Step 1. Create a virtual environment
conda create -p myenv python=3.9 -y
step 2. Activate the environment:
conda activate myenv/
step 3. Install all the requirements:
pip install -r requirements.txt
step 4. start writing the code, with standard file name as main.py
- Upload the PDF Files
- Extract the content from the PDF
- Split content into Chunk
- Do Embeddings of the data (Download embeddings from the OpenAI)
- Store Data into Vector Store (eg: FAISS and Croma)
- User can pass a Prompt
- Based on User query, Similarity search will apply
- Get the Output.