Update app.py

app.py

@@ -7,15 +7,11 @@ import sympy as sp
 import wikipedia
 from bs4 import BeautifulSoup
 from tenacity import retry, stop_after_attempt, wait_fixed
-import spacy
 from io import StringIO
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Initialize NLP for Question Classification ---
-nlp = spacy.load("en_core_web_sm")
-
 # --- Basic Agent Definition ---
 class BasicAgent:
     def __init__(self):
@@ -27,14 +23,13 @@ class BasicAgent:
         print("BasicAgent initialized with Mixtral-8x7B, SymPy, Wikipedia, and DuckDuckGo search.")
 
     def classify_question(self, question: str) -> str:
-        """Classify question type: math, factual, code, file, or general."""
+        """Classify question type using regex (no SpaCy dependency)."""
         question_lower = question.lower()
-        doc = nlp(question)
-        if any(token.text in ["calculate", "solve", "equation", "sum", "product"] or re.search(r'[\d+\-*/=]', question_lower) for token in doc):
+        if re.search(r'[\d+\-*/=]', question_lower) or any(keyword in question_lower for keyword in ["calculate", "solve", "equation", "sum", "product"]):
             return "math"
-        if any(token.text in ["who", "what", "where", "when", "how many"] for token in doc):
+        if any(keyword in question_lower for keyword in ["who", "what", "where", "when", "how many"]):
             return "factual"
-        if any(token.text in ["code", "python", "program"] or ".py" in question_lower for token in doc):
+        if any(keyword in question_lower for keyword in ["code", "python", "program", ".py"]):
             return "code"
         if any(ext in question_lower for ext in [".xlsx", ".csv", ".pdf"]):
             return "file"
@@ -49,7 +44,6 @@ class BasicAgent:
         # Handle file-based questions (basic CSV parsing if text is provided)
         if question_type == "file" and (".xlsx" in question.lower() or ".csv" in question.lower()):
             try:
-                # Assume table data is embedded in question text (simplified)
                 table_match = re.search(r'(\|.*?\|.*?\|.*?\|)', question, re.DOTALL)
                 if table_match:
                     table_text = table_match.group(1)
@@ -91,11 +85,9 @@ class BasicAgent:
         # Handle code questions
         if question_type == "code":
             try:
-                # Extract code snippet if provided
                 code_match = re.search(r'```python\n(.*?)\n```', question, re.DOTALL)
                 if code_match:
                     code = code_match.group(1)
-                    # Simulate code execution (simplified)
                     locals_dict = {}
                     exec(code, {}, locals_dict)
                     concise_answer = str(list(locals_dict.values())[-1]) if locals_dict else "Unknown"
@@ -109,10 +101,10 @@ class BasicAgent:
         # Handle factual questions with Wikipedia
         if question_type == "factual":
             try:
-                doc = nlp(question)
-                key_terms = " ".join([ent.text for ent in doc.ents if ent.label_ in ["PERSON", "ORG", "GPE", "DATE"]][:3])
+                words = re.findall(r'\b[A-Z][a-z]+(?:\s[A-Z][a-z]+)*\b|\b\w+\b', question.lower())
+                key_terms = " ".join([w for w in words if w not in ["what", "is", "the", "of", "in", "on", "at", "by", "for", "how", "many", "who", "where", "when", "if"]][-3:])
                 if not key_terms:
-                    key_terms = " ".join([token.text for token in doc if token.pos_ in ["NOUN", "PROPN"]][-3:])
+                    key_terms = " ".join(words[-3:])
                 print(f"Searching Wikipedia for: {key_terms}")
                 wikipedia.set_lang("en")
                 search_results = wikipedia.search(key_terms, results=1)
@@ -189,15 +181,9 @@ class BasicAgent:
             return response[:sentence_end].strip()
         return response[:50].strip()
 
-# --- Rest of the code (run_and_submit_all and Gradio interface) remains unchanged ---
-# [Insert the original run_and_submit_all function and Gradio interface code here]
-
+# --- Original run_and_submit_all and Gradio interface ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the agent, submits answers, and displays results.
-    """
     space_id = os.getenv("SPACE_ID")
-
     if profile:
         username = f"{profile.username}"
         print(f"User logged in: {username}")
@@ -209,7 +195,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent
     try:
         agent = BasicAgent()
         agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
@@ -218,7 +203,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
 
-    # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -234,11 +218,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     except requests.exceptions.JSONDecodeError as e:
         print(f"Error decoding JSON response: {response.text[:100]}")
         return f"Error decoding server response: {e}", None
-    except Exception as e:
-        print(f"An unexpected error occurred: {e}")
-        return f"An unexpected error occurred: {e}", None
 
-    # 3. Run Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -271,12 +251,10 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers.", pd.DataFrame(results_log)
 
-    # 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)
 
-    # 5. Submit
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)