langchain

Commit Graph

Author	SHA1	Message	Date
Davit Buniatyan	aaac7071a3	Deep Lake retriever example analyzing Twitter the-algorithm source code (#2602 ) Improvements to Deep Lake Vector Store - much faster view loading of embeddings after filters with `fetch_chunks=True` - 2x faster ingestion - use np.float32 for embeddings to save 2x storage, LZ4 compression for text and metadata storage (saves up to 4x storage for text data) - user defined functions as filters Docs - Added retriever full example for analyzing twitter the-algorithm source code with GPT4 - Added a use case for code analysis (please let us know your thoughts how we can improve it) --------- Co-authored-by: Davit Buniatyan <d@activeloop.ai>	1 year ago
William FH	5c0c5fafb2	Multi-Hop / Multi-Spec LLM Chain (#2549 ) Add a notebook showing how to make a chain that composes multiple OpenAPI Endpoint operations to accomplish tasks.	1 year ago
Jan	d2f8ddab10	Fix typo in PromptTemplate from_examples (#2628 )	1 year ago
ecneladis	9a49f5763d	Add missing comma in async_agent.ipynb (#2614 )	1 year ago
Jan	166624d005	Fix typo in error message (#2622 )	1 year ago
Girish Sharma	9aed565f13	Fix missing import in AzureOpenAI embeddings example (#2625 ) ## Why this PR? Fixes #2624 There's a missing import statement in AzureOpenAI embeddings example. ## What's new in this PR? - Import `OpenAIEmbeddings` before creating it's object. ## How it's tested? - By running notebook and creating embedding object. Signed-off-by: letmerecall <girishsharma001@gmail.com>	1 year ago
Tommertom	0f5d3b3390	Typo docs - Update data_augmented_question_answering.ipynb propriterary-> proprietary (#2626 ) Minor typo propritary -> proprietary	1 year ago
Nuno Campos	5376799a23	Allow recovering from JSONDecoder errors in StructuredOutputParser (#2616 )	1 year ago
Nuno Campos	6f39e88a2c	Add AsyncIteratorCallbackHandler (#2329 )	1 year ago
Harrison Chase	6e4e7d2637	bump version to 135 (#2600 )	1 year ago
rkeshwani	5e57496225	#2595 ChromaDB: Add ability to adjust metadata for indexes upon creating co… (#2597 ) Referencing #2595 Added optional default parameter to adjust index metadata upon collection creation per chroma code `ce0bc89777/chromadb/api/local.py (L74)` Allowing for user to have the ability to adjust distance calculation functions.	1 year ago
Harrison Chase	b9e5b27a99	Harrison/motorhead (#2599 ) Co-authored-by: James O'Dwyer <100361543+softboyjimbo@users.noreply.github.com>	1 year ago
Johnny Lim	79a44c8225	Remove unnecessary question mark in link in README (#2589 ) This PR removes an unnecessary question mark in link in the `README.md` file.	1 year ago
Harrison Chase	2f49c96532	Harrison/redis (#2588 ) Co-authored-by: Tyler Hutcherson <tyler.hutcherson@redis.com>	1 year ago
Yuchu Luo	40469eef7f	fix temperature parameter not used in chat models (#2558 )	1 year ago
Will Henchy	125afb51d7	Add shared Google Drive folder support (#2562 ) closes #1634 Adds support for loading files from a shared Google Drive folder to `GoogleDriveLoader`. Shared drives are commonly used by businesses on their Google Workspace accounts (this is my particular use case).	1 year ago
Alex Rad	7bf5b0ccd3	RWKV: do not propagate model_state between calls (#2565 ) RWKV is an RNN with a hidden state that is part of its inference. However, the model state should not be carried across uses and it's a bug to do so. This resets the state for multiple invocations	1 year ago
Venky	7a4e1b72a8	Fix docs links (#2572 ) Fix broken links in documentation.	1 year ago
Roy Xue	f5afb60116	doc: change comment with correct name (#2580 ) In this comment, it should be ConversationalRetrievalChain instead of ChatVectorDBChain	1 year ago
Shishin Mo	f7f118e021	use openai_organization as argument (#2566 ) Added support for passing the openai_organization as an argument, as it was only supported by the environment variable but openai_api_key was supported by both environment variables and arguments. `ChatOpenAI(temperature=0, model_name="gpt-4", openai_api_key="sk-**", openai_organization="org-**")`	1 year ago
akmhmgc	544cc7f395	Modified doc (#2568 ) # description Remove unnecessary codes and made the output easier to check in docs :)	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
Kacper Łukawski	d8967e28d0	Upgrade Qdrant to 1.1.2 (#2554 ) This is a minor upgrade for Qdrant. We made a small bugfix in the local mode, so it might also be good to upgrade Qdrant for LangChain users.	1 year ago
joaoareis	b4d6a425a2	Fix typo in ChatGPT plugins (#2553 ) This PR adds a `,` that was missing in the ChatGPT plugins examples.	1 year ago
Ikko Eltociear Ashimine	fc1d48814c	fix typo in summary_buffer.ipynb (#2547 ) ouput -> output	1 year ago
Duncan Brown	9b78bb7393	Fix a typo in the SQL agent prompt prefix (#2552 ) Fix the grammar in this sentence, and remove the redundant "few" "only ask for a the few relevant columns" -> "only ask for the relevant columns"	1 year ago
Harrison Chase	a32c85951e	agent docs (#2551 )	1 year ago
Harrison Chase	95e780d6f9	bump version 134 (#2544 )	1 year ago
