A Retrieval-Augmented Generation (RAG) chatbot that uses Pinecone as a vector database and Groq for fast LLM inference.
Python | Pinecone | Groq | RAG | LangChain | Streamlit
Documents are processed and converted into embeddings. Pinecone stores and retrieves relevant information from the vector database. The retrieved context is then provided to the Groq-powered LLM to generate an answer.
Semantic Search | Vector Retrieval | Document Question Answering | Context-Aware Responses
This Hugging Face Space is a portfolio showcase of the project. The complete Python RAG application runs separately with its required API services.