langchain

Commit Graph

Author	SHA1	Message	Date
Holt Skinner	1c08dbfb33	IMPROVEMENT: Reduce post-processing time for `DocAIParser` (#13210 ) - Remove `WrappedDocument` introduced in https://github.com/langchain-ai/langchain/pull/11413 - https://github.com/googleapis/python-documentai-toolbox/issues/198 in Document AI Toolbox to improve initialization time for `WrappedDocument` object. @lkuligin @baskaryan @hwchase17	9 months ago
Leonid Kuligin	f3fcdea574	fixed an UnboundLocalError when no documents are found (#12995 ) Replace this entire comment with: - Description: fixed a bug - Issue: the issue # #12780	9 months ago
Stijn Tratsaert	b6f70d776b	VertexAI LLM count_tokens method requires list of prompts (#13451 ) I encountered this during summarization with VertexAI. I was receiving an INVALID_ARGUMENT error, as it was trying to send a list of about 17000 single characters. The [count_tokens method](https://github.com/googleapis/python-aiplatform/blob/main/vertexai/language_models/_language_models.py#L658) made available by Google takes in a list of prompts. It does not fail for small texts, but it does for longer documents because the argument list will be exceeding Googles allowed limit. Enforcing the list type makes it work successfully. This change will cast the input text to count to a list of that single text so that the input format is always correct. [Twitter](https://www.x.com/stijn_tratsaert)	9 months ago
Wang Wei	fe7b40cb2a	feat: add ERNIE-Bot-4 Function Calling (#13320 ) - Description: ERNIE-Bot-Chat-4 Large Language Model adds the ability of `Function Calling` by passing parameters through the `functions` parameter in the request. To simplify function calling for ERNIE-Bot-Chat-4, the `create_ernie_fn_chain()` function has been added. The definition and usage of the `create_ernie_fn_chain()` function is similar to that of the `create_openai_fn_chain()` function. Examples as the follows: ``` import json from langchain.chains.ernie_functions import ( create_ernie_fn_chain, ) from langchain.chat_models import ErnieBotChat from langchain.prompts import ChatPromptTemplate 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) llm = ErnieBotChat(model_name="ERNIE-Bot-4") prompt = ChatPromptTemplate.from_messages( [ ("human", "{query}"), ] ) chain = create_ernie_fn_chain([get_current_weather, get_current_news], llm, prompt, verbose=True) res = chain.run("北京今天的新闻是什么？") print(res) ``` The running results of the above program are shown below： ``` > Entering new LLMChain chain... Prompt after formatting: Human: 北京今天的新闻是什么？ > Finished chain. {'name': 'get_current_news', 'thoughts': '用户想要知道北京今天的新闻。我可以使用get_current_news工具来获取这些信息。', 'arguments': {'location': '北京'}} ```	9 months ago
Adilkhan Sarsen	10418ab0c1	DeepLake Backwards compatibility fix (#13388 ) - Description: during search with DeepLake some people are facing backwards compatibility issues, this PR fixes it by making search accessible for the older datasets --------- Co-authored-by: adolkhan <adilkhan.sarsen@alumni.nu.edu.kz>	9 months ago
Tyler Hutcherson	190952fe76	IMPROVEMENT: Minor redis improvements (#13381 ) - Description: - Fixes a `key_prefix` bug where passing it in on `Redis.from_existing(...)` did not work properly. Updates doc strings accordingly. - Updates Redis filter classes logic with best practices on typing, string formatting, and handling "empty" filters. - Fixes a bug that would prevent multiple tag filters from being applied together in some scenarios. - Added a whole new filter unit testing module. Also updated code formatting for a number of modules that were failing the `make` commands. - Issue: N/A - Dependencies: N/A - Tag maintainer: @baskaryan - Twitter handle: @tchutch94	9 months ago
