1. create a .env file
- add the necessary params - "MONGO_URI", "DB", "COLL"
2. Run the encoder.py
- Load the data into mongodb first
3. Run the rag.py
- Run the query to LLM on gemma with vector search on mongo
run colab with t4 - gpu
1. create a .env file
2. Run the encoder.py
3. Run the rag.py
run colab with t4 - gpu