OpenAI Max Token exceeded when uploading files

[quadriano31]

When trying to upload a file using Agent File Search, I encountered the following error in the logs:

openai.BadRequestError: Error code: 400 - {'error': {'message': 'Requested 488585 tokens, max 300000 tokens per request', 'type': 'max_tokens_per_request'}}
LibreChat logs also show:

Error uploading vectors: File embedding failed.
[/files] Error processing file: File embedding failed.

It seems the file exceeds the token limit accepted by the embedding model. Is there a recommended way to handle large files

rag_api | raise self._make_status_error_from_response(err.response) from None
rag_api | openai.BadRequestError: Error code: 400 - {'error': {'message': 'Requested 488585 tokens, max 300000 tokens per request', 'type': 'max_tokens_per_request', 'param': None, 'code': 'max_tokens_per_request'}}
rag_api |
rag_api | 2025-07-11 10:38:28,754 - root - INFO - Request POST http://rag_api:8000/embed - 200
LibreChat | 2025-07-11 10:38:28 error: Error uploading vectors An error occurred while setting up the request: File embedding failed.
LibreChat | 2025-07-11 10:38:28 error: [/files] Error processing file: File embedding failed.

[quadriano31]

Solved.

Set CHUNK_SIZE=300 in the .env file.