langchain

Commit Graph

Author	SHA1	Message	Date
Eugene Yurtsev	0dea8cc62d	Update doc-string in RunnableWithMessageHistory (#14262 ) Update doc-string in RunnableWithMessageHistory	7 months ago
Erick Friis	2aaf8e11e0	docs[patch]: fix ipynb links (#14325 ) Keeping it simple for now. Still iterating on our docs build in pursuit of making everything mdxv2 compatible for docusaurus 3, and the fewer custom scripts we're reliant on through that, the less likely the docs will break again. Other things to consider in future: Quarto rewriting in ipynbs: https://quarto.org/docs/extensions/nbfilter.html (but this won't do md/mdx files) Docusaurus plugins for rewriting these paths	7 months ago
Jean-Baptiste dlb	38813d7090	Qdrant metadata payload keys (#13001 ) - Description: In Qdrant allows to input list of keys as the content_payload_key to retrieve multiple fields (the generated document will contain the dictionary {field: value} in a string), - Issue: Previously we were able to retrieve only one field from the vector database when making a search - Dependencies: - Tag maintainer: - Twitter handle: @jb_dlb --------- Co-authored-by: Jean Baptiste De La Broise <jeanbaptiste.delabroise@mdpi.com>	7 months ago
Yuchen Liang	ad6dfb6220	feat: mask api key for cerebriumai llm (#14272 ) - Description: Masking API key for CerebriumAI LLM to protect user secrets. - Issue: #12165 - Dependencies: None - Tag maintainer: @eyurtsev --------- Signed-off-by: Yuchen Liang <yuchenl3@andrew.cmu.edu> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
newfinder	d4d64daa1e	Mask API key for baidu qianfan (#14281 ) Description: This PR masked baidu qianfan - Chat_Models API Key and added unit tests. Issue: the issue langchain-ai#12165. Tag maintainer: @eyurtsev --------- Co-authored-by: xiayi <xiayi@bytedance.com>	7 months ago
cxumol	06e3316f54	feat(add): LLM integration of Cloudflare Workers AI (#14322 ) Add [Text Generation by Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/models/text-generation/). It's a new LLM integration. - Dependencies: N/A	7 months ago
Harutaka Kawamura	5efaedf488	Exclude `max_tokens` from request if it's None (#14334 ) <!-- 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. --> We found a request with `max_tokens=None` results in the following error in Anthropic: ``` HTTPError: 400 Client Error: Bad Request for url: https://oregon.staging.cloud.databricks.com/serving-endpoints/corey-anthropic/invocations. Response text: {"error_code":"INVALID_PARAMETER_VALUE","message":"INVALID_PARAMETER_VALUE: max_tokens was not of type Integer: null"} ``` This PR excludes `max_tokens` if it's None.	7 months ago
Nicolas Bondoux	86b08d7753	Fix typo in lcel example for rerank in doc (#14336 ) fix typo in lcel example for rerank in doc	7 months ago
Matt Wells	e1ea191237	Demonstrate use of get_buffer_string (#13013 ) Description The docs for creating a RAG chain with Memory [currently use a manual lambda](https://python.langchain.com/docs/expression_language/cookbook/retrieval#with-memory-and-returning-source-documents) to format chat history messages. [There exists a helper method within the codebase](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/schema/messages.py#L14C15-L14C15) to perform this task so I've updated the documentation to demonstrate its usage Also worth noting that the current documented method of using the included `_format_chat_history ` function actually results in an error: ``` TypeError: 'HumanMessage' object is not subscriptable ``` --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
MinjiK	a1a11ffd78	Amadeus toolkit minor update (#13002 ) - update `Amadeus` toolkit with ability to switch Amadeus environments - update minor code explanations --------- Co-authored-by: MinjiK <minji.kim@amadeus.com>	7 months ago
Alexandre Dumont	b05c46074b	OpenAIEmbeddings: retry_min_seconds/retry_max_seconds parameters (#13138 ) - Description: new parameters in OpenAIEmbeddings() constructor (retry_min_seconds and retry_max_seconds) that allow parametrization by the user of the former min_seconds and max_seconds that were hidden in _create_retry_decorator() and _async_retry_decorator() - Issue: #9298, #12986 - Dependencies: none - Tag maintainer: @hwchase17 - Twitter handle: @adumont make format ✅ make lint ✅ make test ✅ Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
mogith-pn	9e5d146409	Updated integration with Clarifai python SDK functions (#13671 ) Description : Updated the functions with new Clarifai python SDK. Enabled initialisation of Clarifai class with model URL. Updated docs with new functions examples.	7 months ago
