Upload 47 files

app/api/routes/search.py

@@ -4,7 +4,7 @@ import json
 import time
 from datetime import datetime
 
-from fastapi import APIRouter, HTTPException
+from fastapi import APIRouter, HTTPException, Request
 from fastapi.responses import StreamingResponse
 
 from app.api.schemas import (
@@ -23,6 +23,7 @@ from app.sources.tavily import search_tavily
 from app.sources.duckduckgo import search_duckduckgo
 from app.reranking.pipeline import rerank_results
 from app.agents.synthesizer import synthesize_answer, synthesize_answer_stream
+from app.middleware.rate_limiter import limiter
 
 router = APIRouter()
 
@@ -34,7 +35,8 @@ router = APIRouter()
     summary="Search with AI synthesis",
     description="Perform a search with temporal intelligence and return an AI-synthesized answer.",
 )
-async def search(request: SearchRequest) -> SearchResponse:
+@limiter.limit("30/minute")
+async def search(request: SearchRequest, req: Request) -> SearchResponse:
     """
     Perform an intelligent search with:
     - Temporal intent detection
@@ -262,7 +264,8 @@ async def search_stream(request: SearchRequest):
     summary="Deep research with multi-dimensional analysis",
     description="Decompose a query into dimensions, search each in parallel, and generate a comprehensive report.",
 )
-async def deep_research(request: DeepResearchRequest):
+@limiter.limit("5/minute")
+async def deep_research(request: DeepResearchRequest, req: Request):
     """
     Run deep research with streaming progress updates.
     
@@ -295,7 +298,8 @@ async def deep_research(request: DeepResearchRequest):
     summary="Heavy search with content scraping",
     description="Search with full content extraction from top sources for richer answers.",
 )
-async def heavy_search(request: SearchRequest):
+@limiter.limit("10/minute")
+async def heavy_search(request: SearchRequest, req: Request):
     """
     Heavy search with content scraping.
     
@@ -325,7 +329,8 @@ async def heavy_search(request: SearchRequest):
     summary="Search for images",
     description="Search for images related to a query using Brave Image Search.",
 )
-async def image_search(query: str, max_results: int = 6):
+@limiter.limit("60/minute")
+async def image_search(req: Request, query: str, max_results: int = 6):
     """
     Search for images related to a query.
     

app/main.py

@@ -5,9 +5,12 @@ from datetime import datetime
 
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
+from slowapi import _rate_limit_exceeded_handler
+from slowapi.errors import RateLimitExceeded
 
 from app.api.routes import search
 from app.config import get_settings
+from app.middleware.rate_limiter import limiter
 
 
 @asynccontextmanager
@@ -18,6 +21,7 @@ async def lifespan(app: FastAPI):
     print(f"🚀 Lancer API starting...")
     print(f"   LLM Provider: {settings.llm_provider}")
     print(f"   LLM Model: {settings.llm_model}")
+    print(f"   Rate limiting: enabled")
     yield
     # Shutdown
     print("👋 Lancer API shutting down...")
@@ -30,6 +34,10 @@ app = FastAPI(
     lifespan=lifespan,
 )
 
+# Rate limiting
+app.state.limiter = limiter
+app.add_exception_handler(RateLimitExceeded, _rate_limit_exceeded_handler)
+
 # CORS middleware
 app.add_middleware(
     CORSMiddleware,

app/middleware/__init__.py

@@ -0,0 +1 @@
+"""Middleware package."""

app/middleware/rate_limiter.py

@@ -0,0 +1,45 @@
+"""Rate limiting middleware using SlowAPI.
+
+Provides IP-based rate limiting for all API endpoints.
+"""
+
+from slowapi import Limiter
+from slowapi.util import get_remote_address
+from slowapi.errors import RateLimitExceeded
+from slowapi.middleware import SlowAPIMiddleware
+from fastapi import Request
+from fastapi.responses import JSONResponse
+
+
+# Create limiter instance with IP-based key
+limiter = Limiter(
+    key_func=get_remote_address,
+    default_limits=["100/minute"],
+    storage_uri="memory://",  # Use memory storage (OK for single instance on HF Spaces)
+)
+
+
+def rate_limit_exceeded_handler(request: Request, exc: RateLimitExceeded):
+    """Custom handler for rate limit exceeded errors."""
+    return JSONResponse(
+        status_code=429,
+        content={
+            "error": "rate_limit_exceeded",
+            "message": f"Rate limit exceeded: {exc.detail}",
+            "retry_after": getattr(exc, "retry_after", 60),
+        },
+    )
+
+
+# Rate limit decorators for different endpoints
+LIMITS = {
+    "search": "30/minute",
+    "heavy": "10/minute", 
+    "deep": "5/minute",
+    "images": "60/minute",
+}
+
+
+def get_limiter():
+    """Get the limiter instance for dependency injection."""
+    return limiter

pyproject.toml

@@ -20,6 +20,7 @@ dependencies = [
     "numpy>=2.0.0",
     "python-dotenv>=1.0.0",
     "tenacity>=9.0.0",
+    "slowapi>=0.1.9",
 ]
 
 [project.optional-dependencies]