@Vapi Support Bot @Vapi I’m encountering the following error when using the query tool to retrieve data from the knowledge base:

{
  "error": {
    "code": 429,
    "message": "Resource has been exhausted (e.g. check quota).",
    "status": "RESOURCE_EXHAUSTED"
  }
}

I am using Gemini 2.0 Flash. Here's the Call ID: 019e2707-51a2-7000-ba90-5598598ed433

Hi Hamza, It looks like the request is running into a 429 RESOURCE_EXHAUSTED error, which generally indicates a quota or rate limit has been reached. Please check the usage limits and quota settings for the configured setup, then try the request again. Best, Akash Customer Support

@hamza-007 I’ve run into similar issues with Vapi tools, especially when querying knowledge bases. A 429 usually means the underlying provider or retrieval layer is hitting a quota/rate limit, so switching models may not fully solve it. My preferred approach is to build the tools outside of Vapi and connect them through a custom endpoint or MCP server. For knowledge-base queries, I usually set up my own vector database and retrieval logic so I have more control over speed, cost, rate limits, and fallback behavior. That setup has been much more reliable for me than relying only on Vapi’s built-in query tools. I’d be happy to help you think through the architecture if you want to go that route.

How to do that. This is handled by Vapi itself, how to bypass Vapi's rate-limited infrastructure?