Update app.py

app.py

@@ -2,14 +2,6 @@ import os
 import gradio as gr
 import requests
 import pandas as pd
-from io import BytesIO
-import re
-import ffmpeg
-from tenacity import retry, stop_after_attempt, wait_fixed
-
-# --- Tool-specific Imports ---
-from pytube import YouTube
-from youtube_transcript_api import YouTubeTranscriptApi, NoTranscriptFound
 
 # --- LangChain & Dependency Imports ---
 from groq import Groq
@@ -21,99 +13,37 @@ from langchain.tools import Tool
 
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-TEMP_DIR = "/tmp"
-
-# --- Tool Definition: Audio File Transcription ---
-@retry(stop=stop_after_attempt(3), wait=wait_fixed(2))
-def transcribe_audio_file(task_id: str) -> str:
-    """
-    Downloads an audio file (.mp3) for a given task_id, transcribes it, and returns the text.
-    Use this tool ONLY when a question explicitly mentions an audio file, .mp3, recording, or voice memo.
-    """
-    print(f"Tool 'transcribe_audio_file' called with task_id: {task_id}")
-    try:
-        file_url = f"{DEFAULT_API_URL}/files/{task_id}"
-        audio_response = requests.get(file_url)
-        audio_response.raise_for_status()
-        audio_bytes = BytesIO(audio_response.content)
-        audio_bytes.name = f"{task_id}.mp3"
-        client = Groq(api_key=os.getenv("GROQ_API_KEY"))
-        transcription = client.audio.transcriptions.create(file=audio_bytes, model="whisper-large-v3", response_format="text")
-        return str(transcription)
-    except Exception as e:
-        return f"Error during audio file transcription: {e}"
-
-# --- Tool Definition: Video Transcription (prioritizing transcripts) ---
-@retry(stop=stop_after_attempt(3), wait=wait_fixed(2))
-def transcribe_youtube_video(video_url: str) -> str:
-    """
-    Fetches a transcript for a YouTube video from a URL, falling back to download and transcription if needed.
-    Use this tool ONLY when a question provides a youtube.com URL.
-    """
-    print(f"Tool 'transcribe_youtube_video' called with URL: {video_url}")
-    video_path, audio_path = None, None
-    try:
-        # Extract video ID and try to fetch official transcript
-        video_id = re.search(r"(?:v=|\/)([0-9A-Za-z_-]{11}).*", video_url).group(1)
-        transcript = YouTubeTranscriptApi.get_transcript(video_id)
-        return ' '.join([entry['text'] for entry in transcript])
-    except NoTranscriptFound:
-        print("No transcript found; falling back to download and transcribe.")
-        # Fallback to original download logic
-        os.makedirs(TEMP_DIR, exist_ok=True)
-        yt = YouTube(video_url)
-        stream = yt.streams.filter(only_audio=True).first()
-        video_path = stream.download(output_path=TEMP_DIR)
-        audio_path = os.path.join(TEMP_DIR, "output.mp3")
-        stream = ffmpeg.input(video_path)
-        stream = ffmpeg.output(stream, audio_path, q=0, map='a', y='y')
-        ffmpeg.run(stream)
-        client = Groq(api_key=os.getenv("GROQ_API_KEY"))
-        with open(audio_path, "rb") as audio_file:
-            transcription = client.audio.transcriptions.create(file=audio_file, model="whisper-large-v3", response_format="text")
-        return str(transcription)
-    except Exception as e:
-        return f"Error during YouTube transcription: {e}"
-    finally:
-        if video_path and os.path.exists(video_path): os.remove(video_path)
-        if audio_path and os.path.exists(audio_path): os.remove(audio_path)
 
