langchain

Commit Graph

Author	SHA1	Message	Date
Harrison Chase	aad0a498ac	Harrison/output error (#3094 ) Co-authored-by: yummydum <sumita@nowcast.co.jp>	1 year ago
Harrison Chase	db968284f8	tools refactor (#2961 ) Co-authored-by: vowelparrot <130414180+vowelparrot@users.noreply.github.com>	1 year ago
engkheng	19febc77d6	Support inference of `input_variables` from `jinja2` template (#3013 ) `langchain.prompts.PromptTemplate` is unable to infer `input_variables` from jinja2 template. ```python # Using langchain v0.0.141 template_string = """\ Hello world Your variable: {{ var }} {# This will not get rendered #} {% if verbose %} Congrats! You just turned on verbose mode and got extra messages! {% endif %} """ template = PromptTemplate.from_template(template_string, template_format="jinja2") print(template.input_variables) # Output ['# This will not get rendered #', '% endif %', '% if verbose %'] ``` --------- Co-authored-by: engkheng <ongengkheng929@example.com>	1 year ago
Nuno Campos	dac32c59e5	Nc/combining output parser (#3014 ) Co-authored-by: vowelparrot <130414180+vowelparrot@users.noreply.github.com>	1 year ago
Davis Chase	19c85aa990	Factor out doc formatting and add validation (#3026 ) @cnhhoang850 slightly more generic fix for #2944, works for whatever the expected metadata keys are not just `source`	1 year ago
Naveen Tatikonda	3453b7457c	OpenSearch: Add Support for Boolean Filter with ANN search (#3038 ) ### Description Add Support for Boolean Filter with ANN search Documentation - https://opensearch.org/docs/latest/search-plugins/knn/filter-search-knn/#boolean-filter-with-ann-search ### Issues Resolved https://github.com/hwchase17/langchain/issues/2924 Signed-off-by: Naveen Tatikonda <navtat@amazon.com>	1 year ago
Harrison Chase	afd3e70ae5	Harrison/confluent loader (#2994 ) Co-authored-by: Justin Flick <Justinjayflick@gmail.com>	1 year ago
vowelparrot	99c0382209	Generative Characters (#2859 ) Add a time-weighted memory retriever and a notebook that approximates a Generative Agent from https://arxiv.org/pdf/2304.03442.pdf The "daily plan" components are removed for now since they are less useful without a virtual world, but the memory is an interesting component to build off. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
Jan Backes	a9310a3e8b	Add Annoy as VectorStore (#2939 ) Adds Annoy (https://github.com/spotify/annoy) as vector Store. RESOLVES hwchase17/langchain#2842 discord ref: https://discord.com/channels/1038097195422978059/1051632794427723827/1096089994168377354 --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: vowelparrot <130414180+vowelparrot@users.noreply.github.com>	1 year ago
Harrison Chase	e12e00df12	use output parsers in agents (#2987 )	1 year ago
cs0lar	8b9e02da9d	Fix/issue 1213 (#2932 ) ### Background Continuing to implement all the interface methods defined by the `VectorStore` class. This PR pertains to implementation of the `max_marginal_relevance_search` method. ### Changes - a `max_marginal_relevance_search` method implementation has been added in `weaviate.py` - tests have been added to the the new method - vcr cassettes have been added for the weaviate tests ### Test Plan Added tests for the `max_marginal_relevance_search` implementation ### Change Safety - [x] I have added tests to cover my changes	1 year ago
vowelparrot	5ca7ce77cd	Remove pythonrepl from LLM-MathChain (#2943 ) Use numexpr evaluate instead of the python REPL to avoid malicious code injection. Tested against the (limited) math dataset and got the same score as before. For more permissive tools (like the REPL tool itself), other approaches ought to be provided (some combination of Sanitizer + Restricted python + unprivileged-docker + ...), but for a calculator tool, only mathematical expressions should be permitted. See https://github.com/hwchase17/langchain/issues/814	1 year ago
vowelparrot	4ffc58e07b	Add similarity_search_with_normalized_similarities (#2916 ) Add a method that exposes a similarity search with corresponding normalized similarity scores. Implement only for FAISS now. ### Motivation: Some memory definitions combine `relevance` with other scores, like recency , importance, etc. While many (but not all) of the `VectorStore`'s expose a `similarity_search_with_score` method, they don't all interpret the units of that score (depends on the distance metric and whether or not the the embeddings are normalized). This PR proposes a `similarity_search_with_normalized_similarities` method that lets consumers of the vector store not have to worry about the metric and embedding scale. Most providers default to euclidean distance, with Pinecone being one exception (defaults to cosine _similarity_). --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	1 year ago
dev2049	36aa7f30e4	Move PythonRepl -> langchain.utilities (#2917 )	1 year ago
Davit Buniatyan	b3a5b51728	[minor] Deep Lake auth improvements in docs, kwargs pass, faster tests (#2927 ) Minor cosmetic changes - Activeloop environment cred authentication in notebooks with `getpass.getpass` (instead of CLI which not always works) - much faster tests with Deep Lake pytest mode on - Deep Lake kwargs pass Notes - I put pytest environment creds inside `vectorstores/conftest.py`, but feel free to suggest a better location. For context, if I put in `test_deeplake.py`, `ruff` doesn't let me to set them before import deeplake --------- Co-authored-by: Davit Buniatyan <d@activeloop.ai>	1 year ago
Ankush Gola	ec59e9d886	Fix ChatAnthropic stop_sequences error (#2919 ) (#2920 ) Note to self: Always run integration tests, even on "that last minute change you thought would be safe" :) --------- Co-authored-by: Mike Lambert <mike.lambert@anthropic.com>	1 year ago
Mike Lambert	392f1b3218	Add Anthropic ChatModel to langchain (#2293 ) * Adds an Anthropic ChatModel * Factors out common code in our LLMModel and ChatModel * Supports streaming llm-tokens to the callbacks on a delta basis (until a future V2 API does that for us) * Some fixes	1 year ago
Harrison Chase	1e9378d0a8	Harrison/weaviate fixes (#2872 ) Co-authored-by: cs0lar <cristiano.solarino@gmail.com> Co-authored-by: cs0lar <cristiano.solarino@brightminded.com>	1 year ago
Harrison Chase	705596b46a	Harrison/fix create sql agent (#2870 ) Co-authored-by: Timothé Pearce <timothe.pearce@gmail.com>	1 year ago
sergerdn	04c458a270	feat: improve pinecone tests (#2806 ) Improve the integration tests for Pinecone by adding an `.env.example` file for local testing. Additionally, add some dev dependencies specifically for integration tests. This change also helps me understand how Pinecone deals with certain things, see related issues https://github.com/hwchase17/langchain/issues/2484 https://github.com/hwchase17/langchain/issues/2816	1 year ago
vowelparrot	bf0887c486	Add Slack Directory Loader (#2841 ) Fixes linting issue from #2835 Adds a loader for Slack Exports which can be a very valuable source of knowledge to use for internal QA bots and other use cases. ```py # Export data from your Slack Workspace first. from langchain.document_loaders import SLackDirectoryLoader SLACK_WORKSPACE_URL = "https://awesome.slack.com" loader = ("Slack_Exports", SLACK_WORKSPACE_URL) docs = loader.load() ```	1 year ago
Tim Asp	be4fb24b32	OpenAI LLM: update `modelname_to_contextsize` with new models (#2843 ) Token counts pulled from https://openai.com/pricing	1 year ago
KullTC	802363eb6a	Remove print statement from test (#2809 ) Remove unnecessary print statement.	1 year ago
KullTC	64596b23b9	Return output of PythonAstREPLTool when falling back to exec() (#2780 ) When the code ran by the PythonAstREPLTool contains multiple statements it will fallback to exec() instead of using eval(). With this change, it will also return the output of the code in the same way the PythonREPLTool will.	1 year ago
Harrison Chase	e49f1e628c	Harrison/gpt cache (#2744 ) Co-authored-by: SimFG <bang.fu@zilliz.com>	1 year ago
Joshua Snyder	59d054308c	Add type inference for output parsers (#2769 ) Currently, the output type of a number of OutputParser's `parse` methods is `Any` when it can in fact be inferred. This PR makes BaseOutputParser use a generic type and fixes the output types of the following parsers: - `PydanticOutputParser` - `OutputFixingParser` - `RetryOutputParser` - `RetryWithErrorOutputParser` The output of the `StructuredOutputParser` is corrected from `BaseModel` to `Any` since there are no type guarantees provided by the parser. Fixes issue #2715	1 year ago
