5681 Commits (658a3a86072c7cdb577d6f6ad3fcd69922f5bbe5)

 

All Branches   

Search

Author	SHA1	Message	Date
Bagatur	658a3a8607	FEAT: Merge TileDB vecstore (#12811)	11 months ago
Akio Nishimura	c04647bb4e	Correct number of elements in config list in `batch()` and `abatch()` of `BaseLLM` (#12713) ... - **Description:** Correct number of elements in config list in `batch()` and `abatch()` of `BaseLLM` in case `max_concurrency` is not None. - **Issue:** #12643 - **Twitter handle:** @akionux --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago
James Braza	88b506b321	Adds missing `urllib.parse` for IDE warning of `PubMedAPIWrapper` (#12808) ... Resolves an IDE (PyCharm 2023.2.3 PE) warning around `urllib.parse.quote`, also enabling CTRL-click	11 months ago
Bagatur	a2bb0dd445	TileDB update import unit tests	11 months ago
Nikos Papailiou	2fdaa1e5fd	Add TileDB vectorstore implementation (#12624) ... - **Description:** Add [TileDB](https://tiledb.com) vectorstore implementation. TileDB offers ANN search capabilities using the [TileDB-Vector-Search](https://github.com/TileDB-Inc/TileDB-Vector-Search) module. It provides serverless execution of ANN queries and storage of vector indexes both on local disk and cloud object stores (i.e. AWS S3). More details in: - [Why TileDB as a Vector Database](https://tiledb.com/blog/why-tiledb-as-a-vector-database) - [TileDB 101: Vector Search](https://tiledb.com/blog/tiledb-101-vector-search) - **Twitter handle:** @tiledb	11 months ago
盐粒 Yanli	1b233798a0	feat: Supprt pgvecto.rs as a VectorStore (#12718) ... Supprt [pgvecto.rs](https://github.com/tensorchord/pgvecto.rs) as a new VectorStore type. This introduces a new dependency [pgvecto_rs](https://pypi.org/project/pgvecto_rs/) and upgrade SQLAlchemy to ^2. Relate to https://github.com/tensorchord/pgvecto.rs/issues/11 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago
Daniel Chalef	0cbdba6a9b	zep: VectorStore: Use Native MMR (#12690) ... - refactor to use Zep's native MMR; update example - @baskaryan @eyurtsev	11 months ago
Daniel Chalef	cc3d3920e3	Zep: Summary Search and Example (#12686) ... Zep now has the ability to search over chat history summaries. This PR adds support for doing so. More here: https://blog.getzep.com/zep-v0-17/ @baskaryan @eyurtsev	11 months ago
Bagatur	526313002c	add import tests to all modules (#12806)	11 months ago
Harrison Chase	6609a6033f	fix vectorstore imports (#12804) ... Co-authored-by: Bagatur <baskaryan@gmail.com>	11 months ago
Nuno Campos	f66a9d2adf	Automatically add configurable key to config_schema if config_specs i… (#12798) ... …s present <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes (if applicable), - **Dependencies:** any dependencies required for this change, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	11 months ago
Praveen Venkateswaran	21eeba075c	enable the device_map parameter in huggingface pipeline (#12731) ... ### Enabling `device_map` in HuggingFacePipeline For multi-gpu settings with large models, the [accelerate](https://huggingface.co/docs/accelerate/usage_guides/big_modeling#using--accelerate) library provides the `device_map` parameter to automatically distribute the model across GPUs / disk. The [Transformers pipeline](3520e37e86/src/transformers/pipelines/__init__.py (L543)) enables users to specify `device` (or) `device_map`, and handles cases (with warnings) when both are specified. However, Langchain's HuggingFacePipeline only supports specifying `device` when calling transformers which limits large models and multi-gpu use-cases. Additionally, the [default value](8bd3ce59cd/libs/langchain/langchain/llms/huggingface_pipeline.py (L72)) of `device` is initialized to `-1` , which is incompatible with the transformers pipeline when `device_map` is specified. This PR addresses the addition of `device_map` as a parameter , and solves the incompatibility of `device = -1` when `device_map` is also specified. An additional test has been added for this feature. Additionally, some existing tests no longer work since 1. `max_new_tokens` has to be specified under `pipeline_kwargs` and not `model_kwargs` 2. The GPT2 tokenizer raises a `ValueError: Pipeline with tokenizer without pad_token cannot do batching`, since the `tokenizer.pad_token` is `None` ([related issue](https://github.com/huggingface/transformers/issues/19853) on the transformers repo). This PR handles fixing these tests as well. Co-authored-by: Praveen Venkateswaran <praveen.venkateswaran@ibm.com>	11 months ago
