This is a simple Python application built with:
- Python 3.11 Install python
- Conda How to download Ananaconda
- CUDA 11.8 Download Cuda kit
- Ollama Download Ollama
To install the required dependencies, it's recommended to create a new Conda environment:
conda create -p venv python==3.11 -y
conda activate venv/
Install other dependencies
pip install -r requirements.txt
I have used a custom LLM from Gemma-7b-it-GGUF
Invoke-WebRequest -Uri "https://huggingface.co/mlabonne/gemma-7b-it-GGUF/resolve/main/gemma-7b-it.Q5_K_M.gguf" -OutFile "./model/llm/gemma-7b-it.Q5_K_M.gguf"
- Use the Modelfile.txt to add into Ollama list of models.
- Run the following commands in the terminal.
ollama create gemma-updated -f ./models/modelfile.txt
-
For FastAPI
python main.py
-
Using Chainlit
- For ConversationalChain
chainlit run app.py
- For LCEL
chainlit run test-app.py