Sijun He	674bd90a47	DOCS: Fix typo in MongoDB memory docs (#13588 ) - Description: Fix typo in MongoDB memory docs - Tag maintainer: @eyurtsev <!-- Thank you for contributing to LangChain! - Description: Fix typo in MongoDB memory docs - Issue: the issue # it fixes (if applicable), - Dependencies: any dependencies required for this change, - Tag maintainer: @baskaryan - 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. -->	9 months ago
Sergey Kozlov	df03267edf	Fix tool arguments formatting in StructuredChatAgent (#10480 ) In the `FORMAT_INSTRUCTIONS` template, 4 curly braces (escaping) are used to get single curly brace after formatting: ``` "{{{ ... }}}}" -> format_instructions.format() -> "{{ ... }}" -> template.format() -> "{ ... }". ``` Tool's `args_schema` string contains single braces `{ ... }`, and is also transformed to `{{{{ ... }}}}` form. But this is not really correct since there is only one `format()` call: ``` "{{{{ ... }}}}" -> template.format() -> "{{ ... }}". ``` As a result we get double curly braces in the prompt: ```` Respond to the human as helpfully and accurately as possible. You have access to the following tools: foo: Test tool FOO, args: {{'tool_input': {{'type': 'string'}}}} # <--- !!! ... Provide only ONE action per $JSON_BLOB, as shown: ``` { "action": $TOOL_NAME, "action_input": $INPUT } ``` ```` This PR fixes curly braces escaping in the `args_schema` to have single braces in the final prompt: ```` Respond to the human as helpfully and accurately as possible. You have access to the following tools: foo: Test tool FOO, args: {'tool_input': {'type': 'string'}} # <--- !!! ... Provide only ONE action per $JSON_BLOB, as shown: ``` { "action": $TOOL_NAME, "action_input": $INPUT } ``` ```` --------- Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io>	9 months ago
Wouter Durnez	ef7802b325	Add llama2-13b-chat-v1 support to `chat_models.BedrockChat` (#13403 ) Hi 👋 We are working with Llama2 on Bedrock, and would like to add it to Langchain. We saw a [pull request](https://github.com/langchain-ai/langchain/pull/13322) to add it to the `llm.Bedrock` class, but since it concerns a chat model, we would like to add it to `BedrockChat` as well. - Description: Add support for Llama2 to `BedrockChat` in `chat_models` - Issue: the issue # it fixes (if applicable) [#13316](https://github.com/langchain-ai/langchain/issues/13316) - Dependencies: any dependencies required for this change `None` - Tag maintainer: / - Twitter handle: `@SimonBockaert @WouterDurnez` --------- Co-authored-by: wouter.durnez <wouter.durnez@showpad.com> Co-authored-by: Simon Bockaert <simon.bockaert@showpad.com>	9 months ago
jwbeck97	a93616e972	FEAT: Add azure cognitive health tool (#13448 ) - Description: This change adds an agent to the Azure Cognitive Services toolkit for identifying healthcare entities - Dependencies: azure-ai-textanalytics (Optional) --------- Co-authored-by: James Beck <James.Beck@sa.gov.au> Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
Massimiliano Pronesti	6bf9b2cb51	BUG: Limit Azure OpenAI embeddings chunk size (#13425 ) Hi! This short PR aims at: * Fixing `OpenAIEmbeddings`' check on `chunk_size` when used with Azure OpenAI (thus with openai < 1.0). Azure OpenAI embeddings support at most 16 chunks per batch, I believe we are supposed to take the min between the passed value/default value and 16, not the max - which, I suppose, was introduced by accident while refactoring the previous version of this check from this other PR of mine: #10707 * Porting this fix to the newest class (`AzureOpenAIEmbeddings`) for openai >= 1.0 This fixes #13539 (closed but the issue persists). @baskaryan @hwchase17	9 months ago
Zeyang Lin	e53f59f01a	DOCS: doc-string - langchain.vectorstores.dashvector.DashVector (#13502 ) - Description: There are several mistakes in the sample code in the doc-string of `DashVector` class, and this pull request aims to correct them. The correction code has been tested against latest version (at the time of creation of this pull request) of: `langchain==0.0.336` `dashvector==1.0.6` . - Issue: No issue is created for this. - Dependencies: No dependency is required for this change, <!-- - Tag maintainer: for a quicker response, tag the relevant maintainer (see below), --> - Twitter handle: `zeyanglin` <!-- 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. -->	9 months ago
