Add FastAPI query endpoint with Pydantic request validation and health check

requirements.txt

@@ -33,4 +33,8 @@ redis>=5.0.0
 
 # General
 numpy>=2.4.0
-torch>=2.11.0
+torch>=2.11.0
+
+# FastAPI
+fastapi>=0.110.0
+uvicorn>=0.29.0

src/agent/graph.py

@@ -35,4 +35,4 @@
 graph.set_finish_point("assembly")
 
 # Compile
-app = graph.compile()
+agent = graph.compile()

src/api/main.py

@@ -0,0 +1,35 @@
+from fastapi import FastAPI, HTTPException
+from contextlib import asynccontextmanager
+from src.agent.graph import agent
+from pydantic import BaseModel
+
+class QueryRequest(BaseModel):
+    query: str
+
+@asynccontextmanager
+async def lifespan(app):
+    yield
+app = FastAPI(lifespan=lifespan)
+
+@app.post("/query")
+async def query(request: QueryRequest):
+    try:
+        result = agent.invoke({
+            "query": request.query,
+            "search_query": None,
+            "cache_hit": False,
+            "abstracts": [],
+            "llm_response": None,
+            "claims": None,
+            "scored_claims": None,
+            "confidence_score": None,
+            "final_response": None
+        })
+
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Inference failed: {str(e)}")
+
+@app.get("/health")
+async def health():
+    return {"status": "ok"}

tests/pipeline_runner.py

@@ -1,8 +1,8 @@
-from src.agent.graph import app
+from src.agent.graph import agent
 import sys
 
 def main():
-    result = app.invoke({
+    result = agent.invoke({
         "query": "What are the first line treatments for atrial fibrillation?",
         "cache_hit": False,
         "abstracts": [],