Mark Bell	3276aa3e17	__getattr__ should rase AttributeError not ImportError on missing attributes (#12801) ... [The python spec](https://docs.python.org/3/reference/datamodel.html#object.__getattr__) requires that `__getattr__` throw `AttributeError` for missing attributes but there are several places throwing `ImportError` in the current code base. This causes a specific problem with `hasattr` since it calls `__getattr__` then looks only for `AttributeError` exceptions. At present, calling `hasattr` on any of these modules will raise an unexpected exception that most code will not handle as `hasattr` throwing exceptions is not expected. In our case this is triggered by an exception tracker (Airbrake) that attempts to collect the version of all installed modules with code that looks like: `if hasattr(mod, "__version__"):`. With `HEAD` this is causing our exception tracker to fail on all exceptions. I only changed instances of unknown attributes raising `ImportError` and left instances of known attributes raising `ImportError`. It feels a little weird but doesn't seem to break anything.	11 months ago
Daniel Chalef	d966e4d13a	zep: Update Zep docs and messaging (#12764) ... Update Zep documentation with messaging, more details. @baskaryan, @eyurtsev	11 months ago
Illia	71d1a48b66	Use data from all Google search results in SerpApi.com wrapper (#12770) ... - **Description:** Use all Google search results data in SerpApi.com wrapper instead of the first one only - **Tag maintainer:** @hwchase17 _P.S. `libs/langchain/tests/integration_tests/utilities/test_serpapi.py` are not executed during the `make test`._	11 months ago
ba230t	9214d8e6ed	Fixed a typo in templates/docs/CONTRIBUTING.md (delimeters =>delimiters) (#12774) ... - **Description:** Just fixed a minor typo in templates/docs/CONTRIBUTING.md. - **Issue:** No linked issues. Very small contribution!	11 months ago
Armin Stepanjan	185ddc573e	Fix broken links to use cases (#12777) ... This PR replaces broken links to end to end usecases ([/docs/use_cases](https://python.langchain.com/docs/use_cases)) with a non-broken version ([/docs/use_cases/qa_structured/sql](https://python.langchain.com/docs/use_cases/qa_structured/sql)), consistently with the "Use cases" navigation button at the top of the page. --------- Co-authored-by: Matvey Arye <mat@timescale.com> Co-authored-by: Erick Friis <erick@langchain.dev>	11 months ago
니콜라스	25ee10ed4f	Docs: 'memory' -> 'history' typo. (#12779) ... The 'MessagesPlaceholder' expects 'history' but 'RunnablePassthrough' is assigning 'memory'.	11 months ago
yudai yamamoto	1f7e811156	Fixed broken link in Quickstart page (#12516) ... - **Description:** Corrected a specific link within the documentation. - **Issue:** #12490 - **Dependencies:** - **Tag maintainer:** - **Twitter handle:** --------- Co-authored-by: Erick Friis <erick@langchain.dev>	11 months ago
Ikko Eltociear Ashimine	9b02f7d59c	Update llamacpp.ipynb (#12791) ... HuggingFace -> Hugging Face	11 months ago
Tomaz Bratanic	2a9f40ed28	Add input types to cypher templates (#12800)	11 months ago
Nuno Campos	c4fdf78d03	Fix AddableDict raising exception when used with non-addable values (#12785) ... <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes (if applicable), - **Dependencies:** any dependencies required for this change, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	11 months ago
Erick Friis	49e283a0cd	CLI 0.0.13, Configurable Template Demo (#12796)	11 months ago