Johnny Lee	0ab364404e	add continue to fix 'continue_on_failure' parameter for URL doc loader (#2735 ) Currently, the function still fails if `continue_on_failure` is set to True, because `elements` is not set. --------- Co-authored-by: leecjohnny <johnny-lee1255@users.noreply.github.com>	1 year ago
sergerdn	4bdcedab54	fix: some imports for integration tests (#2612 ) Add more missed imports for integration tests. Bump `pytest` to the current latest version. Fix `tests/integration_tests/vectorstores/test_elasticsearch.py` to update its cassette(easy fix). Related PR: https://github.com/hwchase17/langchain/pull/2560	1 year ago
Ankush Gola	c1521ddbdb	Add workaround for not having async vector store methods (#2733 ) This allows us to use the async API for the Retrieval chains, though it is not guaranteed to be thread safe.	1 year ago
vowelparrot	709f26b69e	Added bilibili loader (#2673 ) (#2724 ) I've added a bilibili loader, bilibili is a very active video site in China and I think we need this loader. Example: ```python from langchain.document_loaders.bilibili import BiliBiliLoader loader = BiliBiliLoader( ["https://www.bilibili.com/video/BV1xt411o7Xu/", "https://www.bilibili.com/video/av330407025/"] ) docs = loader.load() ``` Co-authored-by: 了空 <568250549@qq.com>	1 year ago
Abhik Singla	955bd2e1db	Fixed Ast Python Repl for Chatgpt multiline commands (#2406 ) Resolves issue https://github.com/hwchase17/langchain/issues/2252 --------- Co-authored-by: Abhik Singla <abhiksingla@microsoft.com>	1 year ago
Naveen Tatikonda	4364d3316e	Add custom vector fields and text fields for OpenSearch (#2652 ) Description Add custom vector field name and text field name while indexing and querying for OpenSearch Issues https://github.com/hwchase17/langchain/issues/2500 Signed-off-by: Naveen Tatikonda <navtat@amazon.com>	1 year ago
Ankush Gola	b82cbd1be0	Use `run` and `arun` in place of `combine_docs` and `acombine_docs` (#2635 ) `combine_docs` does not go through the standard chain call path which means that chain callbacks won't be triggered, meaning QA chains won't be traced properly, this fixes that. Also fix several errors in the chat_vector_db notebook	1 year ago
Chetanya Rastogi	50c511d75f	Add new loader to load pdf as html content (#2607 ) Adds a new pdf loader using the existing dependency on PDFMiner. The new loader can be helpful for chunking texts semantically into sections as the output html content can be parsed via `BeautifulSoup` to get more structured and rich information about font size, page numbers, pdf headers/footers, etc. which may not be available otherwise with other pdf loaders	1 year ago
sergerdn	cd9336469e	fix: missed deps integrations tests (#2560 ) Almost all integration tests have failed, but we haven't encountered any import errors yet. Some tests failed due to lazy import issues. It doesn't seem like a problem to resolve some of these errors in the next PR. I have a headache from resolving conflicts with `deeplake` and `boto3`, so I will temporarily comment out `boto3`. fix https://github.com/hwchase17/langchain/issues/2426	1 year ago
sergerdn	6dc86ad48f	feat: add pytest-vcr for recording HTTP interactions in integration tests (#2445 ) Using `pytest-vcr` in integration tests has several benefits. Firstly, it removes the need to mock external services, as VCR records and replays HTTP interactions on the fly. Secondly, it simplifies the integration test setup by eliminating the need to set up and tear down external services in some cases. Finally, it allows for more reliable and deterministic integration tests by ensuring that HTTP interactions are always replayed with the same response. Overall, `pytest-vcr` is a valuable tool for simplifying integration test setup and improving their reliability This commit adds the `pytest-vcr` package as a dependency for integration tests in the `pyproject.toml` file. It also introduces two new fixtures in `tests/integration_tests/conftest.py` files for managing cassette directories and VCR configurations. In addition, the `tests/integration_tests/vectorstores/test_elasticsearch.py` file has been updated to use the `@pytest.mark.vcr` decorator for recording and replaying HTTP interactions. Finally, this commit removes the `documents` fixture from the `test_elasticsearch.py` file and replaces it with a new fixture defined in `tests/integration_tests/vectorstores/conftest.py` that yields a list of documents to use in any other tests. This also includes my second attempt to fix issue : https://github.com/hwchase17/langchain/issues/2386 Maybe related https://github.com/hwchase17/langchain/issues/2484	1 year ago
Vashisht Madhavan	aa439ac2ff	Adding an in-context QA evaluation chain + chain of thought reasoning chain for improved accuracy (#2444 ) Right now, eval chains require an answer for every question. It's cumbersome to collect this ground truth so getting around this issue with 2 things: * Adding a context param in `ContextQAEvalChain` and simply evaluating if the question is answered accurately from context * Adding chain of though explanation prompting to improve the accuracy of this w/o GT. This also gets to feature parity with openai/evals which has the same contextual eval w/o GT. TODO in follow-up: * Better prompt inheritance. No need for seperate prompt for CoT reasoning. How can we merge them together --------- Co-authored-by: Vashisht Madhavan <vashishtmadhavan@Vashs-MacBook-Pro.local>	1 year ago
Alex Rad	bd780a8223	Add support for rwkv (#2422 ) This adds support for running RWKV with pytorch. https://github.com/hwchase17/langchain/issues/2398 This does not yet support rwkv.cpp	1 year ago
William FH	f240651bd8	Add Request body (#2507 ) This still doesn't handle the following - non-JSON media types - anyOf, allOf, oneOf's And doesn't emit the typescript definitions for referred types yet, but that can be saved for a separate PR. Also, we could have better support for Swagger 2.0 specs and OpenAPI 3.0.3 (can use the same lib for the latter) recommend offline conversion for now.	1 year ago
Zach Jones	13d1df2140	Feature: AgentExecutor execution time limit (#2399 ) `AgentExecutor` already has support for limiting the number of iterations. But the amount of time taken for each iteration can vary quite a bit, so it is difficult to place limits on the execution time. This PR adds a new field `max_execution_time` to the `AgentExecutor` model. When called asynchronously, the agent loop is wrapped in an `asyncio.timeout()` context which triggers the early stopping response if the time limit is reached. When called synchronously, the agent loop checks for both the max_iteration limit and the time limit after each iteration. When used asynchronously `max_execution_time` gives really tight control over the max time for an execution chain. When used synchronously, the chain can unfortunately exceed max_execution_time, but it still gives more control than trying to estimate the number of max_iterations needed to cap the execution time. --------- Co-authored-by: Zachary Jones <zjones@zetaglobal.com>	1 year ago
Davit Buniatyan	b4914888a7	Deep Lake upgrade to include attribute search, distance metrics, returning scores and MMR (#2455 ) ### Features include - Metadata based embedding search - Choice of distance metric function (`L2` for Euclidean, `L1` for Nuclear, `max` L-infinity distance, `cos` for cosine similarity, 'dot' for dot product. Defaults to `L2` - Returning scores - Max Marginal Relevance Search - Deleting samples from the dataset ### Notes - Added numerous tests, let me know if you would like to shorten them or make smarter --------- Co-authored-by: Davit Buniatyan <d@activeloop.ai>	1 year ago
leo-gan	fd69cc7e42	Removed duplicate BaseModel dependencies (#2471 ) Removed duplicate BaseModel dependencies in class inheritances. Also, sorted imports by `isort`.	1 year ago
Harrison Chase	1e19e004af	Harrison/openapi spec (#2474 ) Co-authored-by: William Fu-Hinthorn <13333726+hinthornw@users.noreply.github.com>	1 year ago
Harrison Chase	26314d7004	Harrison/openapi parser (#2461 ) Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com>	1 year ago
William FH	007babb363	Add a mock server (#2443 ) It's useful to evaluate API Chains against a mock server. This PR makes an example "robot" server that exposes endpoints for the following: - Path, Query, and Request Body argument passing - GET, PUT, and DELETE endpoints exposed OpenAPI spec. Relies on FastAPI + Uvicorn - I could add to the dev dependencies list if you'd like	1 year ago
