Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from smolagents import DuckDuckGoSearchTool
 import re
+import time
 
 web_search = DuckDuckGoSearchTool()
 
@@ -34,16 +35,22 @@ Never invent information. Cite sources for all facts. Use neutral, academic tone
 """
 
 def process_searches(response):
-    # Preserve thinking tags while processing searches
     formatted_response = response.replace("<thinking>", "\n💭 THINKING PROCESS:\n").replace("</thinking>", "\n")
     searches = re.findall(r'<search>(.*?)</search>', formatted_response, re.DOTALL)
     if searches:
         queries = [q.strip() for q in searches[0].split('\n') if q.strip()]
-        results = []
-        for query in queries:
-            search_result = web_search(query)
-            results.append(f"🔍 SEARCH: {query}\nRESULTS: {search_result}\n")
-        return '\n'.join(results)
+        return queries
+    return None
+
+def search_with_retry(query, max_retries=3, delay=2):
+    for attempt in range(max_retries):
+        try:
+            return web_search(query)
+        except Exception as e:
+            if attempt < max_retries - 1:
+                time.sleep(delay)
+                continue
+            raise
     return None
 
 def respond(
@@ -73,38 +80,54 @@ def respond(
     full_response = ""
     search_cycle = True
     
-    while search_cycle:
-        search_cycle = False
-        
-        completion = client.chat.completions.create(
-            model="Qwen/QwQ-32B",
-            messages=messages,
-            max_tokens=10000,
-            temperature=temperature,
-            top_p=top_p,
-            stream=True
-        )
-        
-        response = ""
-        for chunk in completion:
-            token = chunk.choices[0].delta.content or ""
-            response += token
-            full_response += token
-            # Display thinking tags immediately
-            if "<thinking>" in token.lower() or "</thinking>" in token.lower():
+    try:
+        while search_cycle:
+            search_cycle = False
+            
+            try:
+                completion = client.chat.completions.create(
+                    model="Qwen/QwQ-32B",
+                    messages=messages,
+                    max_tokens=max_tokens,
+                    temperature=temperature,
+                    top_p=top_p,
+                    stream=True
+                )
+            except Exception as e:
+                yield f"⚠️ API Error: {str(e)}\n\nPlease check your HF token and model access."
+                return
+
+            response = ""
+            for chunk in completion:
+                token = chunk.choices[0].delta.content or ""
+                response += token
+                full_response += token
                 yield full_response
-        
-    if search_results:
-        search_cycle = True
-        messages.append({"role": "assistant", "content": response})
-        messages.append({
-            "role": "user",
-            "content": f"SEARCH RESULTS:\n{search_results}\nAnalyze these results..."
-        })
-        # Add this line to display queries
-        full_response += f"\n🔍 SEARCH QUERIES USED:\n{chr(10).join(queries)}\n\n"  # ← NEW
-        full_response += "\n🔍 Analyzing search results...\n"
-        yield full_response
+
+            queries = process_searches(response)
+            
+            if queries:
+                search_cycle = True
+                messages.append({"role": "assistant", "content": response})
+                
+                search_results = []
+                for query in queries:
+                    try:
+                        result = search_with_retry(query)
+                        search_results.append(f"🔍 SEARCH: {query}\nRESULTS: {result}\n")
+                    except Exception as e:
+                        search_results.append(f"⚠️ Search Error: {str(e)}\nQuery: {query}")
+                        time.sleep(2)
+                
+                messages.append({
+                    "role": "user",
+                    "content": f"SEARCH RESULTS:\n{chr(10).join(search_results)}\nAnalyze these results..."
+                })
+                full_response += "\n🔍 Analyzing search results...\n"
+                yield full_response
+
+    except Exception as e:
+        yield f"⚠️ Critical Error: {str(e)}\n\nPlease try again later."
 
 demo = gr.ChatInterface(
     respond,