API Overview

Rephole provides a simple REST API for code ingestion and semantic search.

Base URL

http://localhost:3000

Endpoints Summary

Method	Endpoint	Description
GET	/health	Health check
POST	/ingestions/repository	Ingest a repository
GET	/jobs/job/:jobId	Get job status
POST	/queries/search/:repoId	Semantic code search (full files)
POST	/queries/search/:repoId/chunk	Search raw code chunks
GET	/jobs/failed	List failed jobs
POST	/jobs/retry/:jobId	Retry a failed job
POST	/jobs/retry/all	Retry all failed jobs

Authentication

Currently, Rephole does not require authentication. For production deployments, we recommend placing it behind a reverse proxy with authentication.

Request Format

All POST endpoints accept JSON:

curl -X POST http://localhost:3000/endpoint \
  -H "Content-Type: application/json" \
  -d '{"key": "value"}'

Response Format

All responses are JSON:

{
  "status": "ok",
  "data": { }
}

Error Responses

Status Code	Description
400	Bad Request - Invalid parameters
404	Not Found - Resource doesn't exist
500	Internal Server Error

Rate Limiting

No rate limiting is enforced by default. For production, configure rate limiting at the reverse proxy level.

Quick Examples

Health Check

curl http://localhost:3000/health

Ingest Repository

curl -X POST http://localhost:3000/ingestions/repository \
  -H "Content-Type: application/json" \
  -d '{
    "repoUrl": "https://github.com/user/repo.git",
    "meta": {"team": "backend"}
  }'

Search Code

# Note: repoId is required in the URL path
curl -X POST http://localhost:3000/queries/search/repo \
  -H "Content-Type: application/json" \
  -d '{"prompt": "How does authentication work?", "k": 5}'