jeffemmett
/
docling-service
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Document extraction service using Docling for the AI stack
1 Commit 1 Branch 0 Tags 45 KiB
Python 97.9%
Dockerfile 2.1%
Go to file
Jeff Emmett 4ed909dbc4 Initial docling-service: document extraction for AI stack 
- FastAPI service using IBM Docling for document extraction
- Supports PDF, DOCX, PPTX, XLSX, HTML, images with OCR
- Integrates with AI Orchestrator (Ollama) for summarization
- Routes audio to RunPod Whisper for transcription
- Optional indexing to Semantic Search service
- Docker + Traefik configuration for RS 8000 deployment
- Python client library included

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 		2025-11-26 20:47:42 -08:00
.env.example Initial docling-service: document extraction for AI stack 2025-11-26 20:47:42 -08:00
.gitignore Initial docling-service: document extraction for AI stack 2025-11-26 20:47:42 -08:00
Dockerfile Initial docling-service: document extraction for AI stack 2025-11-26 20:47:42 -08:00
client.py Initial docling-service: document extraction for AI stack 2025-11-26 20:47:42 -08:00
docker-compose.yml Initial docling-service: document extraction for AI stack 2025-11-26 20:47:42 -08:00
requirements.txt Initial docling-service: document extraction for AI stack 2025-11-26 20:47:42 -08:00
server.py Initial docling-service: document extraction for AI stack 2025-11-26 20:47:42 -08:00