Additional Notes

Google Cloud Storage (GCS): Uploaded PDFs are stored in the specified GCS bucket. Ensure that the service account used has the necessary permissions to upload and download files.
OpenAI Integration: The system uses OpenAI's API for processing PDFs when metadata is provided. Ensure that the OPENAI_API_KEY environment variable is set correctly.
ZeroX Integration: For PDFs without metadata, ZeroX is used to convert PDFs to markdown. Ensure that the ZEROX_MODEL environment variable is set to a valid model.
Environment Variables: Critical configurations such as database URI, GCS credentials, admin credentials, and API keys are managed through environment variables. Ensure these are securely set in your deployment environment.
Background Processing: PDF processing occurs in the background to improve response times. The file_id can be used to query the status and results of the processing task.
Security:
- Passwords are hashed using bcrypt_sha256 before storage.
- API keys are generated with a combination of SHA-256 hashes and random tokens for uniqueness and security.
- Always protect your admin credentials and API keys. Do not expose them in client-side applications or insecure environments.

For any further assistance or questions, please contact the support team.

Last updated 1 year ago