Cant Get Assistant
# support
e
const prompt = $('Prompt + First_Message').first().json.prompt; const first_message = $('Prompt + First_Message').first().json.first_message; const transfer_tool = $input.first().json.transfer_tool; const assistant = { "name": "Sky", "voice": { "provider": "vapi", "voiceId": "Cole", "language": "en" }, "transcriber": { "provider": "deepgram", "model": "nova-3", "language": "en", "numerals": true, "endpointing": 300, "confidenceThreshold": 0.4 }, "model": { "provider": "cerebras", "model": "llama-3.3-70b", "temperature": 0.5, "semanticCachingEnabled": true, "knowledgeBaseId": "cc289a69-d48c-4581-8c09-0000000000", "tools": [transfer_tool], "messages": [ { "role": "system", "content": prompt } ] }, "firstMessage": first_message, "firstMessageMode": "assistant-speaks-first", "serverMessages": ["end-of-call-report", "status-update", "hang", "function-call"], "clientMessages": [ "transcript", "hang", "function-call", "speech-update", "metadata", "transfer-update", "conversation-update", "workflow.node.started" ], "backgroundSound": "https://www.soundjay.com/ambient/sounds/people-in-lounge-1.mp3", "backgroundDenoisingEnabled": true, "backchannelingEnabled": true, "voicemailMessage": "Please call back when you're available.", "endCallMessage": "Goodbye.", "startSpeakingPlan": { "waitSeconds": 0.6, "smartEndpointingEnabled": "livekit" }, "silenceTimeoutSeconds": 20, "maxDurationSeconds": 450, "modelOutputInMessagesEnabled": false, "hipaaEnabled": false }; return { assistant };
v
Hi there! I see you're experiencing a "Cant Get Assistant" error with your Vapi configuration. Let me help troubleshoot this issue. I'm unable to determine the exact cause without specific error logs, but I can definitely help identify potential issues in your configuration that might be causing this error. Based on the information I found, here are some potential issues and troubleshooting steps: ### Configuration Issues 1.
semanticCachingEnabled
Setting
According to the [documentation](https://discord.com/channels/1211482211119796234/1211483291191083018), the
semanticCachingEnabled
setting was removed from Vapi because it used data from previous conversations. Your configuration has this set to
true
, which might be causing issues. 2. Knowledge Base ID The knowledge base ID in your configuration (
"cc289a69-d48c-4581-8c09-0000000000"
) appears to be incomplete or possibly invalid. Ensure this ID correctly references an existing knowledge base. 3. Assistant ID Configuration The "Cant Get Assistant" error often indicates an issue with the assistant ID configuration. According to [troubleshooting information](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1336652401733668864), you should "ensure that the assistant ID is correctly set on your phone number." ### General Troubleshooting Steps 1. Check Server URL Ensure your server URL is correctly configured and accessible. The [documentation](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1296435541952303124) indicates that a server URL is typically required for the assistant to know where to send and receive data. 2. Review Debugging Artifacts Check the debugging artifacts sent to your server for more detailed information on the error, as suggested in the [troubleshooting guide](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1336652401733668864). 3. Verify API Keys and Access
Double-check all API keys and access permissions for each component (voice, transcriber, model). 4. Check Recent Changes Review any recent changes to your Vapi configuration that might have introduced this issue. 5. Examine Vapi Logs Look into your organization's Vapi logs for any error messages or warnings related to this issue. 6. Verify Dynamic Variables Ensure that the dynamic variables (
$('Prompt + First_Message')
and
$input.first()
) are correctly configured and handled. Is there any specific part of the configuration you'd like me to focus on, or do you have any error logs you can share for more targeted troubleshooting? Sources: - [Vapi assistant configuration troubleshooting](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1336652401733668864) - [Common issues when configuring Vapi assistant](https://discord.com/channels/1211482211119796234/1211483291191083018) - [Vapi assistant model configuration troubleshooting](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1296435541952303124)
e
@Vapi Support Bot why isnt this working? const prompt = $('Prompt + First_Message').first().json.prompt; const first_message = $('Prompt + First_Message').first().json.first_message; const transfer_tool = $input.first().json.transfer_tool; const assistant = { "name": "Sky", "voice": { "provider": "vapi", "voiceId": "Cole", "language": "en" }, "transcriber": { "provider": "deepgram", "model": "nova-3", "language": "en", "numerals": true, "endpointing": 300, "confidenceThreshold": 0.4 }, "model": { "provider": "cerebras", "model": "llama-3.3-70b", "temperature": 0.5, "knowledgeBaseId": "cc289a69-d48c-4581-8c09-576709f3dce9", // Added back the knowledge base "tools": [transfer_tool], "messages": [ { "role": "system", "content": prompt } ] }, "firstMessage": first_message, "firstMessageMode": "assistant-speaks-first", "serverMessages": ["end-of-call-report", "status-update", "hang", "function-call"], "clientMessages": [ "transcript", "hang", "function-call", "speech-update", "metadata", "transfer-update", "conversation-update", "workflow.node.started" ], "backgroundSound": "https://www.soundjay.com/ambient/sounds/people-in-lounge-1.mp3", "backgroundDenoisingEnabled": true, "backchannelingEnabled": true, "voicemailMessage": "Please call back when you're available.", "endCallMessage": "Goodbye.", "startSpeakingPlan": { "waitSeconds": 0.6, "smartEndpointingEnabled": "livekit" }, "silenceTimeoutSeconds": 20, "maxDurationSeconds": 450, "modelOutputInMessagesEnabled": false, "hipaaEnabled": false }; return { assistant };
v
Could you please share any specific error messages you're receiving in the logs? I notice you've made some changes to your configuration, particularly: 1. You've removed the
semanticCachingEnabled
setting
which was a good step since this setting has been [removed from Vapi](https://discord.com/channels/1211482211119796234/1211483291191083018). 2. You've updated the knowledge base ID to what appears to be a complete ID now. To better troubleshoot your issue, I'd like to understand more about: - Are you receiving any specific error messages in your Vapi logs? - How are you defining the dynamic variables (
$('Prompt + First_Message')
and
$input.first().json.transfer_tool
)? These variables need to be properly defined before they're used in your configuration. - Is this configuration part of a workflow or are you using it directly with a phone number? - Have you verified that the assistant ID is correctly set on your phone number as mentioned in the [troubleshooting guide](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1336652401733668864)? Sources: - [Vapi assistant configuration troubleshooting](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1336652401733668864) - [Common issues when configuring Vapi assistant](https://discord.com/channels/1211482211119796234/1211483291191083018)
k
Hey Eric, could you describe what help exactly you're looking out for and where you are currently blocked? What stuff you've taken to unblock yourself?