ChatBot with Memory using RAG (Pinecone), OpenAI API.
- I am a chatbot named TEJ. I am a helpful assistant.
- I chat with user and give answer to user's question using LLM (OpenAI Model)
- I will also store conversation in Pinecone vector index
- Then I will provide a detailed answer to new question of user, also keeping in mind previous conversation
- This will give in-context response to the new question asked by the user.
- I will then end my response with a follow-up.