tensorlakeai / indexify

A realtime serving engine for Data-Intensive Generative AI Applications
https://docs.tensorlake.ai
Apache License 2.0
931 stars 121 forks source link

Setup `document_ai_api_version_workflow.py` example which uses the DocumentAI endpoint for PDF Parsing #1045

Closed stangirala closed 1 week ago

stangirala commented 1 week ago

Context

Add DocumentAI example for customer.

What

Add example where the parse step is an API call.

This is a complete example similar to workflow.py. We call OAI to do the structured extraction, and this step should be replaced as needed.

Testing

Local workflow run and as a Remote Graph.

Screenshot 2024-11-20 at 1 00 01 PM

Contribution Checklist