulling them into the partners package) and templates and removes the classes from the community package, see https://github.com/langchain-ai/langchain/pull/17468 #### Open question How to make the transition smooth for users? Do we move the import aliases and require people to install `langchain-elasticsearch`? Or do we remove the import aliases from the `langchain` package all together? What has worked well for other partner packages? --------- Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
matt haigh	a4896da2a0	Experimental: Add other threshold types to SemanticChunker (#16807) ... **Description** Adding different threshold types to the semantic chunker. I’ve had much better and predictable performance when using standard deviations instead of percentiles.  For all the documents I’ve tried, the distribution of distances look similar to the above: positively skewed normal distribution. All skews I’ve seen are less than 1 so that explains why standard deviations perform well, but I’ve included IQR if anyone wants something more robust. Also, using the percentile method backwards, you can declare the number of clusters and use semantic chunking to get an ‘optimal’ splitting. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	4 months ago
Jaskirat Singh	ce682f5a09	community: vectorstores.kdbai - Added support for when no docs are present (#18103) ... - **Description:** By default it expects a list but that's not the case in corner scenarios when there is no document ingested(use case: Bootstrap application). \ Hence added as check, if the instance is panda Dataframe instead of list then it will procced with return immediately. - **Issue:** NA - **Dependencies:** NA - **Twitter handle:** jaskiratsingh1 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	4 months ago
am-kinetica	9b8f6455b1	Langchain vectorstore integration with Kinetica (#18102) ... - **Description:** New vectorstore integration with the Kinetica database - **Issue:** - **Dependencies:** the Kinetica Python API `pip install gpudb==7.2.0.1`, - **Tag maintainer:** @baskaryan, @hwchase17 - **Twitter handle:** --------- Co-authored-by: Chad Juliano <cjuliano@kinetica.com>	4 months ago
Bagatur	1e8ab83d7b	langchain[patch], core[patch], openai[patch], fireworks[minor]: ChatFireworks.with_structured_output (#18078) ... <img width="1192" alt="Screenshot 2024-02-24 at 3 39 39 PM" src="https://github.com/langchain-ai/langchain/assets/22008038/1cf74774-a23f-4b06-9b9b-85dfa2f75b63">	4 months ago
GoodBai	3589a135ef	community: make `SET allow_experimental_[engine]_index` configurabe in vectorstores.clickhouse (#18107) ... ## Description & Issue While following the official doc to use clickhouse as a vectorstore, I found only the default `annoy` index is properly supported. But I want to try another engine `usearch` for `annoy` is not properly supported on ARM platforms. Here is the settings I prefer: ``` python settings = ClickhouseSettings( table="wiki_Ethereum", index_type="usearch", # annoy by default index_param=[], ) ``` The above settings do not work for the command `set allow_experimental_annoy_index=1` is hard-coded. This PR will make sure the experimental feature follow the `index_type` which is also consistent with Clickhouse's naming conventions.	4 months ago
Dan Stambler	69344a0661	community: Add Laser Embedding Integration (#18111) ... - **Description:** Added Integration with Meta AI's LASER Language-Agnostic SEntence Representations embedding library, which supports multilingual embedding for any of the languages listed here: https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200, including several low resource languages - **Dependencies:** laser_encoders	4 months ago
Luan Fernandes	e867557936	[docs] Update doc-string for buffer_as_messages method in ConversationBufferWindowMemory (#18136) ... minor fix stated in #18080	4 months ago
Bagatur	767523f364	core[patch], langchain[patch], templates: move openai functions parsers to core (#18060) ... 	4 months ago
Nuno Campos	cd3ab3703b	Improve runnable generator error messages (#18142) ... h/t @hinthornw 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.	4 months ago
Nuno Campos	62a30efb12	Fix bug with using configurable_fields after configurable_alternatives (#18139) ... Closes #17915	4 months ago
Nuno Campos	b1d9ce541d	Add BaseMessage.id (#17835) ... 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.	4 months ago
Harrison Chase	935aefa8db	add run name for query constructor (#18101) ... Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	4 months ago
Mohammad Mohtashim	719a1cde75	langchain[patch]: Update doc-string for a method in ConversationBufferWindowMemory (#18090) ... A minor doc fix stated in #18080	4 months ago
Simon Schmidt	2716d58603	langchain: Import from langchain_core in langchain.smith to avoid deprecation warning (#18129) ... Avoids deprecation warning that triggered at import time, e.g. with `python -c 'import langchain.smith'` /opt/venv/lib/python3.12/site-packages/langchain/callbacks/__init__.py:37: LangChainDeprecationWarning: Importing this callback from langchain is deprecated. Importing it from langchain will no longer be supported as of langchain==0.2.0. Please import from langchain-community instead: `from langchain_community.callbacks import base`. To install langchain-community run `pip install -U langchain-community`.	4 months ago
Erick Friis	248c5b84ee	google-genai, google-vertexai: move to langchain-google (#17899) ... These packages have moved to https://github.com/langchain-ai/langchain-google Left tombstone readmes incase anyone ends up at the "Source Code" link from old pypi releases. Can keep these around for a few months.	4 months ago
Erick Friis	3b5bdbfee8	anthropic[minor]: package move (#17974)	4 months ago
Christophe Bornet	a2d5fa7649	community[patch]: Fix GenericRequestsWrapper _aget_resp_content must be async (#18065) ... There are existing tests in `libs/community/tests/unit_tests/tools/requests/test_tool.py`	4 months ago
Neli Hateva	a01e8473f8	community[patch]: Fix GraphSparqlQAChain so that it works with Ontotext GraphDB (#15009) ... - **Description:** Introduce a new parameter `graph_kwargs` to `RdfGraph` - parameters used to initialize the `rdflib.Graph` if `query_endpoint` is set. Also, do not set `rdflib.graph.DATASET_DEFAULT_GRAPH_ID` as default value for the `rdflib.Graph` `identifier` if `query_endpoint` is set. - **Issue:** N/A - **Dependencies:** N/A - **Twitter handle:** N/A	4 months ago
Christophe Bornet	4d6cd5b46a	astradb[patch]: Use astrapy's upsert_one method in AstraDBStore (#18063) ... As `upsert` is deprecated	4 months ago
Danny McAteer	e42110f720	docs: Additional examples for partners/exa README (#18081) ... **Description:** Add additional examples for other modules to partners/exa README **Issue:** #17545 **Dependencies:** None **Twitter handle:** @DannyMcAteer8 --------- Co-authored-by: Daniel McAteer <danielmcateer@Daniels-MBP.attlocal.net> Co-authored-by: Daniel McAteer <danielmcateer@Daniels-MacBook-Pro.local>	4 months ago
dokato	5afb242161	langchain[patch]: Make BooleanOutputParser more robust to non-binary responses (#17810) ... - **Description:** I encountered this error when I tried to use LLMChainFilter. Even if the message slightly differs, like `Not relevant (NO)` this results in an error. It has been reported already here: https://github.com/langchain-ai/langchain/issues/. This change hopefully makes it more robust. - **Issue:** #11408 - **Dependencies:** No - **Twitter handle:** dokatox	4 months ago
kYLe	17ecf6e119	community[patch]: Remove model limitation on Anyscale LLM (#17662) ... **Description:** Llama Guard is deprecated from Anyscale public endpoint. **Issue:** Change the default model. and remove the limitation of only use Llama Guard with Anyscale LLMs Anyscale LLM can also works with all other Chat model hosted on Anyscale. Also added `async_client` for Anyscale LLM	4 months ago
Barun Amalkumar Halder	cc69976860	community[minor] : adds callback handler for Fiddler AI (#17708) ... **Description:** Callback handler to integrate fiddler with langchain. This PR adds the following - 1. `FiddlerCallbackHandler` implementation into langchain/community 2. Example notebook `fiddler.ipynb` for usage documentation [Internal Tracker : FDL-14305] **Issue:** NA **Dependencies:** - Installation of langchain-community is unaffected. - Usage of FiddlerCallbackHandler requires installation of latest fiddler-client (2.5+) **Twitter handle:** @fiddlerlabs @behalder Co-authored-by: Barun Halder <barun@fiddler.ai>	4 months ago
Christophe Bornet	b8b5ce0c8c	astradb: Add AstraDBChatMessageHistory to langchain-astradb package (#17732) ... Co-authored-by: Bagatur <baskaryan@gmail.com>	4 months ago
Maxime Perrin	c06a8732aa	community[patch]: fix llama index imports and fields access (#17870) ... - **Description:** Fixing outdated imports after v0.10 llama index update and updating metadata and source text access - **Issue:** #17860 - **Twitter handle:** @maximeperrin_ --------- Co-authored-by: Maxime Perrin <mperrin@doing.fr>	4 months ago
2jimoo	7fc903464a	community: Add document manager and mongo document manager (#17320) ... - **Description:** - Add DocumentManager class, which is a nosql record manager. - In order to use index and aindex in libs/langchain/langchain/indexes/_api.py, DocumentManager inherits RecordManager. - Also I added the MongoDB implementation of Document Manager too. - **Dependencies:** pymongo, motor <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. Replace this entire comment with: - **Description:** Add DocumentManager class, which is a no sql record manager. To use index method and aindex method in indexes._api.py, Document Manager inherits RecordManager.Add the MongoDB implementation of Document Manager. - **Dependencies:** pymongo, motor Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ 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. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	4 months ago
Leonid Ganeline	3f6bf852ea	experimental: docstrings update (#18048) ... Added missed docstrings. Formatted docsctrings to the consistent format.	4 months ago
kYLe	56b955fc31	community[minor]: Add async_client for Anyscale Chat model (#18050) ... Add `async_client` for Anyscale Chat_model	4 months ago
Eugene Yurtsev	68527b809d	core[patch]: Runnable with message history to use add_messages (#17958) ... This PR updates RunnableWithMessageHistory to use add_messages which will save on round-trips for any chat history abstractions that implement the optimization. If the optimization isn't implemented, add_messages automatically invokes add_message serially.	4 months ago
Bagatur	1c1bb1152e	openai[patch]: refactor with_structured_output (#18052) ... - make schema Optional with default val None, since in json_mode you don't need it if not parsing to pydantic - change return_type -> include_raw - expand docstring examples	4 months ago
Erick Friis	a05fb19f42	openai[patch]: remove numpy dep (#18034)	4 months ago
Danny McAteer	e8be34f8c7	exa[patch]: update readme (#18047)	4 months ago
Yufei (Benny) Chen	ee6a773456	fireworks[patch]: Add Fireworks partner packages (#17694) ... --------- Co-authored-by: Erick Friis <erick@langchain.dev>	4 months ago
Bagatur	22b964f802	community[patch]: Release 0.0.24 (#18038)	5 months ago
Erick Friis	29e0445490	community[patch]: BaseLLM typing in init (#18029)	5 months ago
