🚀 Dev → Main: feat: integrate vector matching service with candidate and job controllers

README.md

@@ -21,6 +21,10 @@ See [Pipeline Setup Guide](./.github/PIPELINE_SETUP.md) for configuration detail
 - **Candidate Management**: Create, read, update, and delete candidate profiles
 - **Job Position Management**: Manage job postings with detailed requirements
 - **Application Tracking**: Track job applications and their statuses
+- **🚀 AI-Powered Matching**: Semantic search-based candidate-job matching using OpenAI embeddings
+- **Vector Search**: ChromaDB for efficient similarity search and ranking
+- **Smart Filtering**: Metadata-based filtering with location, experience, salary, etc.
+- **Auto-Sync**: Automatic synchronization of candidates and jobs to vector database
 - **Schema Validation**: Robust input validation using Zod
 - **Type Safety**: Full TypeScript implementation with Prisma-generated types
 - **Database Relations**: Properly structured database with foreign key relationships
@@ -34,6 +38,8 @@ See [Pipeline Setup Guide](./.github/PIPELINE_SETUP.md) for configuration detail
 - **Language**: TypeScript
 - **Database**: PostgreSQL
 - **ORM**: Prisma
+- **Vector Database**: ChromaDB
+- **AI/ML**: OpenAI Embeddings API
 - **Validation**: Zod
 - **Development**: Nodemon, ts-node
 
@@ -180,14 +186,26 @@ DATABASE_URL="postgresql://username:password@localhost:5432/database_name?schema
 
 # Server
 PORT=3000
-# Optional: Add other environment-specific variables
+NODE_ENV=development
+
+# OpenAI API (required for AI matching)
+OPENAI_API_KEY=your_openai_api_key_here
+
+# ChromaDB (for vector search)
+CHROMA_HOST=localhost
+CHROMA_PORT=8000
+CHROMA_URL=http://localhost:8000
 ```
 
 ### Environment Variable Descriptions
 
 - `DATABASE_URL`: PostgreSQL connection string
 - `PORT`: Port number for the server (default: 3000)
 - `NODE_ENV`: Environment mode (development, production, test)
+- `OPENAI_API_KEY`: **Required** - OpenAI API key for generating embeddings
+- `CHROMA_HOST`: ChromaDB server host (default: localhost)
+- `CHROMA_PORT`: ChromaDB server port (default: 8000)
+- `CHROMA_URL`: Full ChromaDB server URL
 
 ## Database Setup
 
@@ -211,6 +229,87 @@ npx prisma generate
 npx prisma studio
 ```
 
+## ChromaDB Setup
+
+### Option 1: Docker (Recommended)
+```bash
+# Pull and run ChromaDB
+docker pull chromadb/chroma
+docker run -p 8000:8000 chromadb/chroma
+```
+
+### Option 2: Local Installation
+```bash
+# Install ChromaDB
+pip install chromadb
+
+# Run ChromaDB server
+chroma run --host localhost --port 8000
+```
+
+### Verify ChromaDB is Running
+```bash
+curl http://localhost:8000/api/v1/heartbeat
+```
+
+## AI Matching System
+
+### Initial Setup
+1. **Get OpenAI API Key**: Visit [OpenAI Platform](https://platform.openai.com/) and create an API key
+2. **Add to Environment**: Set `OPENAI_API_KEY` in your `.env` file
+3. **Start ChromaDB**: Ensure ChromaDB is running on port 8000
+4. **Sync Data**: Use the sync endpoints to populate the vector database
+
+### Matching API Endpoints
+
+#### Health Check
+```http
+GET /api/matching/health
+```
+
+#### Find Matching Jobs for Candidate
+```http
+GET /api/matching/candidates/{candidateId}/jobs?limit=10&location=Istanbul&remote_ok=true
+```
+
+#### Find Matching Candidates for Job
+```http
+GET /api/matching/jobs/{jobId}/candidates?limit=10&availability=immediate&min_experience=2
+```
+
+#### Sync Individual Items
+```http
+POST /api/matching/sync/candidates/{candidateId}
+POST /api/matching/sync/jobs/{jobId}
+```
+
+#### Bulk Sync
+```http
+POST /api/matching/sync
+Content-Type: application/json
+
+{
+  "type": "all"  // or "candidates" or "jobs"
+}
+```
+
+### Query Parameters for Job Matching
+- `limit`: Number of results (default: 10)
+- `location`: Filter by location
+- `remote_ok`: Filter by remote work availability (true/false)
+- `experience_level`: Filter by experience level (entry, mid, senior, lead)
+- `employment_type`: Filter by employment type (full_time, part_time, contract, internship)
+- `salary_min`: Minimum salary filter
+- `salary_max`: Maximum salary filter
+
+### Query Parameters for Candidate Matching
+- `limit`: Number of results (default: 10)
+- `location`: Filter by location
+- `availability`: Filter by availability (immediate, within_week, within_month, not_available)
+- `min_experience`: Minimum years of experience
+- `max_experience`: Maximum years of experience
+- `max_salary_expectation`: Maximum salary expectation
+
 ## Running the Application
 
 ### Development Mode