I built a system using LlamaIndex to answer questions about pet products (food, treats, medicine) from my list. It works great for those items, but if someone asks about something not in my list, I just get a "not found" message.
Ideally, I'd like a more conversational AI that can:
Search the web for info on products not in my list. Provide general info on the user's query. Avoid "not found" errors for missing items. Would React Agent be a good option for this, or are there other suggestions?
So is this possible to create two tool functions one for retrieving the results from vector database when needed and the other having openai chat completion api and communcating when no product found in the vector db is this possible ? can the agent take that decision when to call which tool function ? Which agent should i use reAct or what ?
