- Step1: Clone the AI_RAG repository from GitHub.
- Step2: Install dependencies with pip install -r requirements.txt.
- Step3: Prepare your document corpus and configure a vector database (e.g., FAISS, Pinecone).
- Step4: Set up embedding and LLM API keys in the config file.
- Step5: Run the indexing script to build the vector store.
- Step6: Execute the query script to send user prompts and receive context-aware responses.