dudub12	8f403ea2d7	info sql tool remove whitespaces in table names (#13712 ) Remove whitespaces from the input of the ListSQLDatabaseTool for better support. for example, the input "table1,table2,table3" will throw an exception whiteout the change although it's a valid input. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
balaba-max	64d5108f99	Feature: GitLab url from ENV (#14221 ) <!-- Thank you for contributing to LangChain! Replace this entire comment with: - Description: add gitlab url from env, - Issue: no issue, - Dependencies: no, - 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. --> --------- Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
kavinraj A S	ab6b41937a	Fixed a typo in smart_llm prompt (#13052 ) <!-- 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. -->	7 months ago
jeffpezzone	7c2ef06136	Adds "NIN" metadata filter for pgvector to all checking for set absence (#14205 ) This PR adds support for metadata filters of the form: `{"filter": {"key": { "NIN" : ["list", "of", "values"]}}}` "IN" is already supported, so this is a quick & related update to add "NIN"	7 months ago
lif	20d2b4a6ba	feat: Increased compatibility with new and old versions for dalle (#14222 ) - Description: Increased compatibility with all versions openai for dalle, This pr add support for openai version from 0 ~ 1.3.	7 months ago
Wang Wei	7205bfdd00	feat: 1. Add system parameters, 2. Align with the QianfanChatEndpoint for function calling (#14275 ) - Description: 1. Add system parameters to the ERNIE LLM API to set the role of the LLM. 2. Add support for the ERNIE-Bot-turbo-AI model according from the document https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Alp0kdm0n. 3. For the function call of ErnieBotChat, align with the QianfanChatEndpoint. With this PR, the `QianfanChatEndpoint()` can use the `function calling` ability with `create_ernie_fn_chain()`. The example is as the following: ``` from langchain.prompts import ChatPromptTemplate import json from langchain.prompts.chat import ( ChatPromptTemplate, ) from langchain.chat_models import QianfanChatEndpoint from langchain.chains.ernie_functions import ( create_ernie_fn_chain, ) def get_current_news(location: str) -> str: """Get the current news based on the location.' Args: location (str): The location to query. Returs: str: Current news based on the location. """ news_info = { "location": location, "news": [ "I have a Book.", "It's a nice day, today." ] } return json.dumps(news_info) def get_current_weather(location: str, unit: str="celsius") -> str: """Get the current weather in a given location Args: location (str): location of the weather. unit (str): unit of the tempuature. Returns: str: weather in the given location. """ weather_info = { "location": location, "temperature": "27", "unit": unit, "forecast": ["sunny", "windy"], } return json.dumps(weather_info) template = ChatPromptTemplate.from_messages([ ("user", "{user_input}"), ]) chat = QianfanChatEndpoint(model="ERNIE-Bot-4") chain = create_ernie_fn_chain([get_current_weather, get_current_news], chat, template, verbose=True) res = chain.run("北京今天的新闻是什么？") print(res) ``` The result of the above code: ``` > Entering new LLMChain chain... Prompt after formatting: Human: 北京今天的新闻是什么？ > Finished chain. {'name': 'get_current_news', 'arguments': {'location': '北京'}} ``` For the `ErnieBotChat`, now can use the `system` parameter to set the role of the LLM. ``` from langchain.prompts import ChatPromptTemplate from langchain.chains import LLMChain from langchain.chat_models import ErnieBotChat llm = ErnieBotChat(model_name="ERNIE-Bot-turbo-AI", system="你是一个能力很强的机器人，你的名字叫小叮当。无论问你什么问题，你都可以给出答案。") prompt = ChatPromptTemplate.from_messages( [ ("human", "{query}"), ] ) chain = LLMChain(llm=llm, prompt=prompt, verbose=True) res = chain.run(query="你是谁？") print(res) ``` The result of the above code: ``` > Entering new LLMChain chain... Prompt after formatting: Human: 你是谁？ > Finished chain. 我是小叮当，一个智能机器人。我可以为你提供各种服务，包括回答问题、提供信息、进行计算等。如果你需要任何帮助，请随时告诉我，我会尽力为你提供最好的服务。 ```	7 months ago
Leonid Kuligin	fd5be55a7b	added get_num_tokens to GooglePalm (#14282 ) added get_num_tokens to GooglePalm + a little bit of refactoring	7 months ago
Massimiliano Pronesti	c215a4c9ec	feat(embeddings): text-embeddings-inference (#14288 ) - Description: Added a notebook to illustrate how to use `text-embeddings-inference` from huggingface. As `HuggingFaceHubEmbeddings` was using a deprecated client, I made the most of this PR updating that too. - Issue: #13286 - Dependencies: None - Tag maintainer: @baskaryan	7 months ago
Tim Van Wassenhove	85b88c33f3	Fixes issue-14295: Correctly pass along the kwargs (#14296 ) - Description: Update code to correctly pass the kwargs - Issue: #14295 - Dependencies: - - Tag maintainer: <-- If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. --> #issue-14295	7 months ago
