Coptic Compass Public API Docs

Explore the public grammar and dictionary APIs in Swagger, then integrate Shenute AI and OCR-backed image context.

Developer Guide OpenAPI JSON Grammar Index Dictionary Search Shenute Endpoint OCR Proxy Shenute UI Grammar Hub

Read-only and versioned responses

Swagger UI plus OpenAPI JSON

Grammar and dictionary endpoints documented

Rights metadata included in the dataset

Shenute AI defaults to the thoth provider

OCR proxy endpoint available at /api/ocr

Image and camera prompts support OCR-backed context

Public consumers should usually start with /api/openapi.json for discovery. Grammar lives at /api/v1/grammar, dictionary search at /api/v1/dictionary/search, Shenute AI at /api/shenute, and OCR requests through /api/ocr.

Dictionary API

Use GET /api/v1/dictionary/search with filters for q, dialect, partOfSpeech, etymology, hasGreek, hasInflections, hasRelatedEntries, exact, limit, and offset. Use the reduced full index at /api/v1/dictionary/search-index.

const response = await fetch(
  "https://www.copticcompass.com/api/v1/dictionary/search?q=ⲙⲟⲓ&dialect=B&partOfSpeech=V&limit=10",
);

const page = await response.json();
const headwords = page.entries.map((entry) => entry.headword);

Shenute AI API

Use POST /api/shenute with a UI-message payload. Supported providers are thoth, openrouter, gemini, and hf. When Hugging Face is rate-limited, the API can fall back to configured alternatives.

const response = await fetch("https://www.copticcompass.com/api/shenute", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    inferenceProvider: "thoth",
    messages: [
      {
        id: "u1",
        role: "user",
        parts: [{ type: "text", text: "Explain this Coptic phrase." }],
      },
    ],
  }),
});

const result = await response.text();

OCR Proxy API

Use POST /api/ocr with multipart form data. Coptic Compass forwards the file to OCR_SERVICE_URL, then returns the upstream OCR response body and content-type to the client. You can pass ?lang=cop (or another language) and set OCR_UPLOAD_FIELD when your backend expects a specific upload field name.

# .env.local
OCR_SERVICE_URL=https://your-ocr-service/upload
# Optional when your backend expects a specific multipart field:
OCR_UPLOAD_FIELD=file

curl -X POST "https://www.copticcompass.com/api/ocr?lang=cop" \
  -F "file=@/path/to/coptic-image.jpg"

# Proxy flow
# 1) Client sends multipart/form-data to /api/ocr
# 2) Coptic Compass forwards to OCR_SERVICE_URL
# 3) Upstream OCR response is returned to the client

Preparing the API docs

Loading the OpenAPI explorer, developer shortcuts, and dataset notes.

Dictionary API

const response = await fetch( "https://www.copticcompass.com/api/v1/dictionary/search?q=ⲙⲟⲓ&dialect=B&partOfSpeech=V&limit=10", ); const page = await response.json(); const headwords = page.entries.map((entry) => entry.headword);

Shenute AI API

const response = await fetch("https://www.copticcompass.com/api/shenute", { method: "POST", headers: { "Content-Type": "application/json" }, body: JSON.stringify({ inferenceProvider: "thoth", messages: [ { id: "u1", role: "user", parts: [{ type: "text", text: "Explain this Coptic phrase." }], }, ], }), }); const result = await response.text();

OCR Proxy API

# .env.local OCR_SERVICE_URL=https://your-ocr-service/upload # Optional when your backend expects a specific multipart field: OCR_UPLOAD_FIELD=file curl -X POST "https://www.copticcompass.com/api/ocr?lang=cop" \ -F "file=@/path/to/coptic-image.jpg" # Proxy flow # 1) Client sends multipart/form-data to /api/ocr # 2) Coptic Compass forwards to OCR_SERVICE_URL # 3) Upstream OCR response is returned to the client