John Mai	16f7912e1b	BUG: fix hunyuan appid type (#13496 ) - Description: fix hunyuan appid type - Issue: https://github.com/langchain-ai/langchain/pull/12022#issuecomment-1815627855	9 months ago
Leonid Ganeline	43972be632	docs updating `AzureML` notebooks (#13492 ) - Added/updated descriptions and links --------- Co-authored-by: Erick Friis <erick@langchain.dev>	9 months ago
Nicolò Boschi	8362bd729b	AstraDB: use includeSimilarity option instead of $similarity (#13512 ) - Description: AstraDB is going to deprecate the `$similarity` projection property in favor of the ´includeSimilarity´ option flag. I moved all the queries to the new format. - Tag maintainer: @hemidactylus - Twitter handle: nicoloboschi	9 months ago
shumpei	7100d586ef	Introduce search_kwargs for Custom Parameters in BingSearchAPIWrapper (#13525 ) Added a `search_kwargs` field to BingSearchAPIWrapper in `bing_search.py,` enabling users to include extra keyword arguments in Bing search queries. This update, like specifying language preferences, adds more customization to searches. The `search_kwargs` seamlessly merge with standard parameters in `_bing_search_results` method. --------- Co-authored-by: Erick Friis <erick@langchain.dev>	9 months ago
Nicolò Boschi	ad0c3b9479	Fix Astra integration tests (#13520 ) - Description: Fix Astra integration tests that are failing. The `delete` always return True as the deletion is successful if no errors are thrown. I aligned the test to verify this behaviour - Tag maintainer: @hemidactylus - Twitter handle: nicoloboschi --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
umair mehmood	69d39e2173	fix: VLLMOpenAI -- create() got an unexpected keyword argument 'api_key' (#13517 ) The issue was accuring because of `openai` update in Completions. its not accepting `api_key` and 'api_base' args. The fix is we check for the openai version and if ats v1 then remove these keys from args before passing them to `Compilation.create(...)` when sending from `VLLMOpenAI` Fixed: #13507 @eyu @efriis @hwchase17 --------- Co-authored-by: Erick Friis <erick@langchain.dev>	9 months ago
Manuel Alemán Cueto	6bc08266e0	Fix for oracle schema parsing stated on the issue #7928 (#13545 ) - Description: In this pull request, we address an issue related to assigning a schema to the SQLDatabase class when utilizing an Oracle database. The current implementation encounters a bug where, upon attempting to execute a query, the alter session parse is not appropriately defined for Oracle, leading to an error, - Issue: #7928, - Dependencies: No dependencies, - Tag maintainer: @baskaryan, --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
Andrew Teeter	325bdac673	feat: load all namespaces (#13549 ) - Description: This change allows for the `MWDumpLoader` to load all namespaces including custom by default instead of only loading the [default namespaces](https://www.mediawiki.org/wiki/Help:Namespaces#Localisation). - Tag maintainer: @hwchase17	9 months ago
Taranjeet Singh	47451764a7	Add embedchain retriever (#13553 ) Description: This commit adds embedchain retriever along with tests and docs. Embedchain is a RAG framework to create data pipelines. Twitter handle: - [Taranjeet's twitter](https://twitter.com/taranjeetio) and [Embedchain's twitter](https://twitter.com/embedchain) Reviewer @hwchase17 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
