Add FastAPI server for PageIndex document indexing service

[MASLER1987]

Summary

This PR introduces a FastAPI-based REST API server for the PageIndex document indexing and retrieval system, along with Docker containerization support.

Key Changes

• New FastAPI server (server.py): Implements a REST API with the following endpoints:

  • GET /health - Health check endpoint
  • GET /documents - List all indexed documents with metadata
  • POST /index - Upload and index PDF or Markdown files
  • GET /documents/{doc_id} - Retrieve document metadata
  • GET /documents/{doc_id}/structure - Get document tree structure
  • GET /documents/{doc_id}/pages - Get page content with flexible page range selection (e.g., '5-7', '3,8', '12')

• Docker support: Added Dockerfile for containerized deployment with Python 3.11-slim base image

• Railway deployment config (railway.toml): Configured for Railway.app deployment with health checks and restart policies

• Dependencies: Updated requirements.txt to include FastAPI, Uvicorn, and python-multipart for the new server functionality

Implementation Details

• File upload handling with temporary directory management and proper cleanup
• Support for PDF and Markdown file formats with validation
• JSON response parsing from PageIndexClient with error handling
• Environment variable configuration for workspace and model selection
• Proper HTTP error responses with descriptive messages

https://claude.ai/code/session_01DC8ofq5uXQoG63AMnHNMEw

[claude]

Claude Code Review

This pull request is from a fork — automated review is disabled. A repository maintainer can comment @claude review to run a one-time review.

[MASLER1987]

sorry