Nicolò Boschi	4c132b4cc6	community: fix openai streaming throws 'AIMessageChunk' object has no attribute 'text' (#18006) ... After upgrading langchain-community to 0.0.22, it's not possible to use openai from the community package with streaming=True ``` File "/home/runner/work/ragstack-ai/ragstack-ai/ragstack-e2e-tests/.tox/langchain/lib/python3.11/site-packages/langchain_community/chat_models/openai.py", line 434, in _generate return generate_from_stream(stream_iter) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/runner/work/ragstack-ai/ragstack-ai/ragstack-e2e-tests/.tox/langchain/lib/python3.11/site-packages/langchain_core/language_models/chat_models.py", line 65, in generate_from_stream for chunk in stream: File "/home/runner/work/ragstack-ai/ragstack-ai/ragstack-e2e-tests/.tox/langchain/lib/python3.11/site-packages/langchain_community/chat_models/openai.py", line 418, in _stream run_manager.on_llm_new_token(chunk.text, chunk=cg_chunk) ^^^^^^^^^^ AttributeError: 'AIMessageChunk' object has no attribute 'text' ``` Fix regression of https://github.com/langchain-ai/langchain/pull/17907 **Twitter handle:** @nicoloboschi	5 months ago
Bagatur	9b982b2aba	community[patch]: Release 0.0.23 (#18027)	5 months ago
Guangdong Liu	4197efd67a	community: Fix SparkLLM error (#18015) ... 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" - **Description:** fix SparkLLM error - **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!	5 months ago
Bagatur	d9e6ca2279	lanchain[patch]: Release 0.1.9 (#17999)	5 months ago
Bagatur	b46d6b04e1	community[patch]: Release 0.0.22 (#17994)	5 months ago
Bagatur	cc0290fdf3	openai[patch]: Release 0.0.7 (#17993)	5 months ago
Bagatur	e045655657	core[patch]: Release 0.1.26 (#17990)	5 months ago
Reid Falconer	0534ba5a7d	langchain[patch]: return formatted SPARQL query on demand (#11263) ... - **Description:** Added the `return_sparql_query` feature to the `GraphSparqlQAChain` class, allowing users to get the formatted SPARQL query along with the chain's result. - **Issue:** NA - **Dependencies:** None Note: I've ensured that the PR passes linting and testing by running make format, make lint, and make test locally. I have added a test for the integration (which relies on network access) and I have added an example to the notebook showing its use.	5 months ago
Leo Diegues	b15fccbb99	community[patch]: Skip `OpenAIWhisperParser` extremely small audio chunks to avoid api error (#11450) ... **Description** This PR addresses a rare issue in `OpenAIWhisperParser` that causes it to crash when processing an audio file with a duration very close to the class's chunk size threshold of 20 minutes. **Issue** #11449 **Dependencies** None **Tag maintainer** @agola11 @eyurtsev **Twitter handle** leonardodiegues --------- Co-authored-by: Leonardo Diegues <leonardo.diegues@grupofolha.com.br> Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago
Jorge Villegas	f6a98032e4	docs: langchain-anthropic README updates (#17684) ... # PR Message - **Description:** This PR adds a README file for the Anthropic API in the `libs/partners` folder of this repository. The README includes: - A brief description of the Anthropic package - Installation & API instructions - Usage examples - **Issue:** [17545](https://github.com/langchain-ai/langchain/issues/17545) - **Dependencies:** None Additional notes: This change only affects the docs package and does not introduce any new dependencies. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago
mackong	9678797625	community[patch]: callback before yield for _stream/_astream (#17907) ... - Description: callback on_llm_new_token before yield chunk for _stream/_astream for some chat models, make all chat models in a consistent behaviour. - Issue: N/A - Dependencies: N/A	5 months ago
Chad Juliano	50ba3c68bb	community[minor]: add Kinetica LLM wrapper (#17879) ... **Description:** Initial pull request for Kinetica LLM wrapper **Issue:** N/A **Dependencies:** No new dependencies for unit tests. Integration tests require gpudb, typeguard, and faker **Twitter handle:** @chad_juliano Note: There is another pull request for Kinetica vectorstore. Ultimately we would like to make a partner package but we are starting with a community contribution.	5 months ago
Erick Friis	ed789be8f4	docs, templates: update schema imports to core (#17885) ... - chat models, messages - documents - agentaction/finish - baseretriever,document - stroutputparser - more messages - basemessage - format_document - baseoutputparser --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	5 months ago