Update app.py

app.py

@@ -18,7 +18,6 @@ openai.api_key = OPENAI_KEY
 client = openai.OpenAI(api_key=OPENAI_KEY)
 
 # --- Tool Definitions ---
-
 def wiki_lookup(query: str) -> str:
     resp = requests.get(
         f"https://en.wikipedia.org/api/rest_v1/page/summary/{requests.utils.quote(query)}"
@@ -26,15 +25,6 @@ def wiki_lookup(query: str) -> str:
     data = resp.json()
     return data.get("extract", "No summary found.")
 
-class YouTubeTranscriptTool:
-    def run(self, url: str) -> str:
-        video_id = url.split('v=')[-1]
-        resp = requests.get(
-            "https://youtubetranscriptparser.example/api/transcript",
-            params={"id": video_id}
-        )
-        return resp.json().get("transcript", "")
-
 class WhisperASRTool:
     def run(self, filename: str) -> str:
         with open(filename, "rb") as audio_file:
@@ -69,85 +59,100 @@ class EnhancedGaiaAgent:
         self.model = model_name
         self.tools = {
             'wikipedia': wiki_lookup,
-            'web_search': lambda q: requests.get(
-                "https://api.duckduckgo.com/",
-                params={"q": q, "format": "json", "t": "hf_agent"}
-            ).json().get('AbstractText',''),
-            'python': lambda code: str(exec(code)),
-            'youtube_transcript': YouTubeTranscriptTool().run,
             'whisper_asr': WhisperASRTool().run,
             'chess': ChessAnalysisTool().run,
             'excel_summation': ExcelSummationTool().run,
         }
 
     def __call__(self, question: str, file: str = None) -> str:
-        prompt = [
-            {"role": "system", "content": (
-                "You are a multi-tool agent. Use TOOL_NAME(input) to call a tool when needed. "
-                "Return only the final answer."
-            )},
-            {"role": "user", "content": question}
-        ]
-        resp = self.client.chat.completions.create(
-            model=self.model,
-            messages=prompt,
-            temperature=0,
-            max_tokens=512
-        )
-        answer = resp.choices[0].message.content.strip()
-
-        if '(' in answer and ')' in answer:
-            tool, args = answer.split('(',1)
-            args = args.rsplit(')',1)[0]
-            func = self.tools.get(tool.strip())
-            if func:
-                return func(args)
-        return answer
-
-# --- Gradio App Wiring ---
-demo = gr.Blocks()
-with demo:
-    gr.Markdown("# GAIA Level 1: Enhanced Multi-Tool Agent")
+        # Direct questions without file use wiki lookup or LLM
+        if file is None:
+            # simple LLM call
+            messages = [
+                {"role": "system", "content": "Answer concisely."},
+                {"role": "user", "content": question}
+            ]
+            resp = self.client.chat.completions.create(
+                model=self.model,
+                messages=messages,
+                temperature=0,
+                max_tokens=256
+            )
+            return resp.choices[0].message.content.strip()
+        # File-based tasks
+        ext = os.path.splitext(file)[1].lower()
+        if ext == '.mp3':
+            return self.tools['whisper_asr'](file)
+        if ext == '.png':
+            return self.tools['chess'](file)
+        if ext == '.xlsx':
+            return self.tools['excel_summation'](file)
+        # fallback
+        return ""
+
+# --- Run & Submit Function ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    if not profile:
+        return "Please log in to Hugging Face with the button.", None
+
+    username = profile.username.strip()
+    space_id = os.getenv("SPACE_ID", "unknown-space")
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+
+    agent = EnhancedGaiaAgent(model_name=os.getenv("OPENAI_MODEL", "gpt-4"))
+
+    # Fetch questions
+    resp = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
+    resp.raise_for_status()
+    questions = resp.json()
+
+    results = []
+    answers_payload = []
+    for item in questions:
+        task_id = item.get("task_id")
+        question = item.get("question")
+        file_name = item.get("file_name") or None
+        # Download file if provided
+        local_file = None
+        if file_name:
+            dl = requests.get(f"{DEFAULT_API_URL}/file/{file_name}")
+            open(file_name, 'wb').write(dl.content)
+            local_file = file_name
+        ans = agent(question, local_file)
+        results.append({"Task ID": task_id, "Submitted Answer": ans})
+        answers_payload.append({"task_id": task_id, "submitted_answer": ans})
+
+    # Submit
+    submission = {"username": username, "agent_code": agent_code, "answers": answers_payload}
+    post = requests.post(f"{DEFAULT_API_URL}/submit", json=submission, timeout=60)
+    post.raise_for_status()
+    res = post.json()
+    status = (
+        f"Submission Successful! Score: {res.get('score')}%"
+    )
+    return status, pd.DataFrame(results)
+
+# --- Original Gradio UI ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
-        Set `OPENAIAPIKEY` in secrets.  
-        Upload images/audio/spreadsheets via Gradio’s upload widgets.  
-        Then click **Run** to answer tasks.
+        **Instructions:**
+
+        1. Clone this space and modify the agent logic.
+        2. Log in to your HF account.
+        3. Click 'Run Evaluation & Submit All Answers'.
+
         """
     )
     gr.LoginButton()
-    video_in = gr.Textbox(label="YouTube URL (for transcript)")
-    audio_in = gr.Audio(label="Audio file (mp3)")
-    image_in = gr.Image(label="Chess Position (PNG)")
-    file_in = gr.File(label="Other File (e.g., .xlsx, .py)")
-    ask_in = gr.JSON(label="Tasks JSON")
-    run_btn = gr.Button("Run Agent on All Tasks")
-    status_out = gr.Textbox(label="Status", lines=5, interactive=False)
-    results_tbl = gr.DataFrame(label="Results")
-
-    def run_all(profile, tasks, y_url, audio, image, file):
-        if not profile:
-            return "Please log in.", None
-        agent = EnhancedGaiaAgent()
-        results = []
-        for item in tasks:
-            q = item['question']
-            fn = item.get('file_name') or ''
-            if fn.endswith('.mp3'):
-                ans = agent.tools['whisper_asr'](audio.name)
-            elif fn.endswith('.png'):
-                ans = agent.tools['chess'](image.name)
-            elif fn.endswith('.xlsx'):
-                ans = agent.tools['excel_summation'](file.name)
-            else:
-                ans = agent(q)
-            results.append({'task_id': item['task_id'], 'answer': ans})
-        return "Done", pd.DataFrame(results)
-
-    run_btn.click(
-        fn=run_all,
-        inputs=[gr.State(), ask_in, video_in, audio_in, image_in, file_in],
-        outputs=[status_out, results_tbl]
+    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", wrap=True)
+
+    run_button.click(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
     )
 
 if __name__ == "__main__":