I want to build a chatbot that can reason over a fairly large codebase for a specific software system and answer support or developer related questions with the entire source code as context. With the current context length limits, what is the best way to build this? Is it still using a vector database to pull in relevant parts into the prompt? Or are there other, better options? I can use GPT-4 Turbo model for this project.

I want to make a chatbot that has access to three different indexes and always queries all of them and synthesizes and answer out of three gpt-4 responses based on each index. How do I query gpt4 directly with a query engine that has no index when sending it the three responses to synthesize?