sergerdn	b410dc76aa	fix: elasticsearch (#2402 ) - Create a new docker-compose file to start an Elasticsearch instance for integration tests. - Add new tests to `test_elasticsearch.py` to verify Elasticsearch functionality. - Include an optional group `test_integration` in the `pyproject.toml` file. This group should contain dependencies for integration tests and can be installed using the command `poetry install --with test_integration`. Any new dependencies should be added by running `poetry add some_new_deps --group "test_integration" ` Note: New tests running in live mode, which involve end-to-end testing of the OpenAI API. In the future, adding `pytest-vcr` to record and replay all API requests would be a nice feature for testing process.More info: https://pytest-vcr.readthedocs.io/en/latest/ Fixes https://github.com/hwchase17/langchain/issues/2386	1 year ago
Ankush Gola	4d730a9bbc	improve `AsyncCallbackManager` (#2410 )	1 year ago
Harrison Chase	c7b083ab56	bump version to 131 (#2391 )	1 year ago
Harrison Chase	0a9f04bad9	Harrison/gpt4all (#2366 ) Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	1 year ago
Harrison Chase	e90d007db3	Harrison/msg files (#2375 ) Co-authored-by: Sahil Masand <masand.sahil@gmail.com> Co-authored-by: Sahil Masand <masands@cbh.com.au>	1 year ago
Kacper Łukawski	585f60a5aa	Qdrant update to 1.1.1 & docs polishing (#2388 ) This PR updates Qdrant to 1.1.1 and introduces local mode, so there is no need to spin up the Qdrant server. By that occasion, the Qdrant example notebooks also got updated, covering more cases and answering some commonly asked questions. All the Qdrant's integration tests were switched to local mode, so no Docker container is required to launch them.	1 year ago
Harrison Chase	fe1eb8ca5f	requests wrapper (#2367 )	1 year ago
Shrined	10dab053b4	Add Enum for agent types (#2321 ) This pull request adds an enum class for the various types of agents used in the project, located in the `agent_types.py` file. Currently, the project is using hardcoded strings for the initialization of these agents, which can lead to errors and make the code harder to maintain. With the introduction of the new enums, the code will be more readable and less error-prone. The new enum members include: - ZERO_SHOT_REACT_DESCRIPTION - REACT_DOCSTORE - SELF_ASK_WITH_SEARCH - CONVERSATIONAL_REACT_DESCRIPTION - CHAT_ZERO_SHOT_REACT_DESCRIPTION - CHAT_CONVERSATIONAL_REACT_DESCRIPTION In this PR, I have also replaced the hardcoded strings with the appropriate enum members throughout the codebase, ensuring a smooth transition to the new approach.	1 year ago
Harrison Chase	d85f57ef9c	Harrison/llama (#2314 ) Co-authored-by: RJ Adriaansen <adriaansen@eshcc.eur.nl>	1 year ago
akmhmgc	94b2f536f3	Modify output for wikipedia api wrapper (#2287 ) ## Description Thanks for the quick maintenance for great repository!! I modified wikipedia api wrapper ## Details - Add output for missing search results - Add tests	1 year ago
Harrison Chase	acfda4d1d8	Harrison/multiline commands (#2280 ) Co-authored-by: Marc Päpper <mpaepper@users.noreply.github.com>	1 year ago
leo-gan	579ad85785	skip unit tests that fail in Windows (#2238 ) Issue #2174 Several unit tests fail in Windows. Added pytest attribute to skip these tests automatically.	1 year ago
Sam Cordner-Matthews	1ddd6dbf0b	Add ability to pass kwargs to loader classes in `DirectoryLoader`, add ability to modify encoding and BeautifulSoup behaviour in `BSHTMLLoader` (#2275 ) Solves #2247. Noted that the only test I added checks for the BeautifulSoup behaviour change. Happy to add a test for `DirectoryLoader` if deemed necessary.	1 year ago
Harrison Chase	2d3918c152	make requests more general (#2209 )	1 year ago
Harrison Chase	5c907d9998	Harrison/base agent without docs (#2166 )	1 year ago
Harrison Chase	f5a4bf0ce4	remove prep (#2136 ) agents should be stateless or async stuff may not work	1 year ago
Harrison Chase	b35260ed47	Harrison/memory base (#2122 ) @3coins + @zoltan-fedor.... heres the pr + some minor changes i made. thoguhts? can try to get it into tmrws release --------- Co-authored-by: Zoltan Fedor <zoltan.0.fedor@gmail.com> Co-authored-by: Piyush Jain <piyushjain@duck.com>	1 year ago
Ankush Gola	ccee1aedd2	add async support for anthropic (#2114 ) should not be merged in before https://github.com/anthropics/anthropic-sdk-python/pull/11 gets released	1 year ago
Harrison Chase	e2c26909f2	Harrison/memory check (#2119 ) Co-authored-by: JIAQIA <jqq1716@gmail.com>	1 year ago
Harrison Chase	3e879b47c1	Harrison/gitbook (#2044 ) Co-authored-by: Irene López <45119610+ireneisdoomed@users.noreply.github.com>	1 year ago
Honkware	aff33d52c5	Add OpenWeatherMap API Tool (#2083 ) Added tool for OpenWeatherMap API	1 year ago
Charlie Holtz	f16c1fb6df	Add replicate take 2 (#2077 ) This PR adds a replicate integration to langchain. It's an updated version of https://github.com/hwchase17/langchain/pull/1993, but with updates to match latest replicate-python code. https://github.com/replicate/replicate-python. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Zeke Sikelianos <zeke@sikelianos.com>	1 year ago
Harrison Chase	f281033362	rm pandas dependency (#2102 )	1 year ago
Harrison Chase	410bf37fb8	Harrison/big query (#2100 ) Co-authored-by: lu-cashmoney <lucas.corley@gmail.com>	1 year ago
Harrison Chase	eff5eed719	Harrison/jina (#2043 ) Co-authored-by: numb3r3 <wangfelix87@gmail.com> Co-authored-by: felix-wang <35718120+numb3r3@users.noreply.github.com>	1 year ago
Harrison Chase	9e74df2404	Fix issue#1645: Parse llm_output even there's newline (#2092 ) (#2099 ) Fix issue#1645: Parse either whitespace or newline after 'Action Input:' in llm_output in mrkl agent. Unittests added accordingly. Co-authored-by: ₿ingnan.ΞTH <brillliantz@outlook.com>	1 year ago
blob42	b7f392fdd6	[agent_executor] convenience func: lookup tool by name (#2001 ) A quick convenience function to lookup a tool by name Co-authored-by: blob42 <spike@w530>	1 year ago
Harrison Chase	f74a1bebf5	Harrison/duckdb (#2064 ) Co-authored-by: Trent Hauck <trent@trenthauck.com>	1 year ago
Ankush Gola	b7ebb8fe30	enable streaming in anthropic llm wrapper (#2065 )	1 year ago
Harrison Chase	30e3b31b04	Harrison/document cleanup (#2062 ) Co-authored-by: Delip Rao <delip@users.noreply.github.com>	1 year ago
Harrison Chase	a0cd6672aa	Harrison/site map (#2061 ) Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>	1 year ago
Daniel Chalef	6598beacdb	PydanticOutputParser unit test (#2047 ) Unit test for PydanticOutputParser --------- Co-authored-by: Daniel Chalef <daniel.chalef@private.org>	1 year ago
Harrison Chase	705431aecc	big docs refactor (#1978 ) Co-authored-by: Ankush Gola <ankush.gola@gmail.com>	1 year ago
Mario Kostelac	e7d6de6b1c	(ChatOpenAI) Add model_name to LLMResult.llm_output (#1960 ) This makes sure OpenAI and ChatOpenAI have the same llm_output, and allow tracking usage per model. Same work for OpenAI was done in https://github.com/hwchase17/langchain/pull/1713.	1 year ago
Harrison Chase	6e1b5b8f7e	Harrison/figma doc loader (#1908 ) Co-authored-by: Ismail Pelaseyed <homanp@gmail.com>	1 year ago
Eli	12f868b292	Propagate "filter" arg in Chroma similarity_search (#1869 ) Technically a duplicate fix to #1619 but with unit tests and a small documentation update - Propagate `filter` arg in Chroma `similarity_search` to delegated call to `similarity_search_with_score` - Add `filter` arg to `similarity_search_by_vector` - Clarify doc strings on FakeEmbeddings	1 year ago
Maurício Maia	f155d9d3ec	Add metadata filter to PGVector search (#1872 ) Add ability to filter pgvector documents by metadata.	1 year ago
Maurício Maia	2212520a6c	Add PGVector collection metadata (#1887 ) The `CollectionStore` for `PGVector` has a `cmetadata` field but it's never used. This PR add the ability to save metadata information to the collection.	1 year ago
Harrison Chase	ce5d97bcb3	Harrison/guarded output parser (#1804 ) Co-authored-by: jerwelborn <jeremy.welborn@gmail.com>	1 year ago
Matt Tucker	a92344f476	Use regex match for bash process error output test assertion. (#1837 ) I was getting the same issue reported in #1339 by [MacYang555](https://github.com/MacYang555) when running the test suite on my Mac. I implemented the fix they suggested to use a regex match in the output assertion for the scenario under test. Resolves #1339	1 year ago
LeoGrin	3701b2901e	use namespace argument in Pinecone constructor (#1757 ) Fix #1756 Use the `namespace` argument of `Pinecone.from_exisiting_index` to set the default value of `namespace` for other methods. Leads to more expected behavior and easier integration in chains. For the test, I've added a line to delete and rebuild the `langchain-demo` index at the beginning of the test. I'm not 100% sure if it's a good idea but it makes the test reproducible.	1 year ago