rafly lesmana	420a17542d	fix: Make YoutubeLoader support on demand language translation (#13583 ) Description: Enhance the functionality of YoutubeLoader to enable the translation of available transcripts by refining the existing logic. Issue: Encountering a problem with YoutubeLoader (#13523) where the translation feature is not functioning as expected. Tag maintainers/contributors who might be interested: @eyurtsev --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	9 months ago
Leonid Ganeline	cc50e023d1	DOCS `langchain decorators` update (#13535 ) added disclaimer --------- Co-authored-by: Erick Friis <erickfriis@gmail.com>	9 months ago
Brace Sproul	02a13030c0	DOCS: updated langchain stack img to be svg (#13540 )	9 months ago
Bagatur	78a1f4b264	bump 338, exp 42 (#13564 )	9 months ago
Bagatur	790ed8be69	update multi index templates (#13569 )	9 months ago
Harrison Chase	f4c0e3cc15	move streaming stdout (#13559 )	9 months ago
Leonid Ganeline	43dad6cb91	BUG fixed `openai_assistant` namespace (#13543 ) BUG: langchain.agents.openai_assistant has a reference as `from langchain_experimental.openai_assistant.base import OpenAIAssistantRunnable` should be `from langchain.agents.openai_assistant.base import OpenAIAssistantRunnable` This prevents building of the API Reference docs	9 months ago
Bassem Yacoube	ff382b7b1b	IMPROVEMENT Adds support for new OctoAI endpoints (#13521 ) small fix to add support for new OctoAI LLM endpoints	9 months ago
Mark Silverberg	cda1b33270	Fix typo/line break in the middle of a word (#13314 ) - Description: a simple typo/extra line break fix - Dependencies: none	9 months ago
William FH	cac849ae86	Use random seed (#13544 ) For default eval llm	9 months ago
Martin Krasser	79ed66f870	EXPERIMENTAL Generic LLM wrapper to support chat model interface with configurable chat prompt format (#8295 ) ## Update 2023-09-08 This PR now supports further models in addition to Lllama-2 chat models. See [this comment](#issuecomment-1668988543) for further details. The title of this PR has been updated accordingly. ## Original PR description This PR adds a generic `Llama2Chat` model, a wrapper for LLMs able to serve Llama-2 chat models (like `LlamaCPP`, `HuggingFaceTextGenInference`, ...). It implements `BaseChatModel`, converts a list of chat messages into the [required Llama-2 chat prompt format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2) and forwards the formatted prompt as `str` to the wrapped `LLM`. Usage example: ```python # uses a locally hosted Llama2 chat model llm = HuggingFaceTextGenInference( inference_server_url="http://127.0.0.1:8080/", max_new_tokens=512, top_k=50, temperature=0.1, repetition_penalty=1.03, ) # Wrap llm to support Llama2 chat prompt format. # Resulting model is a chat model model = Llama2Chat(llm=llm) messages = [ SystemMessage(content="You are a helpful assistant."), MessagesPlaceholder(variable_name="chat_history"), HumanMessagePromptTemplate.from_template("{text}"), ] prompt = ChatPromptTemplate.from_messages(messages) memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True) chain = LLMChain(llm=model, prompt=prompt, memory=memory) # use chat model in a conversation # ... ``` Also part of this PR are tests and a demo notebook. - Tag maintainer: @hwchase17 - Twitter handle: `@mrt1nz` --------- Co-authored-by: Erick Friis <erick@langchain.dev>	9 months ago
William FH	c56faa6ef1	Add execution time (#13542 ) And warn instead of raising an error, since the chain API is too inconsistent.	9 months ago
pedro-inf-custodio	0fb5f857f9	IMPROVEMENT WebResearchRetriever error handling in urls with connection error (#13401 ) - Description: Added a method `fetch_valid_documents` to `WebResearchRetriever` class that will test the connection for every url in `new_urls` and remove those that raise a `ConnectionError`. - Issue: [Previous PR](https://github.com/langchain-ai/langchain/pull/13353), - Dependencies: None, - Tag maintainer: @efriis 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.	9 months ago
