Update app.py

app.py

@@ -1,107 +1,82 @@
 
-
-import os
 import gradio as gr
+from duckduckgo_search import DDGS
+from transformers import pipeline
+from PIL import Image
 import requests
-import pandas as pd
-
-
-
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-
-class SmartAgent:
-    def __init__(self):
-        self.agent = HfAgent("https://api-inference.huggingface.co/chat/agent")
-        print("SmartAgent initialized with Hugging Face tools.")
-
-    def __call__(self, question: str) -> str:
-        print(f"[SmartAgent] Received question: {question[:100]}")
-        try:
-            result = self.agent.run(question)
-            print(f"[SmartAgent] Agent result: {result}")
-            return str(result)
-        except Exception as e:
-            print(f"[SmartAgent] Error: {e}")
-            return f"Agent error: {e}"
-
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    space_id = os.getenv("SPACE_ID")
-    if profile:
-        username = f"{profile.username}"
-    else:
-        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"
-
-    try:
-        agent = SmartAgent()
-    except Exception as e:
-        return f"Error initializing agent: {e}", None
-
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-
-    try:
-        response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
-        questions_data = response.json()
-    except Exception as e:
-        return f"Error fetching questions: {e}", None
-
-    results_log = []
-    answers_payload = []
-    for item in questions_data:
-        task_id = item.get("task_id")
-        question_text = item.get("question")
-        if not task_id or question_text is None:
-            continue
-        try:
-            submitted_answer = agent(question_text)
-            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})
-        except Exception as e:
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-
-    submission_data = {
-        "username": username.strip(),
-        "agent_code": agent_code,
-        "answers": answers_payload
-    }
-
+from bs4 import BeautifulSoup
+import re
+import torch
+from io import BytesIO
+
+# Pipelines
+qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
+caption_pipeline = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
+summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
+
+# Utils
+def search_web(query, max_results=3):
+    with DDGS() as ddgs:
+        results = ddgs.text(query, max_results=max_results)
+        return "\n\n".join([f"**{r['title']}**\n{r['body']}\n{r['href']}" for r in results])
+
+def explain_image(img):
+    return caption_pipeline(img)[0]['generated_text']
+
+def extract_text_from_url(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"Score: {result_data.get('score', 'N/A')}%\n"
-            f"Correct: {result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')}\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
-        )
-        return final_status, pd.DataFrame(results_log)
+        res = requests.get(url, timeout=5)
+        soup = BeautifulSoup(res.text, 'html.parser')
+        # Remove scripts/styles
+        for script in soup(["script", "style"]): script.extract()
+        text = soup.get_text(separator=' ')
+        clean_text = re.sub(r'\s+', ' ', text)
+        return clean_text[:3000]  # Limit to 3000 characters
     except Exception as e:
-        return f"Submission failed: {e}", pd.DataFrame(results_log)
-      
+        return f"Failed to extract text: {str(e)}"
+
+def summarize_url(url):
+    text = extract_text_from_url(url)
+    if len(text) > 100:
+        summary = summarizer(text[:1024])[0]['summary_text']
+        return summary
+    return "Not enough text to summarize."
+
+# Main Agent Function
+def ai_agent(input_text, image=None, url=None):
+    results = []
+
+    # Process Image
+    if image:
+        results.append("🖼️ **Image Explanation:**\n" + explain_image(image))
+
+    # Process URL
+    if url:
+        if "youtube.com" in url or "youtu.be" in url:
+            results.append("📹 **Video URL detected.** Currently only summaries of page content are available.")
+        results.append("🔗 **Webpage Summary:**\n" + summarize_url(url))
+
+    # Web search for complex questions
+    if input_text:
+        if len(input_text.split()) > 10:  # assume complex
+            web_results = search_web(input_text)
+            results.append("🔍 **Web Search Results:**\n" + web_results)
+        else:
+            results.append("🧠 **Answer:**\n" + search_web(input_text))
+
+    return "\n\n---\n\n".join(results)
+
+# Gradio UI
 with gr.Blocks() as demo:
-    gr.Markdown("# Smart AI Agent (Web, Image, Video, and QA Support)")
-    gr.Markdown("""
-        This agent can:
-        - Answer complex questions
-        - Perform web searches
-        - Explain images or videos from URLs
+    gr.Markdown("## 🌐🧠 Multi-Modal AI Agent (Web + Image + URL)")
+    with gr.Row():
+        input_text = gr.Textbox(label="Ask a Question", lines=2, placeholder="E.g. What are the latest AI trends?")
+        image = gr.Image(type="pil", label="Upload an Image (optional)")
+        url = gr.Textbox(label="Provide a URL (optional)", placeholder="https://example.com")
+    submit = gr.Button("Get Answer")
+    output = gr.Markdown()
 
-        Please login and run the evaluation to test the agent.
-    """)
-    gr.LoginButton()
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="Questions and Agent Answers")
+    submit.click(fn=ai_agent, inputs=[input_text, image, url], outputs=output)
 
-    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
+demo.launch()
 
-if __name__ == "__main__":
-    demo.launch(debug=True, share=False)