Chat Completion Inspector

Inspect what request is being made to LLM endpoints under the hood Check the medium article Chat Completion Inspector: Debugging LLM Interactions for more details.

Install dependencies

Install uv

Install uv (if not already installed):

curl -LsSf https://astral.sh/uv/install.sh | sh
source $HOME/.local/bin/env

Install dependencies

After cloning the repository, install the dependencies like this

uv sync

Running the inspector API

Running Inspector API

uv run openai_inspector_server.py

Then every request made to the LLM endpoints will be logged by the inspector API to json file in the root directory.

Running the sample agent

To test if everything is working correctly, you can run the sample agent:

uv run sample_langgraph_agent.py