Mario Kostelac	aff44d0a98	(OpenAI) Add model_name to LLMResult.llm_output (#1713 ) Given that different models have very different latencies and pricings, it's benefitial to pass the information about the model that generated the response. Such information allows implementing custom callback managers and track usage and price per model. Addresses https://github.com/hwchase17/langchain/issues/1557.	1 year ago
Daniel Chalef	b157e0c1c3	Add HTML document_loader that includes page title metadata (#1720 ) This `BSHTMLLoader` document_loader loads an HTML document, extracts text and adds the page title to the returned Document's metadata. The loader uses the already installed bs4 package to extract both text content and the page title. Included in this PR is an example HTML file and an integration test that tests against this file. --------- Co-authored-by: Daniel Chalef <daniel.chalef@private.org>	1 year ago
Kacper Łukawski	4a327dd1d6	Implement basic metadata filtering in Qdrant (#1689 ) This PR implements a basic metadata filtering mechanism similar to the ones in Chroma and Pinecone. It still cannot express complex conditions, as there are no operators, but some users requested to have that feature available.	1 year ago
Harrison Chase	0b29e68c17	Harrison/pgvector (#1679 ) Co-authored-by: Aman Kumar <krsingh.aman@gmail.com>	1 year ago
Xin Qiu	4e13cef05a	feat: add redisearch vectorstore (#1307 ) # Description Add `RediSearch` vectorstore for LangChain RediSearch: [RediSearch quick start](https://redis.io/docs/stack/search/quick_start/) # How to use ``` from langchain.vectorstores.redisearch import RediSearch rds = RediSearch.from_documents(docs, embeddings,redisearch_url="redis://localhost:6379") ```	1 year ago
Jon Luo	0a1b1806e9	sql: do not hard code the LIMIT clause in the table_info section (#1563 ) Seeing a lot of issues in Discord in which the LLM is not using the correct LIMIT clause for different SQL dialects. ie, it's using `LIMIT` for mssql instead of `TOP`, or instead of `ROWNUM` for Oracle, etc. I think this could be due to us specifying the LIMIT statement in the example rows portion of `table_info`. So the LLM is seeing the `LIMIT` statement used in the prompt. Since we can't specify each dialect's method here, I think it's fine to just replace the `SELECT... LIMIT 3;` statement with `3 rows from table_name table:`, and wrap everything in a block comment directly following the `CREATE` statement. The Rajkumar et al paper wrapped the example rows and `SELECT` statement in a block comment as well anyway. Thoughts @fpingham?	1 year ago
Tim Asp	b3234bf3b0	cleanup: unify 3 different pdf loaders, rename PagedPDFSplitter (#1615 ) `OnlinePDFLoader` and `PagedPDFSplitter` lived separate from the rest of the pdf loaders. Because they're all similar, I propose moving all to `pdy.py` and the same docs/examples page. Additionally, `PagedPDFSplitter` naming doesn't match the pattern the rest of the loaders follow, so I renamed to `PyPDFLoader` and had it inherit from `BasePDFLoader` so it can now load from remote file sources.	1 year ago
Luis	562d9891ea	Add regex dict: (#1616 ) This class enables us to send a dictionary containing an output key and the expected format, which in turn allows us to retrieve the result of the matching formats and extract specific information from it. To exclude irrelevant information from our return dictionary, we can prompt the LLM to use a specific command that notifies us when it doesn't know the answer. We refer to this variable as the "no_update_value". Regarding the updated regular expression pattern (r"{}:\s?([^.'\n']).?"), it enables us to retrieve a format as 'Output Key':'value'. We have improved the regex by adding an optional space between ':' and 'value' with "s?", and by excluding points and line jumps from the matches using "[^.'\n']".	1 year ago
Harrison Chase	aed9f9febe	Harrison/return intermediate (#1633 ) Co-authored-by: Mario Kostelac <mario@intercom.io>	1 year ago
yakigac	acd86d33bc	Add read only shared memory (#1491 ) Provide shared memory capability for the Agent. Inspired by #1293 . ## Problem If both Agent and Tools (i.e., LLMChain) use the same memory, both of them will save the context. It can be annoying in some cases. ## Solution Create a memory wrapper that ignores the save and clear, thereby preventing updates from Agent or Tools.	1 year ago
Harrison Chase	c9b5a30b37	move output parsing (#1605 )	1 year ago
Harrison Chase	cb04ba0136	Add support for intermediate steps to SQLDatabaseSequentialChain (#1583 ) (#1601 ) for https://github.com/hwchase17/langchain/issues/1582 I simply added the `return_intermediate_steps` and changed the `output_keys` function. I added 2 simple tests, 1 for SQLDatabaseSequentialChain without the intermediate steps and 1 with Co-authored-by: brad-nemetski <115185478+brad-nemetski@users.noreply.github.com>	1 year ago
Harrison Chase	f95d551f7a	Harrison/shallow metadata (#1599 ) Co-authored-by: Jesse Zhang <jessetanzhang@gmail.com>	1 year ago
Harrison Chase	9f78717b3c	Harrison/callbacks (#1587 )	1 year ago
Harrison Chase	3ee32a01ea	Harrison/prompt layer (#1547 ) Co-authored-by: Jonathan Pedoeem <jonathanped@gmail.com> Co-authored-by: AbuBakar <abubakarsohail123@gmail.com>	1 year ago
Harrison Chase	c844d1fd46	Harrison/chunk size (#1549 ) Co-authored-by: Florian Leuerer <31259070+floleuerer@users.noreply.github.com>	1 year ago
Harrison Chase	357d808484	Harrison/remote paths pdf (#1544 ) Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>	1 year ago
Harrison Chase	cc423f40f1	Harrison/youtube loader (#1545 ) Co-authored-by: Julian Wustl <57504258+Julianwustl@users.noreply.github.com>	1 year ago
Harrison Chase	7ade419a0e	allow passing of messages into prompt template (#1505 )	1 year ago
Harrison Chase	064741db58	Harrison/fix text splitter (#1511 ) Co-authored-by: ajaysolanky <ajsolanky@gmail.com> Co-authored-by: Ajay Solanky <ajaysolanky@saw-l14668307kd.myfiosgateway.com>	1 year ago
Ankush Gola	27104d4921	fix `ChatOpenAI.agenerate` (#1504 )	1 year ago
Harrison Chase	7bec461782	Harrison/memory refactor (#1478 ) moves memory to own module, factors out common stuff	1 year ago
Harrison Chase	0e21463f07	(rfc) chat models (#1424 ) Co-authored-by: Ankush Gola <ankush.gola@gmail.com>	2 years ago
Harrison Chase	63a5614d23	Harrison/simple memory (#1435 ) Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>	2 years ago
Harrison Chase	a1b9dfc099	Harrison/similarity search chroma (#1434 ) Co-authored-by: shibuiwilliam <shibuiyusuke@gmail.com>	2 years ago
Tim Asp	23231d65a9	Add PyMuPDF PDF loader (#1426 ) Different PDF libraries have different strengths and weaknesses. PyMuPDF does a good job at extracting the most amount of content from the doc, regardless of the source quality, extremely fast (especially compared to Unstructured). https://pymupdf.readthedocs.io/en/latest/index.html	2 years ago
Nuno Campos	499e76b199	Allow the regular openai class to be used for ChatGPT models (#1393 ) Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	2 years ago
Kacper Łukawski	9ac442624c	Add Qdrant named arguments (#1386 ) This PR: - Increases `qdrant-client` version to 1.0.4 - Introduces custom content and metadata keys (as requested in #1087) - Moves all the `QdrantClient` parameters into the method parameters to simplify code completion	2 years ago
Ankush Gola	fe30be6fba	add async and streaming support to `OpenAIChat` (#1378 ) title says it all	2 years ago
Harrison Chase	1cd8996074	Harrison/summarizer chain (#1356 ) Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>	2 years ago
Ankush Gola	82baecc892	Add a SQL agent for interacting with SQL Databases and JSON Agent for interacting with large JSON blobs (#1150 ) This PR adds * `ZeroShotAgent.as_sql_agent`, which returns an agent for interacting with a sql database. This builds off of `SQLDatabaseChain`. The main advantages are 1) answering general questions about the db, 2) access to a tool for double checking queries, and 3) recovering from errors * `ZeroShotAgent.as_json_agent` which returns an agent for interacting with json blobs. * Several examples in notebooks --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	2 years ago
Harrison Chase	786852e9e6	partial variables (#1308 )	2 years ago
