#can we use resonse_format in runs of a assistant ai thread
1 messages · Page 1 of 1 (latest)
Hi @wind heron. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Yes, you can use the response_format parameter in the Assistants API. This parameter is available on the Assistants or Run objects. It allows you to define the format of the response from the assistant. The response format can be defined as text, json_object, or json_schema.
However, it's important to note that if you create a thread and run it with an assistant, and then take the threadId and run it with a different assistant, the second assistant will still use the response format defined on the first assistant, even if you defined a specific response format on the second assistant. This is the expected behavior as per the OpenAI community post (https://community.openai.com/t/972205).
For more details on how to use the response_format parameter, you can refer to the OpenAI API documentation (https://platform.openai.com/docs/api-reference).