 # --- Agent Definition ---
-class LangChainAgent:
+class SimpleAgent:
     def __init__(self, groq_api_key: str, tavily_api_key: str):
+        print("Initializing SimpleAgent...")
         self.llm = ChatGroq(model_name="llama3-70b-8192", groq_api_key=groq_api_key, temperature=0.0)
+        
+        # The agent has ONLY ONE tool: web_search
         self.tools = [
             TavilySearch(name="web_search", max_results=3, tavily_api_key=tavily_api_key, description="A search engine for finding up-to-date information on the internet."),
-            Tool(name="audio_file_transcriber", func=transcribe_audio_file, description="Use this for questions mentioning an audio file (.mp3, recording). Input MUST be the task_id."),
-            Tool(name="youtube_video_transcriber", func=transcribe_youtube_video, description="Use this for questions with a youtube.com URL. Input MUST be the URL."),
         ]
+        
+        # A simple, direct prompt
         prompt = ChatPromptTemplate.from_messages([
             ("system", (
-                "You are a powerful problem-solving agent. Your goal is to answer the user's question accurately. "
-                "You have access to a web search tool, an audio file transcriber, and a YouTube video transcriber.\n\n"
-                "**REASONING PROCESS:**\n"
-                "1.  **Analyze the question:** Determine if a tool is needed. Is it a general knowledge question, or does it mention an audio file or a YouTube URL?\n"
-                "2.  **Select ONE tool based on the question:**\n"
-                "    - For general knowledge, facts, or current events: use `web_search`.\n"
-                "    - For an audio file, .mp3, or voice memo: use `audio_file_transcriber` with the `task_id`.\n"
-                "    - For a youtube.com URL: use `youtube_video_transcriber` with the URL. If transcription fails, fall back to web_search for video transcripts or summaries.\n"
-                "    - For anything else (like images, which you cannot see, or math), you must answer directly without using a tool.\n"
-                "3.  **Handle Errors:** If a tool fails (e.g., download error), retry once or use web_search to find alternatives.\n"
-                "4.  **Execute and Answer:** After using a tool, analyze the result and provide ONLY THE FINAL ANSWER without extra text like 'FINAL ANSWER'."
+                "You are a helpful assistant. You have access to one tool: a web search engine. "
+                "Use it when you need to find current information or facts. "
+                "After using the tool, provide ONLY the final, concise answer."
             )),
-            ("human", "Question: {input}\nTask ID: {task_id}"),
+            ("human", "{input}"),
             ("placeholder", "{agent_scratchpad}"),
         ])
+        
         agent = create_tool_calling_agent(self.llm, self.tools, prompt)
         self.agent_executor = AgentExecutor(agent=agent, tools=self.tools, verbose=True, handle_parsing_errors=True)
+        print("SimpleAgent Initialized.")
 
-    def __call__(self, question: str, task_id: str) -> str:
-        urls = re.findall(r'https?://[^\s]+', question)
-        input_for_agent = {"input": question, "task_id": task_id}
-        if urls and "youtube.com" in urls[0]:
-            input_for_agent['video_url'] = urls[0]
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question: {question[:50]}...")
         try:
-            response = self.agent_executor.invoke(input_for_agent)
+            response = self.agent_executor.invoke({"input": question})
             return response.get("output", "Agent failed to produce an answer.")
         except Exception as e:
             return f"Agent execution failed with an error: {e}"
@@ -123,11 +53,13 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
     if not profile: return "Please Login to Hugging Face with the button.", None
     username = profile.username
+    print(f"User logged in: {username}")
+    
     try:
         groq_api_key = os.getenv("GROQ_API_KEY")
         tavily_api_key = os.getenv("TAVILY_API_KEY")
         if not all([groq_api_key, tavily_api_key]): raise ValueError("GROQ or TAVILY API key is missing.")
-        agent = LangChainAgent(groq_api_key=groq_api_key, tavily_api_key=tavily_api_key)
+        agent = SimpleAgent(groq_api_key=groq_api_key, tavily_api_key=tavily_api_key)
     except Exception as e: return f"Error initializing agent: {e}", None
     
     questions_url = f"{DEFAULT_API_URL}/questions"
@@ -141,7 +73,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     for item in questions_data:
         task_id, q_text = item.get("task_id"), item.get("question")
         if not task_id or not q_text: continue
-        answer = agent(question=q_text, task_id=task_id)
+        answer = agent(question=q_text)
         answers_payload.append({"task_id": task_id, "submitted_answer": answer})
         results_log.append({"Task ID": task_id, "Question": q_text, "Submitted Answer": answer})
     
@@ -161,8 +93,8 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
 # --- Gradio Interface ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Ultimate Agent Runner (Search, Audio, Video)")
-    gr.Markdown("This agent can search, transcribe audio files, and transcribe YouTube videos.")
+    gr.Markdown("# Simple Agent Runner (Web Search Only)")
+    gr.Markdown("This agent can only search the web. Let's establish a stable baseline.")
     gr.LoginButton()
     run_button = gr.Button("Run Evaluation & Submit All Answers")
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
@@ -171,7 +103,7 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    for key in ["GROQ_API_KEY", "TAVILY_API_KEY", "SPACE_ID"]:
+    for key in ["GROQ_API_KEY", "TAVILY_API_KEY"]:
         print(f"✅ {key} secret is set." if os.getenv(key) else f"⚠️ WARNING: {key} secret is not set.")
     print("-"*(60 + len(" App Starting ")) + "\n")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)