UICJohn/chatglm3

chatglm3

1. Support more llm args.(eg tempreture)

Environment Setup

export CHATGLM_MODEL_ID="./models/chatglm3-6" # model id or local path
export CHATGLM_DTYPE="q4_0" #dtype for quantization (eg. 'q4_0')

Usage

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

pip install -U langchain-cli

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

langchain app new my-app --package chatglm3

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

langchain app add chatglm3

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

from chatglm3 import chain as chatglm3_chain

add_routes(app, chatglm3_chain, path="/chatglm3")

(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/chatglm3/playground

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/chatglm3")