Tim Asp	72ef69d1ba	Add new iFixit document loader (#1333 ) iFixit is a wikipedia-like site that has a huge amount of open content on how to fix things, questions/answers for common troubleshooting and "things" related content that is more technical in nature. All content is licensed under CC-BY-SA-NC 3.0 Adding docs from iFixit as context for user questions like "I dropped my phone in water, what do I do?" or "My macbook pro is making a whining noise, what's wrong with it?" can yield significantly better responses than context free response from LLMs.	2 years ago
Harrison Chase	166cda2cc6	Harrison/deeplake (#1316 ) Co-authored-by: Davit Buniatyan <d@activeloop.ai>	2 years ago
Harrison Chase	aaad6cc954	Harrison/atlas db (#1315 ) Co-authored-by: Brandon Duderstadt <brandonduderstadt@gmail.com>	2 years ago
Enrico Shippole	9becdeaadf	Add Writer, Banana, Modal, StochasticAI (#1270 ) Add LLM wrappers and examples for Banana, Writer, Modal, Stochastic AI Added rigid json format for Banana and Modal	2 years ago
Dennis Antela Martinez	53c67e04d4	add aleph alpha llm (#1207 ) Integrate Aleph Alpha's client into Langchain to provide access to the luminous models - more info on latest benchmarks here: https://www.aleph-alpha.com/luminous-performance-benchmarks	2 years ago
Harrison Chase	b7708bbec6	rfc: callback changes (#1165 ) conceptually, no reason a tool should know what an "agent action" is unless any objections, can change in all callback handlers	2 years ago
Harrison Chase	44c8d8a9ac	move serpapi wrapper (#1199 ) Co-authored-by: Tim Asp <707699+timothyasp@users.noreply.github.com>	2 years ago
Naveen Tatikonda	0118706fd6	Add Support for OpenSearch Vector database (#1191 ) ### Description This PR adds a wrapper which adds support for the OpenSearch vector database. Using opensearch-py client we are ingesting the embeddings of given text into opensearch cluster using Bulk API. We can perform the `similarity_search` on the index using the 3 popular searching methods of OpenSearch k-NN plugin: - `Approximate k-NN Search` use approximate nearest neighbor (ANN) algorithms from the [nmslib](https://github.com/nmslib/nmslib), [faiss](https://github.com/facebookresearch/faiss), and [Lucene](https://lucene.apache.org/) libraries to power k-NN search. - `Script Scoring` extends OpenSearch’s script scoring functionality to execute a brute force, exact k-NN search. - `Painless Scripting` adds the distance functions as painless extensions that can be used in more complex combinations. Also, supports brute force, exact k-NN search like Script Scoring. ### Issues Resolved https://github.com/hwchase17/langchain/issues/1054 --------- Signed-off-by: Naveen Tatikonda <navtat@amazon.com>	2 years ago
Andrew White	c5015d77e2	Allow k to be higher than doc size in max_marginal_relevance_search (#1187 ) Fixes issue #1186. For some reason, #1117 didn't seem to fix it.	2 years ago
Harrison Chase	9d6d8f85da	Harrison/self hosted runhouse (#1154 ) Co-authored-by: Donny Greenberg <dongreenberg2@gmail.com> Co-authored-by: John Dagdelen <jdagdelen@users.noreply.github.com> Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net> Co-authored-by: Andrew White <white.d.andrew@gmail.com> Co-authored-by: Peng Qu <82029664+pengqu123@users.noreply.github.com> Co-authored-by: Matt Robinson <mthw.wm.robinson@gmail.com> Co-authored-by: jeff <tangj1122@gmail.com> Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MacBook-Pro.local> Co-authored-by: zanderchase <zander@unfold.ag> Co-authored-by: Charles Frye <cfrye59@gmail.com> Co-authored-by: zanderchase <zanderchase@gmail.com> Co-authored-by: Shahriar Tajbakhsh <sh.tajbakhsh@gmail.com> Co-authored-by: Stefan Keselj <skeselj@princeton.edu> Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com> Co-authored-by: cragwolfe <cragcw@gmail.com> Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com> Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com> Co-authored-by: blob42 <contact@blob42.xyz> Co-authored-by: blob42 <spike@w530> Co-authored-by: Enrico Shippole <henryshippole@gmail.com> Co-authored-by: Ibis Prevedello <ibiscp@gmail.com> Co-authored-by: jped <jonathanped@gmail.com> Co-authored-by: Justin Torre <justintorre75@gmail.com> Co-authored-by: Ivan Vendrov <ivan@anthropic.com> Co-authored-by: Sasmitha Manathunga <70096033+mmz-001@users.noreply.github.com> Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com> Co-authored-by: Matt Robinson <mrobinson@unstructuredai.io> Co-authored-by: Jeff Huber <jeffchuber@gmail.com> Co-authored-by: Akshay <64036106+akshayvkt@users.noreply.github.com> Co-authored-by: Andrew Huang <jhuang16888@gmail.com> Co-authored-by: rogerserper <124558887+rogerserper@users.noreply.github.com> Co-authored-by: seanaedmiston <seane999@gmail.com> Co-authored-by: Hasegawa Yuya <52068175+Hase-U@users.noreply.github.com> Co-authored-by: Ivan Vendrov <ivendrov@gmail.com> Co-authored-by: Chen Wu (吴尘) <henrychenwu@cmu.edu> Co-authored-by: Dennis Antela Martinez <dennis.antela@gmail.com> Co-authored-by: Maxime Vidal <max.vidal@hotmail.fr> Co-authored-by: Rishabh Raizada <110235735+rishabh-ti@users.noreply.github.com>	2 years ago
CG80499	af8f5c1a49	Added constitutional chain. (#1147 ) - Added self-critique constitutional chain based on this [paper](https://www.anthropic.com/constitutional.pdf).	2 years ago
Ankush Gola	7b5e160d28	Make Tools own model, add ToolKit Concept (#1095 ) Follow-up of @hinthornw's PR: - Migrate the Tool abstraction to a separate file (`BaseTool`). - `Tool` implementation of `BaseTool` takes in function and coroutine to more easily maintain backwards compatibility - Add a Toolkit abstraction that can own the generation of tools around a shared concept or state --------- Co-authored-by: William FH <13333726+hinthornw@users.noreply.github.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Co-authored-by: Francisco Ingham <fpingham@gmail.com> Co-authored-by: Dhruv Anand <105786647+dhruv-anand-aintech@users.noreply.github.com> Co-authored-by: cragwolfe <cragcw@gmail.com> Co-authored-by: Anton Troynikov <atroyn@users.noreply.github.com> Co-authored-by: Oliver Klingefjord <oliver@klingefjord.com> Co-authored-by: William Fu-Hinthorn <whinthorn@Williams-MBP-3.attlocal.net> Co-authored-by: Bruno Bornsztein <bruno.bornsztein@gmail.com>	2 years ago
Francisco Ingham	3f29742adc	Sql alchemy commands used in table info (#1135 ) This approach has several advantages: * it improves the readability of the code * removes incompatibilities between SQL dialects * fixes a bug with `datetime` values in rows and `ast.literal_eval` Huge thanks and credits to @jzluo for finding the weaknesses in the current approach and for the thoughtful discussion on the best way to implement this. --------- Co-authored-by: Francisco Ingham <> Co-authored-by: Jon Luo <20971593+jzluo@users.noreply.github.com>	2 years ago
Noah Gundotra	8c5fbab72d	[Integration Tests] Cast fake embeddings to ALL float values (#1102 ) Pydantic validation breaks tests for example (`test_qdrant.py`) because fake embeddings contain an integer. This PR casts the embeddings array to all floats. Now the `qdrant` test passes, `poetry run pytest tests/integration_tests/vectorstores/test_qdrant.py`	2 years ago
yakigac	1ed708391e	Fix a bug that shows "KeyError 'items'" (#1118 ) Fix KeyError 'items' when no result found. ## Problem When no result found for a query, google search crashed with `KeyError 'items'`. ## Solution I added a check for an empty response before accessing the 'items' key. It will handle the case correctly. ## Other my twitter: yakigac (I don't mind even if you don't mention me for this PR. But just because last time my real name was shout out :) )	2 years ago
Harrison Chase	5e10e19bfe	Harrison/align table (#1081 ) Co-authored-by: Francisco Ingham <fpingham@gmail.com>	2 years ago
Hasegawa Yuya	e08961ab25	Fixed openai embeddings to be safe by batching them based on token size calculation. (#991 ) I modified the logic of the batch calculation for embedding according to this cookbook https://github.com/openai/openai-cookbook/blob/main/examples/Embedding_long_inputs.ipynb	2 years ago
seanaedmiston	f0a258555b	Support similarity search by vector (in FAISS) (#961 ) Alternate implementation to PR #960 Again - only FAISS is implemented. If accepted can add this to other vectorstores or leave as NotImplemented? Suggestions welcome...	2 years ago
