8 Commits (73da8f863cff5ef6af358ec173572a1a8495baef)

Author	SHA1	Message	Date
Nuno Campos	9cbf14dec2	Fetch runnable config from context var inside runnable lambda and runnable generator (#15334) ... - easier to write custom logic/loops with automatic tracing - if you don't want to streaming support write a regular function and pass to RunnableLambda - if you do want streaming write a generator and pass it to RunnableGenerator ```py import json from typing import AsyncIterator from langchain_core.messages import BaseMessage, FunctionMessage, HumanMessage from langchain_core.agents import AgentAction, AgentFinish from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder from langchain_core.runnables import Runnable, RunnableGenerator, RunnablePassthrough from langchain_core.tools import BaseTool from langchain.agents.output_parsers import OpenAIFunctionsAgentOutputParser from langchain.chat_models import ChatOpenAI from langchain.tools.render import format_tool_to_openai_function def _get_tavily(): from langchain.tools.tavily_search import TavilySearchResults from langchain.utilities.tavily_search import TavilySearchAPIWrapper tavily_search = TavilySearchAPIWrapper() return TavilySearchResults(api_wrapper=tavily_search) async def _agent_executor_generator( input: AsyncIterator[list[BaseMessage]], *, max_iterations: int = 10, tools: dict[str, BaseTool], agent: Runnable[list[BaseMessage], BaseMessage], parser: Runnable[BaseMessage, AgentAction | AgentFinish], ) -> AsyncIterator[BaseMessage]: messages = [m async for mm in input for m in mm] for _ in range(max_iterations): next_message = await agent.ainvoke(messages) yield next_message messages.append(next_message) parsed = await parser.ainvoke(next_message) if isinstance(parsed, AgentAction): result = await tools[parsed.tool].ainvoke(parsed.tool_input) next_message = FunctionMessage(name=parsed.tool, content=json.dumps(result)) yield next_message messages.append(next_message) elif isinstance(parsed, AgentFinish): return def get_agent_executor(tools: list[BaseTool], system_message: str): llm = ChatOpenAI(model="gpt-4-1106-preview", temperature=0, streaming=True) prompt = ChatPromptTemplate.from_messages( [ ("system", system_message), MessagesPlaceholder(variable_name="messages"), ] ) llm_with_tools = llm.bind( functions=[format_tool_to_openai_function(t) for t in tools] ) agent = {"messages": RunnablePassthrough()} | prompt | llm_with_tools parser = OpenAIFunctionsAgentOutputParser() executor = RunnableGenerator(_agent_executor_generator) return executor.bind( tools={tool.name for tool in tools}, agent=agent, parser=parser ) agent = get_agent_executor([_get_tavily()], "You are a very nice agent!") async def main(): async for message in agent.astream( [HumanMessage(content="whats the weather in sf tomorrow?")] ): print(message) if __name__ == "__main__": import asyncio asyncio.run(main()) ``` results in this trace https://smith.langchain.com/public/fa17f05d-9724-4d08-8fa1-750f8fcd051b/r	8 months ago
Nuno Campos	99000c612e	Propagate context vars in all classes/methods (#15329) ... - Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor needs manual handling of context vars <!-- Thank you for contributing to LangChain! Please title your PR "<package>: <description>", where <package> is whichever of langchain, community, core, experimental, etc. is being modified. 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, - **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` from the root of the package you've modified to check this locally. See contribution guidelines for more information on how to write/run tests, lint, etc: https://python.langchain.com/docs/contributing/ 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/docs/integrations` directory. If no one reviews your PR within a few days, please @-mention one of @baskaryan, @eyurtsev, @hwchase17. -->	9 months ago
Nuno Campos	4e4b119614	Fix executor	9 months ago
chyroc	7ce338201c	Patch: improve check openai version (#15301)	9 months ago
Nuno Campos	f7313adf2a	old py compat	9 months ago
Nuno Campos	eb5e250188	Propagate context vars in all classes/methods ... - Any direct usage of ThreadPoolExecutor or asyncio.run_in_executor needs manual handling of context vars	9 months ago
joshy-deshaw	bf5385592e	core, community: propagate context between threads (#15171) ... While using `chain.batch`, the default implementation uses a `ThreadPoolExecutor` and run the chains in separate threads. An issue with this approach is that that [the token counting callback](https://python.langchain.com/docs/modules/callbacks/token_counting) fails to work as a consequence of the context not being propagated between threads. This PR adds context propagation to the new threads and adds some thread synchronization in the OpenAI callback. With this change, the token counting callback works as intended. Having the context propagation change would be highly beneficial for those implementing custom callbacks for similar functionalities as well. --------- Co-authored-by: Nuno Campos <nuno@langchain.dev>	9 months ago
Harrison Chase	d82cbf5e76	Separate out langchain_core package (#13577) ... Co-authored-by: Nuno Campos <nuno@boringbits.io> Co-authored-by: Bagatur <baskaryan@gmail.com> Co-authored-by: Erick Friis <erick@langchain.dev>	10 months ago