README.md

metadata

title: Church Fathers Commentary Search API
emoji: ✝️
colorFrom: purple
colorTo: blue
sdk: docker
pinned: false
license: mit

Church Fathers Commentary Search API

Semantic search over Church Fathers' New Testament commentaries using BGE-large embeddings. This API keeps the model and embeddings in memory for fast responses (~50-100ms after initial load).

Features

• ✅ Fast semantic search with BGE-large-en-v1.5 embeddings
• ✅ Model stays loaded in memory (no cold starts)
• ✅ Searches commentaries from 9 prominent Church Fathers
• ✅ Filter by book or father
• ✅ CORS enabled for easy integration
• ✅ RESTful JSON API with FastAPI
• ✅ Automatic API documentation at /docs

API Endpoints

GET /

Health check and API information

GET /health

Detailed health status, available books, and fathers

POST /search

Perform semantic search over commentaries

Request Body:

{
  "query": "What did the fathers say about baptism?",
  "limit": 10,
  "books": ["matthew", "john"],  // Optional: filter by books
  "fathers": ["Augustine of Hippo"]  // Optional: filter by fathers
}

Response:

{
  "query": "What did the fathers say about baptism?",
  "results": [
    {
      "book": "matthew",
      "father_name": "Augustine of Hippo",
      "source_title": "Tractates on the Gospel of John",
      "content": "Commentary text here...",
      "similarity": 0.892,
      "location_start": "Mt 3:13",
      "location_end": "Mt 3:17"
    }
  ],
  "total_searched": 4523,
  "execution_time_ms": 87.3
}

Available Church Fathers

• Augustine of Hippo
• Athanasius of Alexandria
• Basil of Caesarea
• Gregory of Nazianzus
• Gregory of Nyssa
• Cyril of Alexandria
• Irenaeus
• Cyprian
• Origen of Alexandria

Available Books

All 27 New Testament books: matthew, mark, luke, john, acts, romans, 1corinthians, 2corinthians, galatians, ephesians, philippians, colossians, 1thessalonians, 2thessalonians, 1timothy, 2timothy, titus, philemon, hebrews, james, 1peter, 2peter, 1john, 2john, 3john, jude, revelation

Quick Start

Using cURL

curl -X POST https://dssjon-biblos-cf-api.hf.space/search \
  -H "Content-Type: application/json" \
  -d '{
    "query": "grace and faith",
    "limit": 5
  }'

Using JavaScript

const response = await fetch('https://dssjon-biblos-cf-api.hf.space/search', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    query: 'grace and faith',
    limit: 5,
    books: ['romans', 'ephesians']
  })
})

const data = await response.json()
console.log(data.results)

Using Python

import requests

response = requests.post(
    'https://dssjon-biblos-cf-api.hf.space/search',
    json={
        'query': 'grace and faith',
        'limit': 5,
        'fathers': ['Augustine of Hippo']
    }
)

data = response.json()
print(data['results'])

Interactive Documentation

Visit /docs on your deployed Space for interactive Swagger UI documentation where you can test the API directly.

Performance

• First request: ~2-3 seconds (model loading)
• Subsequent requests: 50-100ms (model already in memory)
• No cold starts after initial load
• Supports concurrent requests

Model Information

• Model: BAAI/bge-large-en-v1.5
• Embedding dimensions: 1024
• Commentary sources: Historical Christian Faith Commentaries Database

Data Source

The commentaries are sourced from the Historical Christian Faith Commentaries Database, an open-source collection of manually curated commentary texts from early Church Fathers.

Deployment

This Space uses Docker SDK with FastAPI. The model and embeddings are loaded once at startup and kept in memory for fast responses.

Local Development

1. Prepare data:

python prepare_data.py --source ../church-fathers/commentary_embeddings

2. Install dependencies:

pip install -r requirements.txt

3. Run locally:

uvicorn app:app --reload

4. Visit http://localhost:8000/docs for interactive API documentation

License

MIT License - Free to use for any purpose

Acknowledgments

• Historical Christian Faith Commentaries Database for the original commentary data
• Hugging Face and the BGE team for the embedding model
• Anthropic Claude for assisting with development