app.py to support PDF, CSV, and DOC files alongside images, as requested.

Made GITHUB_TOKEN variable reusable

Fix use app.py instead.

Refactoring App Structure (#1)

Update app_with_confluence.py

Delete confluence_integration_example_2.py

Delete confluence_integration_example.py

Delete vendor

Update README.md

Update requirements.txt

Migrating Gradio app to Docker-based HF space

Use API asset URL (.assets[0].url) instead of browser_download_url - this requires authentication properly

Remove confluence-ingestor library

The RUN stage with --mount=type=secret successfully authenticates (HTTP 200, token length 40 chars, detects releases array with length 2), extracts the tag, and prints "✅ Release found, continuing...",

Update Dockerfile

Update Dockerfile

Quick test version (add debug)

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update Dockerfile

Update README.md

Update Dockerfile

Update Dockerfile

Update Dockerfile

GITHUB_TOKEN as a build argument

Update Dockerfile

Remove private lib

Update Dockerfile

Update Dockerfile

Add a Dockerfile to repo

Migrate to Docker based space instead of Gradio

Create .space/config.yaml

Try fixing import

Obtain package from GitHub confluence-ingestor repo

Fixed THREE critical issues:

Root Cause: Severe Content Truncation

Update System Prompt to improve LLM behavior

Tweaked code comment

Add additional libraries

Remove phase phrasing

No PyPi install for confluence-ingestor lib yet

Only one requirements file

Now the page titles will be displayed regardless of whether the space is newly ingested or already cached.

Add mock Confluence pages for the 'cquisition-and-Credit-Risk' space, designed specifically to demonstrate the Fraud Model Explainability Assistant with Confluence integration.

Try a different approach for build wheel

Update to confluence_ingestor-0.3.0-py3-none-any.whl version

Add a pip build wheel

Production features: