VAPI•5mo ago

add fine tuned open ai model to vapi

I've created a fine tuned OpenAI model. I'm trying to follow the directions:

Set the custom llm URL to https://api.openai.com/v1.
Assign the custom llm key to the OpenAI key.
Update the model to their model.
Execute a PATCH request to the /assistant endpoint and ensure that model.metadataSendMode is set to off.

Set the custom llm URL to https://api.openai.com/v1.
Assign the custom llm key to the OpenAI key.
Update the model to their model.
Execute a PATCH request to the /assistant endpoint and ensure that model.metadataSendMode is set to off.

Set the custom llm URL to https://api.openai.com/v1.
Assign the custom llm key to the OpenAI key.
Update the model to their model.
Execute a PATCH request to the /assistant endpoint and ensure that model.metadataSendMode is set to off.

Set the custom llm URL to https://api.openai.com/v1.
Assign the custom llm key to the OpenAI key.
Update the model to their model.
Execute a PATCH request to the /assistant endpoint and ensure that model.metadataSendMode is set to off.

I've added the OpenAI key to my profile. In the VAPI UI for the assistant I have added the custom LLM and the model name, however I do NOT see anywhere to "attach the assigned custom llm key to the OpenAI key". Can you guys... add links or something to your docs? Is this not something taht can be done in the UI? Can your documentation reflect that? TBH I have had a terrible experience so far trying to match what the docs say to do vs what to do in the dashboard.

I did ALSO execute the patch request manually. I am seeing a

pipeline-error-custom-llm-401-unauthorized

pipeline-error-custom-llm-401-unauthorized

pipeline-error-custom-llm-401-unauthorized

pipeline-error-custom-llm-401-unauthorized regardless.

add fine tuned open ai model to vapi

Similar Threads

Similar Threads

Similar Threads