langchain

Commit Graph

Author	SHA1	Message	Date
Juan Carlos José Camacho	450c458f8f	community[minor]: Add Datahareld tool (#19680 ) Description: Integrate [dataherald](https://www.dataherald.com) tool, It is a natural language-to-SQL tool. Dependencies: Install dataherald sdk to use it, ``` pip install dataherald ``` --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Christophe Bornet <cbornet@hotmail.com>	6 months ago
Alexander Smirnov	ece008f117	docs: Refine RunnablePassthrough docstring (#19812 ) Description: This update refines the documentation for `RunnablePassthrough` by removing an unnecessary import and correcting a minor syntactical error in the example provided. This change enhances the clarity and correctness of the documentation, ensuring that users have a more accurate guide to follow. Issue: N/A Dependencies: None This PR focuses solely on documentation improvements, specifically targeting the `RunnablePassthrough` class within the `langchain_core` module. By clarifying the example provided in the docstring, users are offered a more straightforward and error-free guide to utilizing the `RunnablePassthrough` class effectively. As this is a documentation update, it does not include changes that require new integrations, tests, or modifications to dependencies. It adheres to the guidelines of minimal package interference and backward compatibility, ensuring that the overall integrity and functionality of the LangChain package remain unaffected. Thank you for considering this documentation refinement for inclusion in the LangChain project.	6 months ago
Egor Krasheninnikov	c8391d4ff1	community[patch]: Fix YandexGPT embeddings (#19720 ) Fix of YandexGPT embeddings. The current version uses a single `model_name` for queries and documents, essentially making the `embed_documents` and `embed_query` methods the same. Yandex has a different endpoint (`model_uri`) for encoding documents, see [this](https://yandex.cloud/en/docs/yandexgpt/concepts/embeddings). The bug may impact retrievers built with `YandexGPTEmbeddings` (for instance FAISS database as retriever) since they use both `embed_documents` and `embed_query`. A simple snippet to test the behaviour: ```python from langchain_community.embeddings.yandex import YandexGPTEmbeddings embeddings = YandexGPTEmbeddings() q_emb = embeddings.embed_query('hello world') doc_emb = embeddings.embed_documents(['hello world', 'hello world']) q_emb == doc_emb[0] ``` The response is `True` with the current version and `False` with the changes I made. Twitter: @egor_krash --------- Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com> Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
Guangdong Liu	4be7ca7b4c	community[patch]:sparkllm standardize init args (#20194 ) Related to https://github.com/langchain-ai/langchain/issues/20085 @baskaryan	6 months ago
Yuki Oshima	0758da8940	community[patch]: Set default value for _ListSQLDatabaseToolInput tool_input (#20409 ) Description: `_ListSQLDatabaseToolInput` raise error if model returns `{}`. For example, gpt-4-turbo returns `{}` with SQL Agent initialized by `create_sql_agent`. So, I set default value `""` for `_ListSQLDatabaseToolInput` tool_input. This is actually a gpt-4-turbo issue, not a LangChain issue, but I thought it would be helpful to set a default value `""`. This problem is discussed in detail in the following Issue. Issue: https://github.com/langchain-ai/langchain/issues/20405 Dependencies: none Sorry, I did not add or change the test code, as tests for this components was not exist . However, I have tested the following code based on the [SQL Agent Document](https://python.langchain.com/docs/use_cases/sql/agents/), to make sure it works. ``` from langchain_community.agent_toolkits.sql.base import create_sql_agent from langchain_community.utilities.sql_database import SQLDatabase from langchain_openai import ChatOpenAI db = SQLDatabase.from_uri("sqlite:///Chinook.db") llm = ChatOpenAI(model="gpt-4-turbo", temperature=0) agent_executor = create_sql_agent(llm, db=db, agent_type="openai-tools", verbose=True) result = agent_executor.invoke("List the total sales per country. Which country's customers spent the most?") print(result["output"]) ```	6 months ago
saberuster	160bcaeb93	text-splitters[minor]: Add lua code splitting (#20421 ) - Description: Complete the support for Lua code in langchain.text_splitter module. - Dependencies: No - Twitter handle: @saberuster If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>	6 months ago