Alex Kira	62b59048de	docs[patch] Add how-to doc for RunnablePassthrough and nav modifications (#14255 ) - Description: Add How To docs for `RunnablePassthrough` with examples. Also redo the ordering and some of the other How-To docs.	7 months ago
Bob Lin	5a23608c41	Add custom async generator example (#14299 ) <img width="1172" alt="Screenshot 2023-12-05 at 11 19 16 PM" src="https://github.com/langchain-ai/langchain/assets/10000925/6b0fbd70-9f6b-4f91-b494-9e88676b4786">	7 months ago
Bob Lin	63fdc6e818	Update docs (#14294 ) ### Description Fixed 3 doc issues: 1. `ConfigurableField ` needs to be imported in `docs/docs/expression_language/how_to/configure.ipynb` 2. use `error` instead of `RateLimitError()` in `docs/docs/expression_language/how_to/fallbacks.ipynb` 3. I think it might be better to output the fixed json data(when I looked at this example, I didn't understand its purpose at first, but then I suddenly realized): <img width="1219" alt="Screenshot 2023-12-05 at 10 34 13 PM" src="https://github.com/langchain-ai/langchain/assets/10000925/7623ba13-7b56-4964-8c98-b7430fabc6de">	7 months ago
Jarkko Lagus	667ad6a5de	Add support for CORS options for AzureSearch (#14305 ) - Description: Add support for setting the CORS options when using AzureSearch indexes	7 months ago
Karim Assi	9401539e43	Allow not enforcing function usage when a single function is passed to openai function executable (#14308 ) - Description: allows not enforcing function usage when a single function is passed to an openAI function executable (or corresponding legacy chain). This is a desired feature in the case where the model does not have enough information to call a function, and needs to get back to the user. - Issue: N/A - Dependencies: N/A - Tag maintainer: N/A	7 months ago
Ran	d22c13ec48	Mask API key for Minimax LLM (#14309 ) - Description: Added masking for the API key for Minimax LLM + tests inspired by https://github.com/langchain-ai/langchain/pull/12418. - Issue: the issue # fixes https://github.com/langchain-ai/langchain/issues/12165 - Dependencies: this fix is dependent on Minimax instantiation fix which is introduced in https://github.com/langchain-ai/langchain/pull/13439, so merge this one after. - Tag maintainer: @eyurtsev --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
Lance Martin	29e993a5f2	Update OpenCLIP docs (#14319 )	7 months ago
Eugene Yurtsev	a74c03da3c	Add metadata to blob (#14162 ) Add metadata to the blob object. This makes it easier to make a pipeline that properly propagates metadata information from raw content to the derived content.	7 months ago
Lance Martin	66848871fc	Multi-modal RAG template (#14186 ) * OpenCLIP embeddings * GPT-4V --------- Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
James Braza	3b75d37cee	Adding `BaseChatMessageHistory.__str__` (#14311 ) Adding __str__ to base chat message history to make it easier to debug	7 months ago
James Braza	8b0060184d	Fixing empty input variable crashing `PromptTemplate` validations (#14314 ) - Fixes `input_variables=[""]` crashing validations with a template `"{}"` - Uses `__cause__` for proper `Exception` chaining in `check_valid_template`	7 months ago
Leonid Ganeline	0f02e94565	docs: `integrations/providers/` update (#14315 ) - added missed provider files (from `integrations/Callbacks` - updated notebooks: added links; updated into consistent formats	7 months ago
Bagatur	6607cc6eab	experimental[patch]: Release 0.0.44 (#14310 )	7 months ago
Eugene Yurtsev	80637727ea	hide api key: arcee (#14304 ) Hide API key for Arcee --------- Co-authored-by: raphael <raph.nunes95@gmail.com>	7 months ago
Bagatur	b2e756c0a8	langchain[patch]: Release 0.0.346 (#14307 )	7 months ago
Bagatur	4a5a13aab3	core[patch]: Release 0.0.10 (#14303 )	7 months ago
Eugene Yurtsev	7ad75edf8b	Fix rag google cloud vertex ai template (#14300 ) Fix template by exposing chain correctly	7 months ago
Eun Hye Kim	f758c8adc4	Fix #11737 issue (extra_tools option of create_pandas_dataframe_agent is not working) (#13203 ) - Description: Fix #11737 issue (extra_tools option of create_pandas_dataframe_agent is not working), - Issue: #11737 , - Dependencies: no, - Tag maintainer: @baskaryan, @eyurtsev, @hwchase17 I needed this method at work, so I modified it myself and used it. There is a similar issue(#11737) and PR(#13018) of @PyroGenesis, so I combined my code at the original PR. You may be busy, but it would be great help for me if you checked. Thank you. - Twitter handle: @lunara_x If you need an .ipynb example about this, please tag me. I will share what I am working on after removing any work-related content. --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
