Update app.py

app.py

@@ -4,7 +4,7 @@ import requests
 import pandas as pd
 import re
 import sympy as sp
-import wikipedia
+from wikipedia_api import Wikipedia
 from bs4 import BeautifulSoup
 
 # --- Constants ---
@@ -20,13 +20,15 @@ class BasicAgent:
         if not self.api_token:
             raise ValueError("HF_TOKEN environment variable not set.")
         self.headers = {"Authorization": f"Bearer {self.api_token}"}
-        print("BasicAgent initialized with Flan-T5-Base, SymPy, Wikipedia, and DuckDuckGo search.")
+        # Initialize Wikipedia API
+        self.wiki = Wikipedia(language='en', user_agent='Mozilla/5.0')
+        print("BasicAgent initialized with Flan-T5-Base, SymPy, Wikipedia API, and DuckDuckGo search.")
 
     def __call__(self, question: str) -> tuple[str, str]:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        print(f"Question: {question[:50]}...")
         reasoning = []
-        
-        # Step 1: Try to identify if the question is mathematical
+
+        # Step 1: Check for mathematical questions
         is_math = any(keyword in question.lower() for keyword in ["calculate", "solve", "what is", "+", "-", "*", "/", "=", "equation", "how many"])
         if is_math:
             try:
@@ -42,36 +44,37 @@ class BasicAgent:
                     concise_answer = str(result)
                     reasoning.append(f"Math Solver (SymPy): Evaluated expression '{expr}'. Result: {concise_answer}")
                 if concise_answer != "No solution":
-                    print(f"Agent returning concise answer (math): {concise_answer}")
+                    print(f"Returning concise answer (math): {concise_answer}")
                     return concise_answer, "\n".join(reasoning)
             except Exception as e:
                 reasoning.append(f"Math Solver (SymPy) failed: {e}")
 
         # Step 2: Try Wikipedia for factual questions
         try:
-            wikipedia.set_lang("en")
-            key_terms = " ".join(question.split()[:5]).strip("?")  # Use more words for better context
-            wiki_summary = wikipedia.summary(key_terms, sentences=2, auto_suggest=True, parser_features="html.parser")
-            prompt = (
-                f"Question: {question}\n"
-                f"Context: {wiki_summary}\n"
-                "Provide a concise answer (e.g., a number or short phrase) based on the context."
-            )
-            wiki_answer = self._query_llm(prompt)
-            answer_match = re.search(r"Answer: (.*?)(?:\n|$)", wiki_answer, re.DOTALL)
-            if answer_match:
-                concise_answer = answer_match.group(1).strip()
-                wiki_reasoning = wiki_answer if wiki_answer else "No reasoning provided."
+            key_terms = " ".join(question.split()[:5]).strip("?")
+            wiki_page = self.wiki.page(key_terms)
+            if wiki_page.exists():
+                wiki_summary = wiki_page.summary[:500]  # Limit to 500 chars
+                prompt = (
+                    f"Question: {question}\n"
+                    f"Context: {wiki_summary}\n"
+                    "Provide a concise answer (e.g., a number or short phrase) based on the context."
+                )
+                wiki_answer = self._query_llm(prompt)
+                answer_match = re.search(r"Answer: (.*?)(?:\n|$)", wiki_answer, re.DOTALL)
+                if answer_match:
+                    concise_answer = answer_match.group(1).strip()
+                    wiki_reasoning = wiki_answer if wiki_answer else "No reasoning provided."
+                else:
+                    concise_answer = self._extract_concise_answer(wiki_answer)
+                    wiki_reasoning = wiki_answer
+                reasoning.append(f"Wikipedia API: Searched '{key_terms}'. Summary: {wiki_summary[:100]}... Answer: {concise_answer}")
+                print(f"Returning concise answer (Wikipedia): {concise_answer}")
+                return concise_answer, "\n".join(reasoning)
             else:
-                concise_answer = self._extract_concise_answer(wiki_answer)
-                wiki_reasoning = wiki_answer
-            reasoning.append(f"Wikipedia: Searched '{key_terms}'. Summary: {wiki_summary[:100]}... Answer: {concise_answer}")
-            print(f"Agent returning concise answer (Wikipedia): {concise_answer}")
-            return concise_answer, "\n".join(reasoning)
-        except wikipedia.exceptions.DisambiguationError:
-            reasoning.append("Wikipedia: Disambiguation error, multiple results found.")
+                reasoning.append(f"Wikipedia API: No page found for '{key_terms}'.")
         except Exception as e:
-            reasoning.append(f"Wikipedia failed: {e}")
+            reasoning.append(f"Wikipedia API failed: {e}")
 
         # Step 3: Try web search with DuckDuckGo
         try:
@@ -95,7 +98,7 @@ class BasicAgent:
                     concise_answer = self._extract_concise_answer(search_answer)
                     search_reasoning = search_answer
                 reasoning.append(f"Web Search (DuckDuckGo): Searched '{question}'. Answer: {concise_answer}")
-                print(f"Agent returning concise answer (search): {concise_answer}")
+                print(f"Returning concise answer (search): {concise_answer}")
                 return concise_answer, "\n".join(reasoning)
             else:
                 reasoning.append("Web Search (DuckDuckGo): No relevant results found.")
@@ -119,7 +122,7 @@ class BasicAgent:
                 concise_answer = self._extract_concise_answer(full_response)
                 llm_reasoning = full_response
             reasoning.append(f"LLM (Flan-T5-Base): {llm_reasoning}")
-            print(f"Agent returning concise answer (LLM): {concise_answer}")
+            print(f"Returning concise answer (LLM): {concise_answer}")
             return concise_answer, "\n".join(reasoning)
         except Exception as e:
             print(f"Error querying Inference API: {e}")
@@ -155,10 +158,10 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     and displays the results.
     """
     # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")  # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -184,16 +187,16 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
+            print("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
@@ -218,19 +221,19 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
                 "Reasoning": reasoning
             })
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({
-                 "Task ID": task_id,
-                 "Question": question_text,
-                 "Submitted Answer": f"AGENT ERROR: {e}",
-                 "Reasoning": f"Error: {e}"
-             })
+            print(f"Error running agent on task {task_id}: {e}")
+            results_log.append({
+                "Task ID": task_id,
+                "Question": question_text,
+                "Submitted Answer": f"AGENT ERROR: {e}",
+                "Reasoning": f"Error: {e}"
+            })
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission 
+    # 4. Prepare Submission
     submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
@@ -310,7 +313,7 @@ if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")  # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -318,7 +321,7 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:  # Print repo URLs if SPACE_ID is found
         print(f"✅ SPACE_ID found: {space_id_startup}")
         print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
         print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")