ccurme	4b6b0a87b6	groq[patch]: Make stream robust to ToolMessage (#20417 ) ```python from langchain.agents import AgentExecutor, create_tool_calling_agent, tool from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder from langchain_groq import ChatGroq prompt = ChatPromptTemplate.from_messages( [ ("system", "You are a helpful assistant"), ("human", "{input}"), MessagesPlaceholder("agent_scratchpad"), ] ) model = ChatGroq(model_name="mixtral-8x7b-32768", temperature=0) @tool def magic_function(input: int) -> int: """Applies a magic function to an input.""" return input + 2 tools = [magic_function] agent = create_tool_calling_agent(model, tools, prompt) agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True) agent_executor.invoke({"input": "what is the value of magic_function(3)?"}) ``` ``` > Entering new AgentExecutor chain... Invoking: `magic_function` with `{'input': 3}` 5The value of magic\_function(3) is 5. > Finished chain. {'input': 'what is the value of magic_function(3)?', 'output': 'The value of magic\\_function(3) is 5.'} ```	6 months ago
ccurme	38faa74c23	community[patch]: update use of deprecated llm methods (#20393 ) .predict and .predict_messages for BaseLanguageModel and BaseChatModel	6 months ago
Corey Zumar	3a068b26f3	community[patch]: Databricks - fix scope of dangerous deserialization error in Databricks LLM connector (#20368 ) fix scope of dangerous deserialization error in Databricks LLM connector --------- Signed-off-by: dbczumar <corey.zumar@databricks.com>	6 months ago
Bagatur	f1248f8d9a	core[patch]: configurable init params (#20070 ) Proposed fix for #20061. need to test --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
aditya thomas	4f75b230ed	partner[ai21]: masking of the api key for ai21 models (#20257 ) Description: Masking of the API key for AI21 models Issue: Fixes #12165 for AI21 Dependencies: None Note: This fix came in originally through #12418 but was possibly missed in the refactor to the AI21 partner package --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Leonid Ganeline	e512d3c6a6	langchain: `callbacks` imports fix (#20348 ) Replaced all `from langchain.callbacks` into `from langchain_core.callbacks` . Changes in the `langchain` and `langchain_experimental` --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Erick Friis	d83b720c40	templates: readme langsmith not private beta (#20173 )	6 months ago
balloonio	e7b1a44c5b	community[patch]: Invoke callback prior to yielding token fix for Llamafile (#20365 ) - [x] PR title: community[patch]: Invoke callback prior to yielding token fix for Llamafile - [x] PR message: - Description: Invoke callback prior to yielding token in stream method in community llamafile.py - Issue: https://github.com/langchain-ai/langchain/issues/16913 - Dependencies: None - Twitter handle: @bolun_zhang If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.	6 months ago
balloonio	93caa568f9	community[patch]: Invoke callback prior to yielding token fix for HuggingFaceEndpoint (#20366 ) - [x] PR title: community[patch]: Invoke callback prior to yielding token fix for HuggingFaceEndpoint - [x] PR message: - Description: Invoke callback prior to yielding token in stream method in community HuggingFaceEndpoint - Issue: https://github.com/langchain-ai/langchain/issues/16913 - Dependencies: None - Twitter handle: @bolun_zhang If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>	6 months ago
Nicolas	ad04585e30	community[minor]: Firecrawl.dev integration (#20364 ) Added the [FireCrawl](https://firecrawl.dev) document loader. Firecrawl crawls and convert any website into LLM-ready data. It crawls all accessible subpages and give you clean markdown for each. - Description: Adds FireCrawl data loader - Dependencies: firecrawl-py - Twitter handle: @mendableai ccing contributors: (@ericciarla @nickscamara) --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Tomaz Bratanic	a1b105ac00	experimental[patch]: Skip pydantic validation for llm graph transformer and fix JSON response where possible (#19915 ) LLMs might sometimes return invalid response for LLM graph transformer. Instead of failing due to pydantic validation, we skip it and manually check and optionally fix error where we can, so that more information gets extracted	6 months ago