Nuno Campos	d1c6ad7769	Fix on_llm_new_token(chunk=) for some chat models (#12784) ... It was passing in message instead of generation <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes (if applicable), - **Dependencies:** any dependencies required for this change, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	11 months ago
Erick Friis	070823f294	CLI 0.0.12 (#12787)	11 months ago
Bagatur	979501c0ca	bump 329 (#12778)	11 months ago
Matvey Arye	9369d6aca0	Fixes to the docs for timescale vector template (#12756)	11 months ago
Lance Martin	33810126bd	Update chat prompt structure in LLaMA SQL cookbook (#12364) ... Co-authored-by: Erick Friis <erick@langchain.dev>	11 months ago
ElliotKetchup	58b90f30b0	Update llama.cpp integration (#11864) ... <!-- - **Description:** removed redondant link, replaced it with Meta's LLaMA repo, add resources for models' hardware requirements, - **Issue:** None, - **Dependencies:** None, - **Tag maintainer:** None, - **Twitter handle:** @ElliotAlladaye -->	11 months ago
Manuel Soria	a228f340f1	Semantic search within postgreSQL using pgvector (#12365) ... Cookbook showing how to incoporate RAG search within a postgreSQL database using pgvector. --------- Co-authored-by: Lance Martin <lance@langchain.dev> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev>	11 months ago
Erick Friis	da821320d3	Fixes 'Nonetype' not iterable for ObsidianLoader (#12751) ... Implements #12726 from @Di3mex	11 months ago
Juan Bustos	67b6f4dc71	Update google_vertex_ai_palm.ipynb (#12715) ... Fixed a typo <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** Fixed a typo on the code - **Issue:** the issue # it fixes (if applicable), Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	11 months ago
Eugene Yurtsev	b1caae62fd	APIChain add restrictions to domains (CVE-2023-32786) (#12747) ... * Restrict the chain to specific domains by default * This is a breaking change, but it will fail loudly upon object instantiation -- so there should be no silent errors for users * Resolves CVE-2023-32786	11 months ago
Erick Friis	4421ba46d7	Demo Server, Fix Timescale (#12746) ... - improve demo server - missing deps	11 months ago
Eugene Yurtsev	0e1aedb9f4	Use jinja2 sandboxing by default (#12733) ... * This is an opt-in feature, so users should be aware of risks if using jinja2. * Regardless we'll add sandboxing by default to jinja2 templates -- this sandboxing is a best effort basis. * Best strategy is still to make sure that jinja2 templates are only loaded from trusted sources.	11 months ago
Erick Friis	ab5309f6f2	template updates (#12736) ... - langchain license - add timescale vector dep to that template	11 months ago
Lance Martin	6406c53089	Update template index w/ Timescale (#12729)	11 months ago
Erick Friis	14340ee7cd	use http.client instead of urllib3 (#12660) ... dep problems with requests cloudflare debugging not worth it with urllib	11 months ago
Bagatur	eee5181b7a	bump 328, exp 37 (#12722)	11 months ago
Erick Friis	3405dbbc64	dash not underscore (#12716) ... template names are auto-populating with the wrong convention (with underscores)	11 months ago
123-fake-st	8bd3ce59cd	PyPDFLoader use url in metadata source if file is a web path (#12092) ... **Description:** Update `langchain.document_loaders.pdf.PyPDFLoader` to store url in metadata (instead of a temporary file path) if user provides a web path to a pdf - **Issue:** Related to #7034; the reporter on that issue submitted a PR updating `PyMuPDFParser` for this behavior, but it has unresolved merge issues as of 20 Oct 2023 #7077 - In addition to `PyPDFLoader` and `PyMuPDFParser`, these other classes in `langchain.document_loaders.pdf` exhibit similar behavior and could benefit from an update: `PyPDFium2Loader`, `PDFMinerLoader`, `PDFMinerPDFasHTMLLoader`, `PDFPlumberLoader` (I'm happy to contribute to some/all of that, including assisting with `PyMuPDFParser`, if my work is agreeable) - The root cause is that the underlying pdf parser classes, e.g. `langchain.document_loaders.parsers.pdf.PyPDFParser`, never receive information about the url; the parsers receive a `langchain.document_loaders.blob_loaders.blob`, which contains the pdf contents and local file