Sean Bearden	77a15fa988	Added ability to pass arguments to the Playwright browser (#13146 ) - Description: Enhanced `create_sync_playwright_browser` and `create_async_playwright_browser` functions to accept a list of arguments. These arguments are now forwarded to `browser.chromium.launch()` for customizable browser instantiation. - Issue: #13143 - Dependencies: None - Tag maintainer: @eyurtsev, - Twitter handle: Dr_Bearden --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
Joan Fontanals	dcccf8fa66	adapt Jina Embeddings to new Jina AI Embedding API (#13658 ) - Description: Adapt JinaEmbeddings to run with the new Jina AI Embedding platform - Twitter handle: https://twitter.com/JinaAI_ --------- Co-authored-by: Joan Fontanals Martinez <joan.fontanals.martinez@jina.ai> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
Philippe PRADOS	e0c03d6c44	Pprados/lite google drive (#13175 ) - Fix bug in the document - Add clarification on the use of langchain-google drive.	7 months ago
guillaumedelande	ea0afd07ca	Update azuresearch.py following recent change from azure-search-documents library (#13472 ) - Description: Reference library azure-search-documents has been adapted in version 11.4.0: 1. Notebook explaining Azure AI Search updated with most recent info 2. HnswVectorSearchAlgorithmConfiguration --> HnswAlgorithmConfiguration 3. PrioritizedFields(prioritized_content_fields) --> SemanticPrioritizedFields(content_fields) 4. SemanticSettings --> SemanticSearch 5. VectorSearch(algorithm_configurations) --> VectorSearch(configurations) --> Changes now reflected on Langchain: default vector search config from langchain is now compatible with officially released library from Azure. - Issue: Issue creating a new index (due to wrong class used for default vector search configuration) if using latest version of azure-search-documents with current langchain version - Dependencies: azure-search-documents>=11.4.0, - Tag maintainer: , --------- Co-authored-by: Erick Friis <erick@langchain.dev>	7 months ago
price-deshaw	5cb3393e20	update OpenAI function agents' llm validation (#13538 ) - Description: This PR modifies the LLM validation in OpenAI function agents to check whether the LLM supports OpenAI functions based on a property (`supports_oia_functions`) instead of whether the LLM passed to the agent `isinstance` of `ChatOpenAI`. This allows classes that extend `BaseChatModel` to be passed to these agents as long as they've been integrated with the OpenAI APIs and have this property set, even if they don't extend `ChatOpenAI`. - Issue: N/A - Dependencies: none	7 months ago
Max Weng	74c7b799ef	migrate openai audio api (#13557 ) for issue https://github.com/langchain-ai/langchain/issues/13162 migrate openai audio api, as [openai v1.0.0 Migration Guide](https://github.com/openai/openai-python/discussions/742) <!-- 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. --> --------- Co-authored-by: Double Max <max@ground-map.com>	7 months ago
Arnaud Gelas	abbba6c7d8	openapi/planner.py: Deal with json in markdown output cases (#13576 ) - Description: In openapi/planner deal with json in markdown output cases - Issue: In some cases LLMs could return json in markdown which can't be loaded. - Dependencies: - Tag maintainer: @eyurtsev - Twitter handle: --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago
Harrison Chase	8eab4d95c0	Harrison/delegate from template (#14266 ) Co-authored-by: M.R. Sopacua <144725145+msopacua@users.noreply.github.com>	7 months ago
Erick Friis	956d55de2b	docs[patch]: chat model page names (#14264 )	7 months ago
Nolan	b49104c2c9	Add missing doc key to metadata field in AzureSearch Vectorstore (#13328 ) - Description: Adds doc key to metadata field when adding document to Azure Search. - Issue: -, - Dependencies: -, - Tag maintainer: @eyurtsev, - Twitter handle: @finnless Right now the document key with the name FIELDS_ID is not included in the FIELDS_METADATA field, and therefore is not included in the Document returned from a query. This is really annoying if you want to be able to modify that item in the vectorstore. Other's thoughts on this are welcome.	7 months ago
Jon Watte	e042e5df35	fix: call _on_llm_error() (#13581 ) Description: There's a copy-paste typo where on_llm_error() calls _on_chain_error() instead of _on_llm_error(). Issue: #13580 Dependencies: None Tag maintainer: @hwchase17 Twitter handle: @jwatte "Run `make format`, `make lint` and `make test` to check this locally." The test scripts don't work in a plain Ubuntu LTS 20.04 system. It looks like the dev container pulling is stuck. Or maybe the internet is just ornery today. --------- Co-authored-by: jwatte <jwatte@observeinc.com> Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>	7 months ago

1 2 3 4 5 ...

6387 Commits (99743539ae4550d222c585de4a6dca042e267ea3) All Branches Search

6387 Commits (99743539ae4550d222c585de4a6dca042e267ea3)

All Branches