Update app.py

app.py

@@ -1,258 +1,73 @@
 import os
 import time
-import moviepy
 import requests
+import moviepy.editor
 import whisper
 import gradio as gr
 import pandas as pd
+import wikipedia
 from duckduckgo_search import DDGS
 from transformers import pipeline
-from sklearn.metrics.pairwise import cosine_similarity
-import numpy as np
 
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-class BasicAgent:
+class SmartAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
-        # Initialize the Whisper model for video transcription
-        self.whisper_model = whisper.load_model("base")  # You can change the model to `large`, `medium`, etc.
-        self.search_pipeline = pipeline("question-answering")
-        self.nlp_model = pipeline("feature-extraction")  # For semantic similarity (using transformer model)
-
-    def score_search_results(self, question: str, search_results: list) -> str:
-        # Transform the question and results to embeddings (vector representations)
-        question_embedding = self.nlp_model(question)
-        question_embedding = np.mean(question_embedding[0], axis=0)
-
-        best_score = -1
-        best_answer = None
-
-        # Loop through search results and calculate similarity
-        for result in search_results:
-            result_embedding = self.nlp_model(result['body'])
-            result_embedding = np.mean(result_embedding[0], axis=0)
-
-            # Calculate cosine similarity
-            similarity = cosine_similarity([question_embedding], [result_embedding])
-
-            # Check if this result is better
-            if similarity > best_score:
-                best_score = similarity
-                best_answer = result['body']
-
-        return best_answer
-
-    def search(self, question: str) -> str:
-        try:
-            with DDGS() as ddgs:
-                results = list(ddgs.text(question, max_results=3))  # Fetch top 3 results
-                if results:
-                    # Score all the results and return the best one
-                    return self.score_search_results(question, results)
-                else:
-                    return "No relevant search results found."
-        except Exception as e:
-            return f"Search error: {e}"
+        print("SmartAgent initialized.")
+        self.whisper_model = whisper.load_model("base")
+        self.qa_pipeline = pipeline("question-answering")
 
     def call_whisper(self, video_path: str) -> str:
-        # Transcribe the video to text using Whisper model
         video = moviepy.editor.VideoFileClip(video_path)
         audio_path = "temp_audio.wav"
         video.audio.write_audiofile(audio_path)
-        
-        # Transcribe audio to text
         result = self.whisper_model.transcribe(audio_path)
         return result["text"]
 
-    def __call__(self, question: str, video_path: str = None) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-
-        # If a video path is provided, use Whisper to transcribe the video
-        if video_path:
-            transcription = self.call_whisper(video_path)
-            print(f"Transcribed video text: {transcription[:100]}...")  # Print first 100 characters
-            return transcription
-
-        # If no video is provided, search the web for an answer
-        search_answer = self.search(question)
-        print(f"Agent returning search result: {search_answer[:100]}...")
-        time.sleep(2)
-        return search_answer
-
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    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
-
-    if profile:
-        username = f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
-
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
-
-    # 1. Instantiate Agent
-    try:
-        agent = BasicAgent()
-    except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
-    
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
-    try:
-        response = requests.get(questions_url, timeout=15)
-        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(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}")
-        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
-
-    # 3. Run Agent
-    results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
-        task_id = item.get("task_id")
-        question_text = item.get("question")
-        video_link = item.get("video_link")  # Assuming the question contains an optional video link
-
-        if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
-            continue
+    def classify_question(self, question: str) -> str:
+        q = question.lower()
+        if "how many" in q or "number of" in q:
+            return "count"
+        elif "when" in q or "what year" in q:
+            return "date"
+        return "open"
 
+    def wiki_search(self, question: str) -> str:
         try:
-            # Pass video_link if available, else just the question text
-            submitted_answer = agent(question_text, video_path=video_link)
-            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            results = wikipedia.search(question, results=1)
+            if not results:
+                return ""
+            page = wikipedia.page(results[0])
+            return page.content
         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}"})
+            return ""
 
-    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 
-    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)
-        response.raise_for_status()
-        result_data = response.json()
-        final_status = (
-            f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
-        )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
+    def fallback_duckduckgo(self, question: str) -> str:
         try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
-
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
-        1. Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2. Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-        ---
-        **Disclaimers:**
-        Once clicking on the "submit button, it can take quite some time (this is the time for the agent to go through all the questions).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution.
-        """
-    )
-
-    gr.LoginButton()
-
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+            with DDGS() as ddgs:
+                results = list(ddgs.text(question, max_results=3))
+                return results[0]["body"] if results else ""
+        except Exception as e:
+            return ""
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+    def answer_with_context(self, question: str, context: str) -> str:
+        try:
+            if not context.strip():
+                return "No reliable context found."
+            result = self.qa_pipeline(question=question, context=context)
+            return result["answer"]
+        except Exception as e:
+            return f"QA error: {e}"
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    def __call__(self, question: str, video_path: str = None) -> str:
+        print(f"Agent received question: {question[:60]}...")
 
-if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID")
+        if video_path:
+            return self.call_whisper(video_path)
 
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-    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")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        classification = self.classify_question(question)
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+        context = self.wiki_search(question)
+        if not context:
+            context = self.fallback_duckduckgo(question)
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+        return self.answer_with_context(question, context)