rogerserper	e46cd3b7db	Google Search API integration with serper.dev (wrapper, tests, docs, … (#909 ) Adds Google Search integration with [Serper](https://serper.dev) a low-cost alternative to SerpAPI (10x cheaper + generous free tier). Includes documentation, tests and examples. Hopefully I am not missing anything. Developers can sign up for a free account at [serper.dev](https://serper.dev) and obtain an api key. ## Usage ```python from langchain.utilities import GoogleSerperAPIWrapper from langchain.llms.openai import OpenAI from langchain.agents import initialize_agent, Tool import os os.environ["SERPER_API_KEY"] = "" os.environ['OPENAI_API_KEY'] = "" llm = OpenAI(temperature=0) search = GoogleSerperAPIWrapper() tools = [ Tool( name="Intermediate Answer", func=search.run ) ] self_ask_with_search = initialize_agent(tools, llm, agent="self-ask-with-search", verbose=True) self_ask_with_search.run("What is the hometown of the reigning men's U.S. Open champion?") ``` ### Output ``` Entering new AgentExecutor chain... Yes. Follow up: Who is the reigning men's U.S. Open champion? Intermediate answer: Current champions Carlos Alcaraz, 2022 men's singles champion. Follow up: Where is Carlos Alcaraz from? Intermediate answer: El Palmar, Spain So the final answer is: El Palmar, Spain > Finished chain. 'El Palmar, Spain' ```	2 years ago
Ankush Gola	caa8e4742e	Enable streaming for OpenAI LLM (#986 ) * Support a callback `on_llm_new_token` that users can implement when `OpenAI.streaming` is set to `True`	2 years ago
Harrison Chase	88bebb4caa	Harrison/llm integrations (#1039 ) Co-authored-by: jped <jonathanped@gmail.com> Co-authored-by: Justin Torre <justintorre75@gmail.com> Co-authored-by: Ivan Vendrov <ivan@anthropic.com>	2 years ago
Harrison Chase	ec727bf166	Align table info (#999 ) (#1034 ) Currently the chain is getting the column names and types on the one side and the example rows on the other. It is easier for the llm to read the table information if the column name and examples are shown together so that it can easily understand to which columns do the examples refer to. For an instantiation of this, please refer to the changes in the `sqlite.ipynb` notebook. Also changed `eval` for `ast.literal_eval` when interpreting the results from the sample row query since it is a better practice. --------- Co-authored-by: Francisco Ingham <> --------- Co-authored-by: Francisco Ingham <fpingham@gmail.com>	2 years ago
Enrico Shippole	f30dcc6359	Add GooseAI, CerebriumAI, Petals, ForefrontAI (#981 ) Add GooseAI, CerebriumAI, Petals, ForefrontAI	2 years ago
Anton Troynikov	d43d430d86	Chroma persistence (#1028 ) This PR adds persistence to the Chroma vector store. Users can supply a `persist_directory` with any of the `Chroma` creation methods. If supplied, the store will be automatically persisted at that directory. If a user creates a new `Chroma` instance with the same persistence directory, it will get loaded up automatically. If they use `from_texts` or `from_documents` in this way, the documents will be loaded into the existing store. There is the chance of some funky behavior if the user passes a different embedding function from the one used to create the collection - we will make this easier in future updates. For now, we log a warning.	2 years ago
Anton Troynikov	78abd277ff	Chroma in LangChain (#1010 ) Chroma is a simple to use, open-source, zero-config, zero setup vectorstore. Simply `pip install chromadb`, and you're good to go. Out-of-the-box Chroma is suitable for most LangChain workloads, but is highly flexible. I tested to 1M embs on my M1 mac, with out issues and reasonably fast query times. Look out for future releases as we integrate more Chroma features with LangChain!	2 years ago
Shahriar Tajbakhsh	b7747017d7	Import of `declarative_base` when SQLAlchemy <1.4 (#883 ) In [pyproject.toml](https://github.com/hwchase17/langchain/blob/master/pyproject.toml), the expectation is `SQLAlchemy = "^1"`. But, the way `declarative_base` is imported in [cache.py](https://github.com/hwchase17/langchain/blob/master/langchain/cache.py) will only work with SQLAlchemy >=1.4. This PR makes sure Langchain can be run in environments with SQLAlchemy <1.4	2 years ago
Harrison Chase	c64f98e2bb	Harrison/format agent instructions (#973 ) Co-authored-by: Andrew White <white.d.andrew@gmail.com> Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net> Co-authored-by: Peng Qu <82029664+pengqu123@users.noreply.github.com>	2 years ago
Harrison Chase	91c6cea227	Harrison/batch embeds (#972 ) Co-authored-by: John Dagdelen <jdagdelen@users.noreply.github.com> Co-authored-by: Harrison Chase <harrisonchase@Harrisons-MBP.attlocal.net>	2 years ago
Ankush Gola	bc7e56e8df	Add asyncio support for LLM (OpenAI), Chain (LLMChain, LLMMathChain), and Agent (#841 ) Supporting asyncio in langchain primitives allows for users to run them concurrently and creates more seamless integration with asyncio-supported frameworks (FastAPI, etc.) Summary of changes: LLM * Add `agenerate` and `_agenerate` * Implement in OpenAI by leveraging `client.Completions.acreate` Chain * Add `arun`, `acall`, `_acall` * Implement them in `LLMChain` and `LLMMathChain` for now Agent * Refactor and leverage async chain and llm methods * Add ability for `Tools` to contain async coroutine * Implement async SerpaPI `arun` Create demo notebook. Open questions: * Should all the async stuff go in separate classes? I've seen both patterns (keeping the same class and having async and sync methods vs. having class separation)	2 years ago
Harrison Chase	bc53c928fc	Harrison/athropic (#921 ) Co-authored-by: Mike Lambert <mlambert@gmail.com> Co-authored-by: mrbean <sam@you.com> Co-authored-by: mrbean <43734688+sam-h-bean@users.noreply.github.com> Co-authored-by: Ivan Vendrov <ivendrov@gmail.com>	2 years ago
Harrison Chase	1e56879d38	Harrison/save faiss (#916 ) Co-authored-by: Shrey Joshi <shreyjoshi2004@gmail.com>	2 years ago
Harrison Chase	e2b834e427	Harrison/prompt template prefix (#888 ) Co-authored-by: Gabriel Simmons <simmons.gabe@gmail.com>	2 years ago
Harrison Chase	f95cedc443	Harrison/sql rows (#915 ) Co-authored-by: Jon Luo <20971593+jzluo@users.noreply.github.com>	2 years ago
Harrison Chase	ba5a2f06b9	Harrison/inference endpoint (#861 ) Co-authored-by: Eno Reyes <enoreyes@gmail.com>	2 years ago
Kevin Huo	31b054f69d	Add pinecone integration test (#911 ) Basic integration test for pinecone	2 years ago
Harrison Chase	93a091cfb8	Optionally return shell output on incorrect command (#894 ) (#899 ) This allows the LLM to correct its previous command by looking at the error message output to the shell. Additionally, this uses subprocess.run because that is now recommended over subprocess.check_output: https://docs.python.org/3/library/subprocess.html#using-the-subprocess-module Co-authored-by: Amos Ng <me@amos.ng>	2 years ago
Harrison Chase	a2b699dcd2	prompt template from string (#884 )	2 years ago
Harrison Chase	8df6b68093	fix length based example selector (#862 )	2 years ago
Harrison Chase	3f48eed5bd	Harrison/milvus (#856 ) Signed-off-by: Filip Haltmayer <filip.haltmayer@zilliz.com> Signed-off-by: Frank Liu <frank.liu@zilliz.com> Co-authored-by: Filip Haltmayer <81822489+filip-halt@users.noreply.github.com> Co-authored-by: Frank Liu <frank@frankzliu.com>	2 years ago
kahkeng	4a8f5cdf4b	Add alternative token-based text splitter (#816 ) This does not involve a separator, and will naively chunk input text at the appropriate boundaries in token space. This is helpful if we have strict token length limits that we need to strictly follow the specified chunk size, and we can't use aggressive separators like spaces to guarantee the absence of long strings. CharacterTextSplitter will let these strings through without splitting them, which could cause overflow errors downstream. Splitting at arbitrary token boundaries is not ideal but is hopefully mitigated by having a decent overlap quantity. Also this results in chunks which has exact number of tokens desired, instead of sometimes overcounting if we concatenate shorter strings. Potentially also helps with #528.	2 years ago
Harrison Chase	23d5f64bda	Harrison/ngram example (#846 ) Co-authored-by: Sean Spriggens <ssprigge@syr.edu>	2 years ago
Harrison Chase	d564308e0f	rfc: instruct embeddings (#811 ) Co-authored-by: seanaedmiston <seane999@gmail.com>	2 years ago
Harrison Chase	7b4882a2f4	Harrison/tf embeddings (#817 ) Co-authored-by: Ryohei Kuroki <10434946+yakigac@users.noreply.github.com>	2 years ago
