Metadata-Version: 2.4
Name: model_controller
Version: 1.0.0
Summary: AI-powered Git analysis tool using Gemini AI
Project-URL: Documentation, https://github.com/model_controller/model_controller#readme
Project-URL: Issues, https://github.com/model_controller/model_controller/issues
Author: Vumit Contributors
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.9
Classifier: Topic :: Software Development :: Version Control :: Git
Requires-Python: >=3.9
Requires-Dist: click>=8.1.8
Requires-Dist: mlflow==2.13.0
Description-Content-Type: text/markdown

# LM Serving


### Setup environment variables
- Create file `.env` in the root directory with the following content `template.env`
- Update the `.env` file with your own values

- Run:
```bash
source .env
```

### Run with Docker (deployment phase)

_Notice that all processes below will be run inside a Docker container!_

- `make build`: Build Docker image LMDeploy
- `make up_server`: Up LMDeploy server serving model InternVL
- `make down_server`: Down LMDeploy server

### Inference with API Client

- Requirements:
  - Python 3.8
  
  - Install dependencies:
```bash
pip3 install -r requirement/requirements-dev.txt
```


```python

python3 client/main.py --image-urls <IMAGE1_URL> <IMAGE2_URL> --prompt <PROMPT> --api-key <API_KEY>

python3 client/main.py --image-paths <IMAGE1_PATH> <IMAGE2_PATH> --prompt <PROMPT>  --api-key <API_KEY> # For local image path
```