P. Taylor Goetz	9317df7f16	community[patch]: Add "model" attribute to the payload sent to Ollama in `ChatOllama` (#20354 ) Example Ollama API calls: Request without "model": ``` curl --location 'http://localhost:11434/api/chat' \ --header 'Content-Type: application/json' \ --data '{ "messages": [ { "role": "user", "content": "What is the capitol of PA?" } ], "stream": false }' ``` Response: ``` {"error":"model is required"} ``` Request with "model": ``` curl --location 'http://localhost:11434/api/chat' \ --header 'Content-Type: application/json' \ --data '{ "model": "openchat", "messages": [ { "role": "user", "content": "What is the capitol of PA?" } ], "stream": false }' ``` Response: ``` { "eval_duration" : 733248000, "created_at" : "2024-04-11T23:04:08.735766843Z", "model" : "openchat", "message" : { "content" : " The capital city of Pennsylvania is Harrisburg.", "role" : "assistant" }, "total_duration" : 3138731168, "prompt_eval_count" : 25, "load_duration" : 466562959, "done" : true, "prompt_eval_duration" : 1938495000, "eval_count" : 10 } ```	6 months ago
Alex Sherstinsky	fad0962643	community: for Predibase -- enable both Predibase-hosted and HuggingFace-hosted fine-tuned adapter repositories (#20370 )	6 months ago
Eugene Yurtsev	6470b30173	langchain[patch]: Add deprecation warning to extraction chains (#20224 ) Add deprecation warnings to extraction chains	6 months ago
Eugene Yurtsev	b65a1d4cfd	langchain[patch]: Add another unit test for indexing code (#20387 ) Add another unit test for indexing	6 months ago
Erick Friis	29282371db	core: bind_tools interface on basechatmodel (#20360 )	6 months ago
Erick Friis	e6806a08d4	multiple: standard chat model tests (#20359 )	6 months ago
Isak Nyberg	bac9fb9a7c	community: add gpt-4 pricing in callback (#20292 ) Added the pricing for `gpt-4-turbo` and `gpt-4-turbo-2024-04-09` in the callback method. related to issue #17173 https://openai.com/pricing#language-models	6 months ago
Leonid Ganeline	7cf2d2759d	community[patch]: docstrings update (#20301 ) Added missed docstrings. Format docstings to the consistent form.	6 months ago
Eugene Yurtsev	2900720cd3	core[patch]: Update documentation for base retriever (#20345 ) Updating in code documentation for base retriever to direct folks toward the .invoke and .ainvoke methods + explain how to implement	6 months ago
Erick Friis	ec0273fc92	chroma: release 0.1.0 (#20355 )	6 months ago
Erick Friis	da707d0755	chroma: remove relevance score int test (#20346 ) deprecating feature in #20302	6 months ago
Bagatur	6608089030	langchain[patch]: Release 0.1.16 (#20335 )	6 months ago
Eugene Yurtsev	653489a1a9	docs: Update documentation for custom LLMs (#19972 ) Update documentation for customizing LLMs	6 months ago
Bagatur	799714c629	release anthropic, fireworks, openai, groq, mistral (#20333 )	6 months ago
Bagatur	e72330aacc	core[patch]: Release 0.1.42 (#20332 )	6 months ago
ccurme	795c728f71	mistral[patch]: add IDs to tool calls (#20299 ) Mistral gives us one ID per response, no individual IDs for tool calls. ```python from langchain.agents import AgentExecutor, create_tool_calling_agent, tool from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder from langchain_mistralai import ChatMistralAI prompt = ChatPromptTemplate.from_messages( [ ("system", "You are a helpful assistant"), ("human", "{input}"), MessagesPlaceholder("agent_scratchpad"), ] ) model = ChatMistralAI(model="mistral-large-latest", temperature=0) @tool def magic_function(input: int) -> int: """Applies a magic function to an input.""" return input + 2 tools = [magic_function] agent = create_tool_calling_agent(model, tools, prompt) agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True) agent_executor.invoke({"input": "what is the value of magic_function(3)?"}) ``` --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	6 months ago
Eugene Yurtsev	22fd844e8a	community[patch]: Add deprecation warnings to postgres implementation (#20222 ) Add deprecation warnings to postgres implementation that are in langchain-postgres.	6 months ago
Eugene Yurtsev	f02f708f52	core[patch]: For now remove user warning (#20321 ) Remove warning since it creates a lot of noise.	6 months ago
Bagatur	c706689413	openai[patch]: use tool_calls in request (#20272 )	6 months ago
Bagatur	e936fba428	langchain[patch]: agents check prompt partial vars (#20303 )	6 months ago