Jason Liu	54f9e4287f	Pass kwargs from initialize_agent into agent classmethod (#799 ) # Problem I noticed that in order to change the prefix of the prompt in the `zero-shot-react-description` agent we had to dig around to subset strings deep into the agent's attributes. It requires the user to inspect a long chain of attributes and classes. `initialize_agent -> AgentExecutor -> Agent -> LLMChain -> Prompt from Agent.create_prompt` ``` python agent = initialize_agent( tools=tools, llm=fake_llm, agent="zero-shot-react-description" ) prompt_str = agent.agent.llm_chain.prompt.template new_prompt_str = change_prefix(prompt_str) agent.agent.llm_chain.prompt.template = new_prompt_str ``` # Implemented Solution `initialize_agent` accepts `*kwargs` but passes it to `AgentExecutor` but not `ZeroShotAgent`, by simply giving the kwargs to the agent class methods we can support changing the prefix and suffix for one agent while allowing future agents to take advantage of `initialize_agent`. ``` agent = initialize_agent( tools=tools, llm=fake_llm, agent="zero-shot-react-description", agent_kwargs={"prefix": prefix, "suffix": suffix} ) ``` To be fair, this was before finding docs around custom agents here: https://langchain.readthedocs.io/en/latest/modules/agents/examples/custom_agent.html?highlight=custom%20#custom-llmchain but i find that my use case just needed to change the prefix a little. # Changes Pass kwargs to Agent class method * Added a test to check suffix and prefix --------- Co-authored-by: Jason Liu <jason@jxnl.coA>	2 years ago
Roy Williams	6086292252	Centralize logic for loading from LangChainHub, add ability to pin dependencies (#805 ) It's generally considered to be a good practice to pin dependencies to prevent surprise breakages when a new version of a dependency is released. This commit adds the ability to pin dependencies when loading from LangChainHub. Centralizing this logic and using urllib fixes an issue identified by some windows users highlighted in this video - https://youtu.be/aJ6IQUh8MLQ?t=537	2 years ago
Harrison Chase	1ad7973cc6	Harrison/tool decorator (#790 ) Co-authored-by: Jason Liu <jxnl@users.noreply.github.com> Co-authored-by: Jason Liu <jason@jxnl.coA>	2 years ago
Harrison Chase	248c297f1b	Sample row in table info for SQLDatabase (#769 ) (#782 ) The agents usually benefit from understanding what the data looks like to be able to filter effectively. Sending just one row in the table info allows the agent to understand the data before querying and get better results. --------- Co-authored-by: Francisco Ingham <> --------- Co-authored-by: Francisco Ingham <fpingham@gmail.com>	2 years ago
Amos Ng	6ad360bdef	Suggestions for better debugging (#765 ) Please feel free to disregard any changes you disagree with	2 years ago
Ankush Gola	57609845df	add tracing support to langchain (#741 ) * add implementations of `BaseCallbackHandler` to support tracing: `SharedTracer` which is thread-safe and `Tracer` which is not and is meant to be used locally. * Tracers persist runs to locally running `langchain-server` Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	2 years ago
Amos Ng	fa6826e417	Fix sqlalchemy warnings when running tests (#733 ) This has been bugging me when running my own tests that call langchain methods :P	2 years ago
scadEfUr	e3df8ab6dc	move hyde into chains (#728 ) Co-authored-by: scadEfUr <>	2 years ago
Harrison Chase	0ffeabd14f	Harrison/serialize llm chain (#671 )	2 years ago
Harrison Chase	cbc146720b	verbose flag (#683 )	2 years ago
dham	e04b063ff4	add faiss local saving/loading (#676 ) - This uses the faiss built-in `write_index` and `load_index` to save and load faiss indexes locally - Also fixes #674 - The save/load functions also use the faiss library, so I refactored the dependency into a function	2 years ago
Harrison Chase	a2eeaf3d43	strip whitespace (#680 )	2 years ago
Harrison Chase	0b204d8c21	Harrison/quadrant (#665 ) Co-authored-by: Kacper Łukawski <kacperlukawski@users.noreply.github.com>	2 years ago
Harrison Chase	54d7f1c933	fix caching (#658 )	2 years ago
Harrison Chase	4d4cff0530	Harrison/cohere experimental (#638 ) Co-authored-by: inyourhead <44607279+xettrisomeman@users.noreply.github.com>	2 years ago
Harrison Chase	1ac3319e45	simplify parsing of the final answer (#621 )	2 years ago
Harrison Chase	ffc7e04d44	Harrison/wolfram alpha (#579 ) Co-authored-by: Nicolas <nicolascamara29@gmail.com>	2 years ago
Harrison Chase	1511606799	Harrison/fix splitting (#563 ) fix issue where text splitting could possibly create empty docs	2 years ago
Harrison Chase	1192cc0767	smart text splitter (#530 ) smart text splitter that iteratively tries different separators until it works!	2 years ago
Harrison Chase	9833fcfe32	fix caching (#555 )	2 years ago
Harrison Chase	330a5b42d4	fix map reduce chain (#550 )	2 years ago
Harrison Chase	4974f49bb7	add return_direct flag to tool (#537 ) adds a return_direct flag to tools, which just returns the tool output as the final output	2 years ago
Harrison Chase	1631981f84	Harrison/fix and test caching (#538 )	2 years ago
Harrison Chase	9e04c34e20	Add BaseCallbackHandler and CallbackManager (#478 ) Co-authored-by: Ankush Gola <9536492+agola11@users.noreply.github.com>	2 years ago
Harrison Chase	0db05b6725	Harrison/add human prefix (#520 ) Co-authored-by: Andrew Huang <jhuang16888@gmail.com>	2 years ago
Harrison Chase	985496f4be	Docs refactor (#480 ) Big docs refactor! Motivation is to make it easier for people to find resources they are looking for. To accomplish this, there are now three main sections: - Getting Started: steps for getting started, walking through most core functionality - Modules: these are different modules of functionality that langchain provides. Each part here has a "getting started", "how to", "key concepts" and "reference" section (except in a few select cases where it didnt easily fit). - Use Cases: this is to separate use cases (like summarization, question answering, evaluation, etc) from the modules, and provide a different entry point to the code base. There is also a full reference section, as well as extra resources (glossary, gallery, etc) Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>	2 years ago
Harrison Chase	0072686aab	Harrison/new search engine (#477 ) Co-authored-by: Nicolas <nicolascamara29@gmail.com>	2 years ago
Harrison Chase	d0f194de73	add logic for agent stopping (#420 )	2 years ago
Harrison Chase	95157d0aad	Add schema property to sql database utility class (#448 ) (#462 ) Co-authored-by: Harrison Chase <hw.chase.17@gmail.com> Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com> Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Diwank Singh Tomer <diwank.singh@gmail.com>	2 years ago
Harrison Chase	0c5d3fd894	version 0.0.49 (#436 )	2 years ago
Harrison Chase	f8b605293f	Harrison/improve memory (#432 ) add AI prefix add new type of memory Co-authored-by: Jason <chisanch@usc.edu>	2 years ago
Harrison Chase	ee3b8e89b3	better parsing of agent output (#418 )	2 years ago
Harrison Chase	20959d8c36	check memory variables (#411 ) can have multiple input keys, if some come from memory	2 years ago
Harrison Chase	6b60c509ac	(WIP) add HyDE (#393 ) Co-authored-by: cameronccohen <cameron.c.cohen@gmail.com> Co-authored-by: Cameron Cohen <cameron.cohen@quantco.com>	2 years ago
Harrison Chase	c104d507bf	Harrison/improve data augmented generation docs (#390 ) Co-authored-by: cameronccohen <cameron.c.cohen@gmail.com> Co-authored-by: Cameron Cohen <cameron.cohen@quantco.com>	2 years ago
Harrison Chase	cf98f219f9	Harrison/tools exp (#372 )	2 years ago
Harrison Chase	e7b625fe03	fix text splitter (#375 )	2 years ago
Harrison Chase	3474f39e21	Harrison/improve cache (#368 ) make it so everything goes through generate, which removes the need for two types of caches	2 years ago
Ankush Gola	8d0869c6d3	change run to use args and kwargs (#367 ) Before, `run` was not able to be called with multiple arguments. This expands the functionality.	2 years ago
Harrison Chase	a7084ad6e4	Harrison/version 0040 (#366 )	2 years ago
mrbean	50257fce59	Support Streaming Tokens from OpenAI (#364 ) https://github.com/hwchase17/langchain/issues/363 @hwchase17 how much does this make you want to cry?	2 years ago
mrbean	fe6695b9e7	Add HuggingFacePipeline LLM (#353 ) https://github.com/hwchase17/langchain/issues/354 Add support for running your own HF pipeline locally. This would allow you to get a lot more dynamic with what HF features and models you support since you wouldn't be beholden to what is hosted in HF hub. You could also do stuff with HF Optimum to quantize your models and stuff to get pretty fast inference even running on a laptop.	2 years ago
Harrison Chase	c1b50b7b13	Harrison/map reduce merge (#344 ) Co-authored-by: John Nay <JohnNay@users.noreply.github.com>	2 years ago
Harrison Chase	78b31e5966	Harrison/cache (#343 )	2 years ago
