feat: add RAG search endpoint with content extraction

- Add /rag/search endpoint for web, news, and image search via SearXNG
- Add /content/extract and /content/extract/batch endpoints
- Add ContentExtractor client using Trafilatura for content extraction
- Enhance HybridRAG web search with full content extraction
- Add Redis caching for search results
- Add new configuration options for search and extraction timeouts

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/routers/content.py

@@ -0,0 +1,132 @@
+"""
+Content extraction router for Library Desk API.
+
+Endpoints for extracting main content from web URLs using Trafilatura.
+"""
+
+import time
+from fastapi import APIRouter, HTTPException, Depends
+import logging
+
+from src.models.content import (
+    ContentExtractionRequest,
+    ContentExtractionResponse,
+    BatchContentExtractionRequest,
+    BatchContentExtractionResponse,
+)
+from src.clients.content_extractor import ContentExtractor
+from src.core.dependencies import verify_api_key
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/content", tags=["Content Extraction"])
+
+
+# Lazy import to avoid circular dependency
+def get_content_extractor() -> ContentExtractor:
+    """Get content extractor instance."""
+    from src.core.dependencies import get_content_extractor as _get_extractor
+    return _get_extractor()
+
+
+@router.post("/extract", response_model=ContentExtractionResponse)
+async def extract_content(
+    request: ContentExtractionRequest,
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Extract main content from a single URL.
+
+    Uses Trafilatura to fetch the URL and extract the main text content,
+    removing navigation, ads, and other boilerplate.
+
+    **Example Request:**
+    ```json
+    {
+        "url": "https://example.com/article",
+        "include_metadata": true,
+        "max_length": 2000
+    }
+    ```
+
+    **Returns:** Extracted content with optional metadata (title, author, date)
+    """
+    start_time = time.time()
+
+    try:
+        extractor = get_content_extractor()
+        result = await extractor.extract(
+            url=request.url,
+            include_metadata=request.include_metadata,
+            max_length=request.max_length
+        )
+
+        extraction_time_ms = int((time.time() - start_time) * 1000)
+
+        return ContentExtractionResponse(
+            result=result,
+            extraction_time_ms=extraction_time_ms
+        )
+
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Content extraction failed: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Content extraction failed")
+
+
+@router.post("/extract/batch", response_model=BatchContentExtractionResponse)
+async def extract_content_batch(
+    request: BatchContentExtractionRequest,
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Extract content from multiple URLs in parallel.
+
+    Processes up to 20 URLs concurrently with per-URL timeouts.
+    Failed extractions are included in results with success=false.
+
+    **Example Request:**
+    ```json
+    {
+        "urls": [
+            "https://example.com/article1",
+            "https://example.com/article2"
+        ],
+        "include_metadata": true,
+        "max_length": 2000
+    }
+    ```
+
+    **Returns:** List of extraction results with success/failure counts
+    """
+    start_time = time.time()
+
+    if not request.urls:
+        raise HTTPException(status_code=400, detail="URLs list cannot be empty")
+
+    try:
+        extractor = get_content_extractor()
+        results = await extractor.extract_batch(
+            urls=request.urls,
+            include_metadata=request.include_metadata,
+            max_length=request.max_length
+        )
+
+        extraction_time_ms = int((time.time() - start_time) * 1000)
+        successful = sum(1 for r in results if r.success)
+        failed = len(results) - successful
+
+        return BatchContentExtractionResponse(
+            results=results,
+            total_urls=len(request.urls),
+            successful=successful,
+            failed=failed,
+            extraction_time_ms=extraction_time_ms
+        )
+
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+    except Exception as e:
+        logger.error(f"Batch content extraction failed: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Batch extraction failed")

src/routers/rag_search.py

@@ -0,0 +1,87 @@
+"""
+RAG search router for Library Desk API.
+
+Endpoints for web, news, and image search with content extraction.
+"""
+
+import httpx
+from fastapi import APIRouter, HTTPException, Depends
+import logging
+
+from src.models.rag_search import RAGSearchRequest, RAGSearchResponse
+from src.services.rag_search_service import RAGSearchService
+from src.core.dependencies import verify_api_key
+
+logger = logging.getLogger(__name__)
+
+router = APIRouter(prefix="/rag", tags=["RAG Search"])
+
+
+# Lazy import to avoid circular dependency
+def get_rag_search_service() -> RAGSearchService:
+    """Get RAG search service instance."""
+    from src.core.dependencies import get_rag_search_service as _get_service
+    return _get_service()
+
+
+@router.post("/search", response_model=RAGSearchResponse)
+async def search(
+    request: RAGSearchRequest,
+    api_key: str = Depends(verify_api_key)
+):
+    """
+    Execute RAG-optimized web search with content extraction.
+
+    Searches via SearXNG and extracts full content from results using
+    Trafilatura. Results are cached in Redis for efficiency.
+
+    **Search Types:**
+    - `web`: General web search (default)
+    - `news`: News articles with recency filtering
+    - `images`: Image search results
+
+    **Example Request:**
+    ```json
+    {
+        "query": "Python async programming best practices",
+        "search_type": "web",
+        "limit": 10,
+        "user": "default"
+    }
+    ```
+
+    **Response includes:**
+    - Full extracted text content per result
+    - Original search snippets
+    - Source domain names
+    - Markdown sources summary for LLM consumption
+
+    **Error Codes:**
+    - 400: Invalid query (empty or too long)
+    - 502: Search provider (SearXNG) error
+    - 504: Search timeout
+    """
+    try:
+        service = get_rag_search_service()
+        response = await service.search(
+            query=request.query,
+            search_type=request.search_type,
+            limit=request.limit,
+            user=request.user
+        )
+        return response
+
+    except ValueError as e:
+        raise HTTPException(status_code=400, detail=str(e))
+
+    except httpx.TimeoutException:
+        logger.error(f"Search timed out for query: {request.query}")
+        raise HTTPException(status_code=504, detail="Search timed out")
+
+    except httpx.HTTPError as e:
+        logger.error(f"Search provider error: {e}")
+        raise HTTPException(status_code=502, detail="Search provider error")
+
+    except Exception as e:
+        logger.error(f"RAG search failed: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail="Search failed")