Piyush Jain	d2335d0114	IMPROVEMENT Neptune graph updates (#13491 ) ## Description This PR adds an option to allow unsigned requests to the Neptune database when using the `NeptuneGraph` class. ```python graph = NeptuneGraph( host='<my-cluster>', port=8182, sign=False ) ``` Also, added is an option in the `NeptuneOpenCypherQAChain` to provide additional domain instructions to the graph query generation prompt. This will be injected in the prompt as-is, so you should include any provider specific tags, for example `<instructions>` or `<INSTR>`. ```python chain = NeptuneOpenCypherQAChain.from_llm( llm=llm, graph=graph, extra_instructions=""" Follow these instructions to build the query: 1. Countries contain airports, not the other way around 2. Use the airport code for identifying airports """ ) ```	9 months ago
William FH	5a28dc3210	Override Keys Option (#13537 ) Should be able to override the global key if you want to evaluate different outputs in a single run	9 months ago
Bagatur	e584b28c54	bump 337 (#13534 )	9 months ago
Wietse Venema	e80b53ff4f	TEMPLATE Add VertexAI Chuck Norris template (#13531 ) <!-- 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: Erick Friis <erick@langchain.dev>	9 months ago
Bagatur	2e2114d2d0	FEATURE: Runnable with message history (#13418 ) Add RunnableWithMessageHistory class that can wrap certain runnables and manages chat history for them.	9 months ago
Bagatur	0fc3af8932	IMPROVEMENT: update assistants output and doc (#13480 )	9 months ago
Bagatur	b4312aac5c	TEMPLATES: Add multi-index templates (#13490 ) One that routes and one that fuses --------- Co-authored-by: Erick Friis <erick@langchain.dev>	9 months ago
Hugues Chocart	35e04f204b	[LLMonitorCallbackHandler] Various improvements (#13151 ) Small improvements for the llmonitor callback handler, like better support for non-openai models. --------- Co-authored-by: vincelwt <vince@lyser.io>	9 months ago
Noah Stapp	c1b041c188	Add Wrapping Library Metadata to MongoDB vector store (#13084 ) Description MongoDB drivers are used in various flavors and languages. Making sure we exercise our due diligence in identifying the "origin" of the library calls makes it best to understand how our Atlas servers get accessed.	9 months ago
Leonid Ganeline	21552628c8	DOCS updated `data_connection` index page (#13426 ) - the `Index` section was missed. Created it. - text simplification --------- Co-authored-by: Erick Friis <erick@langchain.dev>	9 months ago
Guy Korland	7f8fd70ac4	Add optional arguments to FalkorDBGraph constructor (#13459 ) Description: Add optional arguments to FalkorDBGraph constructor Tag maintainer: baskaryan Twitter handle: @g_korland	9 months ago
Leonid Ganeline	e3a5cd7969	docs `integrations/vectorstores/` cleanup (#13487 ) - updated titles to consistent format - added/updated descriptions and links - format heading	9 months ago
Leonid Ganeline	1d2981114f	DOCS updated `async-faiss` example (#13434 ) The original notebook has the `faiss` title which is duplicated in the`faiss.jpynb`. As a result, we have two `faiss` items in the vectorstore ToC. And the first item breaks the searching order (it is placed between `A...` items). - I updated title to `Asynchronous Faiss`.	9 months ago
Erick Friis	9dfad613c2	IMPROVEMENT Allow openai v1 in all templates that require it (#13489 ) - pyproject change - lockfiles	9 months ago
chris stucchio	d7f014cd89	Bug: OpenAIFunctionsAgentOutputParser doesn't handle functions with no args (#13467 ) Description/Issue: When OpenAI calls a function with no args, the args are `""` rather than `"{}"`. Then `json.loads("")` blows up. This PR handles it correctly. Dependencies: None	9 months ago
Yujie Qian	41a433fa33	IMPROVEMENT: add input_type to VoyageEmbeddings (#13488 ) - Description: add input_type to VoyageEmbeddings	9 months ago

... 3 4 5 6 7 ...

6164 Commits (700428593a86531ae0c891096c0d02aabcbc72af) All Branches Search

6164 Commits (700428593a86531ae0c891096c0d02aabcbc72af)

All Branches