refactor: make Azure Document Intelligence an internal LLAMACLOUD accelerator instead of a standalone ETL service

This commit is contained in:
Anish Sarkar 2026-04-08 03:26:24 +05:30
parent 1fa8d1220b
commit 20fa93f0ba
9 changed files with 200 additions and 85 deletions

View file

@ -20,7 +20,7 @@ AUTH_TYPE=LOCAL
# Allow new user registrations (TRUE or FALSE)
# REGISTRATION_ENABLED=TRUE
# Document parsing service: DOCLING, UNSTRUCTURED, LLAMACLOUD, or AZURE_DI
# Document parsing service: DOCLING, UNSTRUCTURED, or LLAMACLOUD
ETL_SERVICE=DOCLING
# Embedding model for vector search
@ -282,8 +282,7 @@ STT_SERVICE=local/base
# LlamaCloud (if ETL_SERVICE=LLAMACLOUD)
# LLAMA_CLOUD_API_KEY=
# Azure Document Intelligence (if ETL_SERVICE=AZURE_DI)
# Optional: Azure Document Intelligence accelerator (used with LLAMACLOUD)
# AZURE_DI_ENDPOINT=https://your-resource.cognitiveservices.azure.com/
# AZURE_DI_KEY=