Harrison Chase	8cf62ce06e	Harrison/single input (#347 ) allow passing of single input into chain Co-authored-by: thepok <richterthepok@yahoo.de>	2 years ago
Harrison Chase	9bb7195085	Harrison/llm saving (#331 ) Co-authored-by: Akash Samant <70665700+asamant21@users.noreply.github.com>	2 years ago
Hunter Gerlach	482611f426	unit test / code coverage improvements (#322 ) This PR has two contributions: 1. Add test for when stop token is found in middle of text 2. Add code coverage tooling and instructions - Add pytest-cov via poetry - Add necessary config files - Add new make instruction for `coverage` - Update README with coverage guidance - Update minor README formatting/spelling Co-authored-by: Hunter Gerlach <hunter@huntergerlach.com>	2 years ago
Shobith Alva	19a9fa16a9	Add `clear()` method for `Memory` (#305 ) a simple helper to clear the buffer in `Conversation*Memory` classes	2 years ago
Harrison Chase	e02d6b2288	beta: logger (#307 )	2 years ago
andersenchen	5267ebce2d	Add LLMCheckerChain (#281 ) Implementation of https://github.com/jagilley/fact-checker. Works pretty well. <img width="993" alt="Screenshot 2022-12-07 at 4 41 47 PM" src="https://user-images.githubusercontent.com/101075607/206302751-356a19ff-d000-4798-9aee-9c38b7f532b9.png"> Verifying this manually: 1. "Only two kinds of egg-laying mammals are left on the planet today—the duck-billed platypus and the echidna, or spiny anteater." https://www.scientificamerican.com/article/extreme-monotremes/ 2. "An [Echidna] egg weighs 1.5 to 2 grams (0.05 to 0.07 oz)[[19]](https://en.wikipedia.org/wiki/Echidna#cite_note-19) and is about 1.4 centimetres (0.55 in) long." https://en.wikipedia.org/wiki/Echidna#:~:text=sleep%20is%20suppressed.-,Reproduction,a%20reptile%2Dlike%20egg%20tooth. 3. "A [platypus] lays one to three (usually two) small, leathery eggs (similar to those of reptiles), about 11 mm (7⁄16 in) in diameter and slightly rounder than bird eggs." https://en.wikipedia.org/wiki/Platypus#:~:text=It%20lays%20one%20to%20three,slightly%20rounder%20than%20bird%20eggs. 4. Therefore, an Echidna is the mammal that lays the biggest eggs. cc @hwchase17	2 years ago
Harrison Chase	3c1c7ba672	update branch name in gha (#274 )	2 years ago
Akash Samant	48b093823e	Add a Transformation Chain (#257 ) Arbitrary transformation chains that can be used to add dictionary extractions from llms/other chains	2 years ago
coyotespike	b7bef36ee1	BashChain (#260 ) Love the project, a ton of fun! I think the PR is pretty self-explanatory, happy to make any changes! I am working on using it in an `LLMBashChain` and may update as that progresses. Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	2 years ago
Harrison Chase	28be37f470	LLMRequestsChain (#267 )	2 years ago
John McDonnell	68666d6a22	Gracefully degrade when model asks for nonexistent tool (#268 ) Not yet tested, but very simple change, assumption is that we're cool with just producing a generic output when tool is not found	2 years ago
Harrison Chase	f5c665a544	combine python files (#256 )	2 years ago
Harrison Chase	db58032973	introduce output parser (#250 )	2 years ago
Harrison Chase	a9ce04201f	Harrison/improve usability of api chain (#247 ) improve usability of api chain	2 years ago
Harrison Chase	c897bd6cbd	api chain (#246 ) Co-authored-by: Subhash Ramesh <33400216+thecooltechguy@users.noreply.github.com>	2 years ago
Xupeng (Tony) Tong	bb4bf9d6d0	chore: minor clean up / formatting (#233 ) to get familiarize with the project	2 years ago
Harrison Chase	3ca2c8d6c5	allow passing of stop params into openai (#232 )	2 years ago
Harrison Chase	ca2394028f	move search to not be a chain (#226 )	2 years ago
Andrew Gleave	ea67c049f0	Support SQL statements that return no results (#222 ) Adds support for statements such as insert, update etc which do not return any rows. `engine.execute` is deprecated and so execution has been updated to use `connection.exec_driver_sql` as-per: https://docs.sqlalchemy.org/en/14/core/connections.html#sqlalchemy.engine.Engine.execute	2 years ago
Akash Samant	d368c43648	Bug Fix (#221 ) Quick bug fix for semantic similarity vector injection	2 years ago
Harrison Chase	1b9b8efbc9	pal chain (#207 ) from https://arxiv.org/pdf/2211.10435.pdf	2 years ago
Harrison Chase	b94244eb12	nits (#210 ) use json.dump move test to integration tests (since it requires huggingface_hub)	2 years ago
Akash Samant	ae72cf84b8	Save Prompts (#194 )	2 years ago
Bagatur	b90e25f786	Add HuggingFace Hub Embeddings (#125 ) Add support for calling HuggingFace embedding models using the HuggingFaceHub Inference API. New class mirrors the existing HuggingFaceHub LLM implementation. Currently only supports 'sentence-transformers' models. Closes #86	2 years ago
Harrison Chase	6eab5254e5	add docs for custom agents (#196 )	2 years ago
Harrison Chase	08deed9002	Harrison/memory docs (#195 ) update memory docs and change variables	2 years ago
Harrison Chase	b913df3774	make attrs public (#187 ) since they are used outside of the class, should be public	2 years ago
Harrison Chase	ae9c6257fe	Harrison/arbitrary params (#186 )	2 years ago
Samantha Whitmore	a408ed3ea3	Samantha/add conversation chain (#166 ) Add MemoryChain and ConversationChain as chains that take a docstore in addition to the prompt, and use the docstore to stuff context into the prompt. This can be used to have an ongoing conversation with a chatbot. Probably needs a bit of refactoring for code quality Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	2 years ago
Harrison Chase	4334ffa6f9	Harrison/clean up language (#179 ) dynamic prompts are no longer a thing	2 years ago
Samantha Whitmore	09f301cd38	Add add_example method to all ExampleSelector classes, with tests (#178 ) Also updated docs, and noticed an issue with the add_texts method on VectorStores that I had missed before -- the metadatas arg should be required to match the classmethod which initializes the VectorStores (the add_example methods break otherwise in the ExampleSelectors)	2 years ago
Harrison Chase	d3a7429f61	(WIP) agents (#171 )	2 years ago
Harrison Chase	4a4dfbfbed	Harrison/sequential chains (#168 ) add support for basic sequential chains	2 years ago
Samantha Whitmore	315b0c09c6	wip: add method for both docstore and embeddings (#119 ) this will break atm but wanted to get thoughts on implementation. 1. should add() be on docstore interface? 2. should InMemoryDocstore change to take a list of documents as init? (makes this slightly easier to implement in FAISS -- if we think it is less clean then could expose a method to get the number of documents currently in the dict, and perform the logic of creating the necessary dictionary in the FAISS.add_texts method. Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	2 years ago
Harrison Chase	c02eb199b6	add few shot example (#148 )	2 years ago
Nicholas Larus-Stone	0c3ae78ec1	chore: update ascii colors to work with dark mode (#152 )	2 years ago
Nicholas Larus-Stone	ca4b10bb74	feat: add option to ignore or restrict to SQL tables (#151 ) `SQLDatabase` now accepts two `init` arguments: 1. `ignore_tables` to pass in a list of tables to not search over 2. `include_tables` to restrict to a list of tables to consider	2 years ago
Harrison Chase	1835e8a681	prompt nit (#141 ) doing some cleanup, and i think this just simplifies things...	2 years ago
Harrison Chase	bbb405a492	update colors (#140 )	2 years ago
Harrison Chase	9f223e6ccc	Harrison/fix lint (#138 )	2 years ago
Delip Rao	76cecf8165	A fix for Jupyter environment variable issue (#135 ) - fixes the Jupyter environment variable issues mentioned in issue #134 - fixes format/lint issues in some unrelated files (from make format/lint) ![image](https://user-images.githubusercontent.com/347398/201599322-090af858-362d-4d69-bf59-208aea65419a.png)	2 years ago
Harrison Chase	f23b3ceb49	consolidate run functions (#126 ) consolidating logic for when a chain is able to run with single input text, single output text open to feedback on naming, logic, usefulness	2 years ago
Edmar Ferreira	8a5ec894e7	Prompt from file proof of concept using plain text (#127 ) This is a simple proof of concept of using external files as templates. I'm still feeling my way around the codebase. As a user, I want to use files as prompts, so it will be easier to manage and test prompts. The future direction is to use a template engine, most likely Mako.	2 years ago
Harrison Chase	d87e73ddb1	huggingface tokenizer (#75 )	2 years ago
Harrison Chase	e43534d41c	add integration with manifest (#62 )	2 years ago

... 3 4 5 6 7 ...

475 Commits (5c87dbf5a8c5467a5d9fa5a7b9311eae8f837c65)