This open-source project delivers an efficient emotion classification system built on FastAPI 🚀. It uses a compact, yet highly accurate model running on onnxruntime for rapid CPU-based processing. It is an ideal solution for applications requiring fast and reliable emotion classification without the need for GPU hardware. More details about the model in the model page.

This project functions as the backend supporting the emotion plugin designed for use with PostHog-LLM.

git clone https://github.com/minuva/fast-nlp-text-emotion.git
cd fast-nlp-text-emotion
pip install -r requirements.txt

Run the following command to start the server (from the root directory):

chmod +x ./run.sh
./run.sh

Check config.py for more configuration options.

Run the following command to start the server (the root directory):

docker build --tag emotion .
docker run --network=postlang --network-alias=emotion -p 9612:9612 -it emotion

The network and the network alias are used to allow PostHog-LLM to communicate with the emotion classification service. Since PostHog-LLM is running in a docker container, we connect the two services by adding them to the same network for fast and reliable communication.

curl -X 'POST' \
  'http:https://127.0.0.1:9612/conversation_emotions_plugin' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -d '{
  "llm_input": "I like you.",
  "llm_output": "My apologies."
}'