Harrison Chase	247a88f2f9	Harrison/move eval (#2533 )	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
tmyjoe	c9f93f5f74	fix: token counting for chat openai. (#2543 ) I noticed that the value of get_num_tokens_from_messages in `ChatOpenAI` is always one less than the response from OpenAI's API. Upon checking the official documentation, I found that it had been updated, so I made the necessary corrections. Then now I got the same value from OpenAI's API. `d972e7482e (diff-2d4485035b3a3469802dbad11d7b4f834df0ea0e2790f418976b303bc82c1874L474)`	1 year ago
SangamSwadiK	8cded3fdad	fix typo (#2532 ) 1) Any breaking changes ? None 2) What does this do ? Fix typo in QA eval cc @hwchase17	1 year ago
Ankush Gola	dca21078ad	Run tools concurrently in `_atake_next_step` (#2537 ) small refactor to allow this	1 year ago
Ankush Gola	6dbd29e440	add async vector operations in VectorStore base class (#2535 ) not currently implemented by any subclasses	1 year ago
akmhmgc	481de8df7f	Modify docs (#2539 ) # description Modified doc according to recently added `AgentType`.	1 year ago
Harrison Chase	a31c9511e8	Harrison/redis improvements (#2528 ) Co-authored-by: Tyler Hutcherson <tyler.hutcherson@redis.com>	1 year ago
Hamza Kyamanywa	ec489599fd	Correct typo in documentation for word 'therefore' (#2529 ) This PR corrects a typo in the langchain [documentation.](https://python.langchain.com/en/latest/modules/indexes.html#:~:text=We%20therefor%20have%20a%20concept) It corrects the word `therefor` to `therefore`	1 year ago
Harrison Chase	3d0449bb45	agent tool retrieval (#2530 )	1 year ago
William FH	632c65d64b	Add to notebook to assist in ground truth question generation (#2523 ) At the bottom of the notebook, continue to show how to generate example test cases with the assistance of an LLM	1 year ago
Harrison Chase	15cdfa9e7f	Harrison/table index (#2526 ) Co-authored-by: Alvaro Sevilla <alvaro@chainalysis.com>	1 year ago
Harrison Chase	704b0feb38	Harrison/allow org none (#2527 )	1 year ago
Alex Iribarren	aecd1c8ee3	Gitbook enhancements (#2279 ) The gitbook importer had some issues while trying to ingest a particular site, these commits allowed it to work as expected. The last commit (`06017ff`) is to open the door to extending this class for other documentation formats (which will come in a future PR).	1 year ago
Harrison Chase	58a93f88da	Harrison/entity store (#2525 ) Co-authored-by: Alex Iribarren <alex.iribarren@gmail.com>	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
AeroXi	e131156805	set default embedding max token size (#2330 ) #991 has already implemented this convenient feature to prevent exceeding max token limit in embedding model. > By default, this function is deactivated so as not to change the previous behavior. If you specify something like 8191 here, it will work as desired. According to the author, this is not set by default. Until now, the default model in OpenAIEmbeddings's max token size is 8191 tokens, no other openai model has a larger token limit. So I believe it will be better to set this as default value, other wise users may encounter this error and hard to solve it.	1 year ago
Fabian Venturini Cabau	0316900d2f	feat: implements similarity_search_by_vector on Weaviate (#2522 ) This PR implements `similarity_search_by_vector` in the Weaviate vectorstore.	1 year ago
Harrison Chase	5c64b86ba3	Harrison/weaviate retriever (#2524 ) Co-authored-by: Erika Cardenas <110841617+erika-cardenas@users.noreply.github.com>	1 year ago
Tiago De Gaspari	c2f21a519f	Add support to set up openai organizations (#2514 ) Add support for defining the organization of OpenAI, similarly to what is done in the reference code below: ``` import os import openai openai.organization = os.getenv("OPENAI_ORGANIZATION") openai.api_key = os.getenv("OPENAI_API_KEY") ```	1 year ago
William FH	629fda3957	Use JSON rather than JSON5 (#2520 ) Evaluation so far has shown that agents do a reasonable job of emitting `json` blocks as arguments when cued (instead of typescript), and `json` permits the `strict=False` flag to permit control characters, which are likely to appear in the response in particular. This PR makes this change to the request and response synthesizer chains, and fixes the temperature to the OpenAI agent in the eval notebook. It also adds a `raise_error = False` flag in the notebook to facilitate debugging	1 year ago
William FH	f8e4048cd8	Add an Example Evaluation Notebook for the API Chain (#2516 ) Taking the Klarna API as an example, uses evaluation chain's to judge the quality of the request and response synthesizers based on a small set of curated queries. Also updates intermediate steps for chain to emit a dict so each step can be keyed for lookup ![image](https://user-images.githubusercontent.com/13333726/230505771-5cdb4de4-6fe7-4f54-b944-f29d438fa42c.png)	1 year ago

1 2 3 4 5 ...

1188 Commits (aaac7071a37ec81d37ce59efb69a755c92c0708c) All Branches Search

1188 Commits (aaac7071a37ec81d37ce59efb69a755c92c0708c)

All Branches