langchain/templates/xml-agent
Erick Friis 2a7e0a27cb
update lc version (#12655)
also updated py version in `csv-agent` and `rag-codellama-fireworks`
because they have stricter python requirements
2023-10-31 10:19:15 -07:00
..
tests Templates (#12294) 2023-10-25 18:47:42 -07:00
xml_agent improve agent templates (#12528) 2023-10-30 18:15:13 -07:00
LICENSE Templates (#12294) 2023-10-25 18:47:42 -07:00
main.py Templates (#12294) 2023-10-25 18:47:42 -07:00
poetry.lock update lc version (#12655) 2023-10-31 10:19:15 -07:00
pyproject.toml update lc version (#12655) 2023-10-31 10:19:15 -07:00
README.md Readme rewrite (#12615) 2023-10-31 00:06:02 -07:00

xml-agent

This package creates an agent that uses XML syntax to communicate its decisions of what actions to take. It uses Anthropic's Claude models for writing XML syntax and can optionally look up things on the internet using DuckDuckGo.

Environment Setup

Two environment variables need to be set:

  • ANTHROPIC_API_KEY: Required for using Anthropic

Usage

To use this package, you should first have the LangChain CLI installed:

pip install -U "langchain-cli[serve]"

To create a new LangChain project and install this as the only package, you can do:

langchain app new my-app --package xml-agent

If you want to add this to an existing project, you can just run:

langchain app add xml-agent

And add the following code to your server.py file:

from xml_agent import chain as xml_agent_chain

add_routes(app, xml_agent_chain, path="/xml-agent")

(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. LangSmith is currently in private beta, you can sign up here. If you don't have access, you can skip this section

export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"

If you are inside this directory, then you can spin up a LangServe instance directly by:

langchain serve

This will start the FastAPI app with a server is running locally at http://localhost:8000

We can see all templates at http://127.0.0.1:8000/docs We can access the playground at http://127.0.0.1:8000/xml-agent/playground

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/xml-agent")