I sent a batch request but the response says it cant do operations on uploaded files. I looked at the storage to view the batch response, batch request and the file uploaded. Everything checks out, the files are uploaded, the file id match but there is the response for the 2 batch prompt concerning 2 different files:
{"id": "batch_req_679989873a108190b6acb6aa255ff44f", "custom_id": "request-1", "response": {"status_code": 200, "request_id": "202b55e62546f97d58636f4347c8fe9c", "body": {"id": "chatcmpl-AurTRsD95NAPCrKNAqs549cMk7mav", "object": "chat.completion", "created": 1738115285, "model": "gpt-4o-2024-08-06", "choices": [{"index": 0, "message": {"role": "assistant", "content": "I'm sorry, I don't have access to external documents or systems to directly analyze specific files, including the one you've referenced with ID: file-6JjfdvLNJygZKpDnKRQwM6. However, I can assist you by explaining how you might manually extract the required metadata and format it into JSON if you can provide the content or details of the file. Alternatively, you can describe the document or provide snippets, and I can guide you on how to categorize it according to the rules provided.", "refusal": null}, "logprobs": null, "finish_reason": "stop"}], "usage": {"prompt_tokens": 2128, "completion_tokens": 107, "total_tokens": 2235, "prompt_tokens_details": {"cached_tokens": 0, "audio_tokens": 0}, "completion_tokens_details": {"reasoning_tokens": 0, "audio_tokens": 0, "accepted_prediction_tokens": 0, "rejected_prediction_tokens": 0}}, "service_tier": "default", "system_fingerprint": "fp_50cad350e4"}}, "error": null}
{"id": "batch_req_679989874d348190a71203023414696b", "custom_id": "request-2", "response": {"status_code": 200, "request_id": "821bc13a918b4a88cf2e93cf8384ee62", "body": {"id": "chatcmpl-AurUR7ciXnVqq34Jd4NJ7iys0O3cf", "object": "chat.completion", "created": 1738115347, "model": "gpt-4o-2024-08-06", "choices": [{"index": 0, "message": {"role": "assistant", "content": "I'm sorry, but I am not able to access specific files or perform actions on uploaded content directly. However, I can help guide you on how to analyze the document based on the metadata requirements and mappings you've provided. If you share the relevant information extracted from the document, I can assist you in formulating the JSON output as per your guidelines.", "refusal": null}, "logprobs": null, "finish_reason": "stop"}], "usage": {"prompt_tokens": 2128, "completion_tokens": 70, "total_tokens": 2198, "prompt_tokens_details": {"cached_tokens": 0, "audio_tokens": 0}, "completion_tokens_details": {"reasoning_tokens": 0, "audio_tokens": 0, "accepted_prediction_tokens": 0, "rejected_prediction_tokens": 0}}, "service_tier": "default", "system_fingerprint": "fp_4691090a87"}}, "error": null}
Has anyone figured out how to get batch requested to work with uploaded files?