Bagatur	cb25fa0d55	core[patch]: fix ChatGeneration.text with content blocks (#20294 )	6 months ago
Bagatur	03b247cca1	core[patch]: include tool_calls in ai msg chunk serialization (#20291 )	6 months ago
Erick Friis	0fa551c278	chroma: bump rc, keep optional (#20298 )	6 months ago
Erick Friis	16f8fff14f	chroma: add required fastapi dep to restrict to <1 (#20297 )	6 months ago
Erick Friis	991fd82532	chroma: add optional fastapi dep to restrict to <1 (#20295 )	6 months ago
killind-dev	f8a54d1d73	chroma: Add chroma partner package (#19292 ) Description: Adds chroma to the partners package. Tests & code mirror those in the community package. Dependencies: None Twitter handle: @akiradev0x --------- Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Yuki Watanabe	eef19954f3	core[patch]: fix duplicated kwargs in `_load_sql_databse_chain` (#19908 ) `kwargs` is specified twice in [this line](`3218463f6a/libs/langchain/langchain/chains/loading.py (L386)`), causing runtime error when passing any keyword arguments.	6 months ago
Nuno Campos	15271ac832	core: mustache prompt templates (#19980 ) Co-authored-by: Erick Friis <erick@langchain.dev>	6 months ago
Leonid Ganeline	4cb5f4c353	community[patch]: import flattening fix (#20110 ) This PR should make it easier for linters to do type checking and for IDEs to jump to definition of code. See #20050 as a template for this PR. - As a byproduct: Added 3 missed `test_imports`. - Added missed `SolarChat` in to __init___.py Added it into test_import ut. - Added `# type: ignore` to fix linting. It is not clear, why linting errors appear after ^ changes. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>	6 months ago
Yuki Oshima	12190ad728	openai[patch]: Fix langchain-openai unknown parameter error with gpt-4-turbo (#20271 ) Description: I fixed langchain-openai unknown parameter error with gpt-4-turbo. It seems that the behavior of the Chat Completions API implicitly changed when using the latest gpt-4-turbo model, differing from previous models. It now appears to reject parameters that are not listed in the [API Reference](https://platform.openai.com/docs/api-reference/chat/create). So I found some errors and fixed them. Issue: https://github.com/langchain-ai/langchain/issues/20264 Dependencies: none Twitter handle: https://twitter.com/oshima_123	6 months ago
ccurme	21c1ce0bc1	update agents to use tool call messages (#20074 ) ```python from langchain.agents import AgentExecutor, create_tool_calling_agent, tool from langchain_anthropic import ChatAnthropic from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder prompt = ChatPromptTemplate.from_messages( [ ("system", "You are a helpful assistant"), MessagesPlaceholder("chat_history", optional=True), ("human", "{input}"), MessagesPlaceholder("agent_scratchpad"), ] ) model = ChatAnthropic(model="claude-3-opus-20240229") @tool def magic_function(input: int) -> int: """Applies a magic function to an input.""" return input + 2 tools = [magic_function] agent = create_tool_calling_agent(model, tools, prompt) agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True) agent_executor.invoke({"input": "what is the value of magic_function(3)?"}) ``` ``` > Entering new AgentExecutor chain... Invoking: `magic_function` with `{'input': 3}` responded: [{'text': '<thinking>\nThe user has asked for the value of magic_function applied to the input 3. Looking at the available tools, magic_function is the relevant one to use here, as it takes an integer input and returns an integer output.\n\nThe magic_function has one required parameter:\n- input (integer)\n\nThe user has directly provided the value 3 for the input parameter. Since the required parameter is present, we can proceed with calling the function.\n</thinking>', 'type': 'text'}, {'id': 'toolu_01HsTheJPA5mcipuFDBbJ1CW', 'input': {'input': 3}, 'name': 'magic_function', 'type': 'tool_use'}] 5 Therefore, the value of magic_function(3) is 5. > Finished chain. {'input': 'what is the value of magic_function(3)?', 'output': 'Therefore, the value of magic_function(3) is 5.'} ``` --------- Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>	6 months ago
Erick Friis	9eb6f538f0	infra, multiple: rc release versions (#20252 )	6 months ago
Bagatur	0d0458d1a7	mistralai[patch]: Pre-release 0.1.2-rc.1 (#20251 )	6 months ago

1 2 3 4 5 ...

3766 Commits (450c458f8f07f1a1493a13a7b29f17b84820f90d)