Jina

app.py

@@ -11,7 +11,7 @@ from datetime import datetime
 from typing import List, Dict, Any, Optional, Annotated
 from langgraph.graph import Graph, StateGraph
 from langgraph.prebuilt import ToolNode
-from tools import simple_search
+from tools import simple_search, jina_search_tool
 from openai import OpenAI
 from typing_extensions import TypedDict
 
@@ -26,6 +26,7 @@ print("trial")
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")  # Make sure to set this environment variable
+JINA_API_KEY = os.getenv("JINA_API_KEY")  # Get Jina API key from environment
 
 # Create logs directory if it doesn't exist
 LOGS_DIR = "question_logs"
@@ -190,11 +191,27 @@ Return ONLY a Python dictionary in this exact format, with no other text or expl
             print("\n=== Search Tool ===")
             print(f"Search Query: {state['search_query']}")
             
-            # Use the simplified search function
-            search_results = simple_search(
-                query=state["search_query"],
-                max_results=3
-            )
+            # Try Jina search first, fall back to simple search if it fails
+            search_results = []
+            if JINA_API_KEY:
+                try:
+                    search_results = jina_search_tool(
+                        query=state["search_query"],
+                        api_key=JINA_API_KEY
+                    )
+                    print("Using Jina search results")
+                except Exception as e:
+                    print(f"Jina search failed: {e}, falling back to simple search")
+                    search_results = simple_search(
+                        query=state["search_query"],
+                        max_results=3
+                    )
+            else:
+                print("No Jina API key found, using simple search")
+                search_results = simple_search(
+                    query=state["search_query"],
+                    max_results=3
+                )
             
             print("Search Results:")
             for i, result in enumerate(search_results, 1):
@@ -204,7 +221,8 @@ Return ONLY a Python dictionary in this exact format, with no other text or expl
             state["logs"]["search"] = {
                 "query": state["search_query"],
                 "results": search_results,
-                "timestamp": datetime.now().isoformat()
+                "timestamp": datetime.now().isoformat(),
+                "search_type": "jina" if JINA_API_KEY and search_results else "simple"
             }
             
             state["history"].append({

tools.py

@@ -1,5 +1,7 @@
 from typing import List
 from duckduckgo_search import DDGS
+import requests
+import os
 
 # --- Simple Search Tool ---
 
@@ -21,3 +23,29 @@ def simple_search(query: str, max_results: int = 3) -> List[str]:
             print("Skipping malformed search result:", r, "Error:", e)
 
     return results
+
+# --- Jina Search Tool ---
+
+def jina_search_tool(query: str, api_key: str) -> List[str]:
+    """
+    Perform a web search using Jina AI's s.jina.ai endpoint and retrieve clean, LLM-friendly content.
+    """
+    api_endpoint = f"https://s.jina.ai/{query.replace(' ', '+')}"
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Accept": "application/json",
+        "User-Agent": "Mozilla/5.0"
+    }
+
+    try:
+        response = requests.get(api_endpoint, headers=headers, timeout=10)
+        if response.status_code == 200:
+            data = response.json()
+            contents = [item.get("content", "") for item in data.get("results", [])]
+            return contents
+        else:
+            print(f"Failed to fetch search results: Status code {response.status_code}")
+            return []
+    except Exception as e:
+        print(f"Error fetching search results: {e}")
+        return []