path, but not the url - This update passes the web path directly to the parser since it's minimally invasive and doesn't require further changes to maintain existing behavior for local files... bigger picture, I'd consider extending `blob` so that extra information like this can be communicated, but that has much bigger implications on the codebase which I think warrants maintainer input - **Dependencies:** None ```python # old behavior >>> from langchain.document_loaders import PyPDFLoader >>> loader = PyPDFLoader('https://arxiv.org/pdf/1706.03762.pdf') >>> docs = loader.load() >>> docs[0].metadata {'source': '/var/folders/w2/zx77z1cs01s1thx5dhshkd58h3jtrv/T/tmpfgrorsi5/tmp.pdf', 'page': 0} # new behavior >>> from langchain.document_loaders import PyPDFLoader >>> loader = PyPDFLoader('https://arxiv.org/pdf/1706.03762.pdf') >>> docs = loader.load() >>> docs[0].metadata {'source': 'https://arxiv.org/pdf/1706.03762.pdf', 'page': 0} ```	11 months ago
Dave Kwon	b1954aab13	feat: Add page metadata on PDFMinerLoader (#12277) ... - **Description:** #12273 's suggestion PR Like other PDFLoader, loading pdf per each page and giving page metadata. - **Issue:** #12273 - **Twitter handle:** @blue0_0hope --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	11 months ago
Duda Nogueira	7148f3e1fe	Weaviate - Fix schema existence check (#12711) ... This will allow you create the schema beforehand. The check was failing and preventing importing into existing classes. <!-- Thank you for contributing to LangChain! Replace this entire comment with: - **Description:** a description of the change, - **Issue:** the issue # it fixes (if applicable), - **Dependencies:** any dependencies required for this change, - **Tag maintainer:** for a quicker response, tag the relevant maintainer (see below), - **Twitter handle:** we announce bigger features on Twitter. If your PR gets announced, and you'd like a mention, we'll gladly shout you out! Please make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md 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/extras` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	11 months ago
Sayandip	8dbbcf0b6c	Adding a template for Solo Performance Prompting Agent (#12627) ... **Description:** This template creates an agent that transforms a single LLM into a cognitive synergist by engaging in multi-turn self-collaboration with multiple personas. **Tag maintainer:** @hwchase17 --------- Co-authored-by: Sayandip Sarkar <sayandip.sarkar@skypointcloud.com> Co-authored-by: Erick Friis <erick@langchain.dev>	11 months ago
Aidos Kanapyanov	ae63c186af	Mask API key for Anyscale LLM (#12406) ... Description: Add masking of API Key for Anyscale LLM when printed. Issue: #12165 Dependencies: None Tag maintainer: @eyurtsev --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	11 months ago
Predrag Gruevski	5ae51a8a85	Fix typo highlighted by `ruff` autoformatter. (#12691) ... H/t @MichaReiser for spotting it: https://github.com/langchain-ai/langchain/pull/12585/files#r1378253045	11 months ago
Predrag Gruevski	724b92231d	Remove `black` caching config from CI lint workflow. (#12594) ... To merge after #12585 is merged.	11 months ago
Predrag Gruevski	0ea837404a	Only publish to test PyPI from the `_test_release.yml` workflow. (#12668) ... PyPI trusted publishing wants to know which workflow is expected to do the publish. We always want to publish from the same workflow, so we're making `_test_release.yml` the only workflow that publishes to Test PyPI.	11 months ago
Predrag Gruevski	321cd44f13	Use separate jobs for building and publishing test releases. (#12671) ... This follows the principle of least privilege. Our `poetry build` step doesn't need, and shouldn't get, access to our GitHub OIDC capability. This is the same structure as I used in the already-merged PR for refactoring the regular PyPI release workflow: #12578.	11 months ago
Erick Friis	44c8b159b9	properly increment version in cli (#12685) ... Went from 0.0.9 -> 0.0.11 without releasing. Back to 10, then release.	11 months ago