- Clone repository and go to the root directory.
- Use
conda
orpython3 -m venv venv
to create a virtual environment. Activate the virtual environment. - Run
pip install -r requirements.txt
to install all the required dependencies. - Run
python src/run.py
to start ASGI server. - The following are the endpoints exposed from the service (a) POST /flowvision/v1/extract-reading (b) POST /flowvision/v1/feedback
- The API specification will give more details about the request and response structure
- Choose the
Qwen/Qwen2-VL-2B-Instruct
model in the conf/config.yaml file.
- Choose the
gpt-4o
model in the conf/config.yaml file.