Add FastAPI endpoints for JSON API - /recommend, /health, /evaluate

app.py

@@ -465,9 +465,83 @@ with gr.Blocks(
     )
 
 
+# ============================================================================
+# FASTAPI INTEGRATION FOR API ENDPOINT
+# ============================================================================
+
+from fastapi import FastAPI, Query
+from fastapi.middleware.cors import CORSMiddleware
+from typing import List, Dict, Any
+
+app = FastAPI(
+    title="SHL Assessment Recommendation API",
+    description="AI-powered assessment recommendations using 2-Stage RAG Pipeline",
+    version="2.0.0"
+)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+@app.get("/health")
+def health_check():
+    """Health check endpoint"""
+    return {
+        "status": "healthy",
+        "total_assessments": len(engine.assessments),
+        "model": "SBERT + Cross-Encoder"
+    }
+
+@app.get("/recommend")
+def recommend_api(
+    query: str = Query(..., min_length=3, description="Job description or requirements"),
+    max_results: int = Query(default=10, ge=1, le=10, description="Max results")
+):
+    """Get assessment recommendations as JSON"""
+    results = engine.recommend(query.strip(), max_results=max_results)
+    return {
+        "query": query,
+        "total_results": len(results),
+        "recommendations": results
+    }
+
+@app.get("/evaluate")
+def evaluate_api():
+    """Run evaluation metrics"""
+    test_cases = [
+        {"query": "need Python developer for backend engineering role", "relevant": ["Software Developer", "Coding", "IT Professional"]},
+        {"query": "hiring receptionist to handle customer inquiries", "relevant": ["Customer Service", "Contact Center", "Front Desk"]},
+        {"query": "executive position requiring strategic decisions", "relevant": ["Manager", "Supervisor", "Virtual Assessment"]},
+        {"query": "fresh graduates for analyst trainee program", "relevant": ["Graduate", "Apprentice", "Entry Level"]},
+        {"query": "B2B account executive in enterprise software", "relevant": ["Sales Professional", "Account Manager", "Sales Representative"]},
+    ]
+    
+    results = []
+    for tc in test_cases:
+        recs = engine.recommend(tc["query"], max_results=5)
+        names = [r["name"] for r in recs]
+        # Simple P@1 check
+        p1 = 1.0 if any(rel.lower() in names[0].lower() for rel in tc["relevant"]) else 0.0
+        results.append({"query": tc["query"][:40], "top_result": names[0], "P@1": p1})
+    
+    avg_p1 = sum(r["P@1"] for r in results) / len(results)
+    return {
+        "aggregate": {"mean_P@1": round(avg_p1, 3)},
+        "per_query": results,
+        "total_test_cases": len(test_cases)
+    }
+
+# Mount Gradio app to FastAPI
+app = gr.mount_gradio_app(app, demo, path="/")
+
 # ============================================================================
 # LAUNCH APPLICATION
 # ============================================================================
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)

requirements.txt

@@ -3,3 +3,5 @@ sentence-transformers>=2.2.2
 faiss-cpu>=1.7.4
 numpy>=1.24.0
 torch>=2.0.0
+fastapi>=0.100.0
+uvicorn>=0.23.0