Hello. Starting a few days ago my custom knowledge base no longer seems to work. https://dashboard.vapi.ai/calls/2598ae4c-4dbe-4952-99fb-59f147035f5f In logs it says that after 750ms the bot gave up waiting for the knowledge base. Where can I configure this timeout?

Hi there! 👋 I see you're having an issue with your custom knowledge base timing out. I don't have specific information on how to directly configure the 750ms timeout you're seeing in your logs. However, I can share what I know about timeout settings for knowledge bases in Vapi. According to the documentation, there are a few timeout-related settings you should know about: 1. The default timeout for assistant requests is 7.5 seconds (7500ms) [according to Discord discussions](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1244742792580694097). 2. There is a

timeoutSeconds

parameter that can be configured in the knowledge base configuration, with a default value of 20 seconds. This appears in the JSON structure for creating phone calls and configuring assistants:

json
{
  "knowledgeBase": {
    "server": {
      "url": "url",
      "timeoutSeconds": 20,
      "backoffPlan": {
        "maxRetries": 0,
        "type": {
          "key": "value"
        },
        "baseDelaySeconds": 1
      }
    }
  },
  "knowledgeBaseId": "knowledgeBaseId"
}

3. Currently, [according to Discord discussions](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1323288623629471866), "there is no way to manually set a large timeout" but the Vapi team is working on adding this ability. 4. You might also want to look into the

waitSeconds

parameter, which some users have set to 0.8 as a good median value. The 750ms timeout you're seeing is significantly shorter than the default timeouts mentioned in the documentation, which suggests there might be another configuration or issue at play. Is there anything else about your custom knowledge base configuration you'd like me to help with? Sources: - [Discord discussion about default timeout](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1244742792580694097)

@Alexandru Bagu was the guide helpful

No

Go to your assistant’s configuration settings where the knowledge base is integrated, locate the knowledge base section in your assistant’s configuration and set the timeout seconds parameter to a value between 20 and 600 seconds, depending on your requirements then save the changes and redeploy your assistant to apply the new settings..

I tried to find those settings but I dont see them anywhere

did you create the knowledgebase with trieve ? or did you do it with vapi (when it was accesible via dashboard?)

🔵 15:43:02:326 \[user LOG\] Knowledge base retrieval aborted. Request took too long. Waited for 750 ms 🔵 15:43:04:015 Couldn't Retrieve Knowledge Base. Error: Custom KB Read Request Aborted. Abort Reason: Knowledge base retrieval timed out. Aborted after 750 ms

{
  "provider": "custom-knowledge-base",
  "server": {
    "url": "https://private-knowledge.bss-lab.it/vapi-query-knowledge/e611875e-9ae2-4292-88f1-155680a8aba2",
    "secret": "AHDnK822UagM9DQ4LzPdoE3MaW3UbhYFq5BnaFaPf4LrJ8KDLpk75NwsAsBseKvq",
    "timeoutSeconds": 10,
    "headers": {},
    "backoffPlan": {
      "maxRetries": 0,
      "type": "fixed",
      "baseDelaySeconds": 0
    }
  }
}

Any idea when this is going to be implemented?

We will ping you when resolved appreciate your patience thanks

Is there an update on this? I've been dealing with the same issue, where the assistant gives up on the knowledge base after 750ms and generates a made-up response to the user's question.

Following - seeing the same issue

Hey guys this issue will be picked in next sprint cycle staring from next week.

hi! i have some problem now, i get error " [LOG] Knowledge base retrieval aborted. Request took too long. Waited for 750 ms". is that some bug or diferent ?

Hey! To help track down this issue, could you share: - The call ID

callid: d0188511-44e2-48ad-b937-c604b76a3109

Hey @Samet, just to confirm this issue is resolved right?

no. Frankly, being stuck at the short system prompt upsets me. Isn't there a way to increase the delay in the response on the Trieve side? I want the assistant to respond late, but only if it responds with data. Do you have a suggestion?

All I can say is to add to roadmap at we will add it soon.