Update app.py

app.py

@@ -6,7 +6,7 @@ import inspect
 import pandas as pd
 from smolagents import (
     ToolCallingAgent,
-    OpenAIServerModel,
+    LiteLLMModel,
     DuckDuckGoSearchTool,
     WikipediaSearchTool,
     PythonInterpreterTool,
@@ -29,110 +29,87 @@ def get_current_date_time() -> str:
 class BasicAgent:
     def __init__(self):
         print("BasicAgent initialized.")
-        sambanova_api_key = os.getenv("SAMBANOVA_API_KEY")
-        self.model = OpenAIServerModel(
-            model_id="Meta-Llama-3.3-70B-Instruct",
-            api_base="https://api.sambanova.ai/v1",
-            api_key=sambanova_api_key,
+        groq_api_key = os.getenv("GROQ_API_KEY")
+        if not groq_api_key:
+            raise ValueError("GROQ_API_KEY environment variable not set")
+        self.model = LiteLLMModel(
+            model_id="groq/llama-3.3-70b-versatile",
+            api_key=groq_api_key,
         )
-        tools = [
+        self.tools = [
             DuckDuckGoSearchTool(),
             WikipediaSearchTool(),
             PythonInterpreterTool(),
             get_current_date_time,
         ]
-        self.tools = tools
+        self.agent = ToolCallingAgent(
+            tools=self.tools,
+            model=self.model,
+            max_steps=6,
+        )
+        print("BasicAgent ready with Groq Llama-3.3-70B.")
 
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}")
-        # Retry up to 3 times with backoff on rate limit errors
-        for attempt in range(3):
-            try:
-                agent = ToolCallingAgent(
-                    tools=self.tools,
-                    model=self.model,
-                    max_steps=8,
-                )
-                answer = agent.run(question)
-                print(f"Agent answer: {str(answer)[:100]}")
-                return str(answer)
-            except Exception as e:
-                err = str(e)
-                if "429" in err or "rate_limit" in err.lower() or "rate limit" in err.lower():
-                    wait = 60 * (attempt + 1)
-                    print(f"Rate limit hit, waiting {wait}s before retry {attempt+1}/3...")
-                    time.sleep(wait)
-                else:
-                    print(f"Agent error: {e}")
-                    return f"Error: {e}"
-        return "Error: Rate limit exceeded after retries"
+        print(f"Agent received question: {question[:80]}...")
+        try:
+            answer = self.agent.run(question)
+            print(f"Agent answer: {str(answer)[:200]}")
+            return str(answer)
+        except Exception as e:
+            print(f"Agent error: {e}")
+            return f"Error: {str(e)}"
 
 
-# --- run_and_submit_all function (Keep as is) ---
+# --- The rest of the code (keep as-is) ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
-
     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"
-
     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)
-
+    print(f"Agent code: {agent_code}")
     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.")
+            print("No questions.")
+            return "No questions.", None
     except Exception as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
-
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    for item in questions_data:
+    for i, item in enumerate(questions_data):
         task_id = item.get("task_id")
         question_text = item.get("question")
-        if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
+        if not task_id or not question_text:
             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:
-            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}"})
-        # Pause between questions to avoid per-minute rate limits
-        time.sleep(3)
-
+            print(f"Error on task {task_id}: {e}")
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"ERROR: {e}"})
+        time.sleep(1)
     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)
-
+        return "No answers.", pd.DataFrame(results_log)
     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)
-
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    print(f"Submitting {len(answers_payload)} answers...")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
@@ -140,60 +117,37 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         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.')}"
+            f"Score: {result_data.get('score')}%\n"
+            f"Correct: {result_data.get('correct_count')}/{result_data.get('total_attempted')}\n"
+            f"Message: {result_data.get('message')}"
         )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
+        print(final_status)
+        return final_status, pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"Submission Failed: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        print(f"Submission error: {e}")
+        return f"Submission failed: {e}", pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Build Gradio UI ---
 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. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
-"""
+        **Instructions:**
+        1. Clone this space and set `GROQ_API_KEY` in your Space secrets.
+        2. Log in with your Hugging Face account below.
+        3. Click 'Run Evaluation & Submit' to start.
+        """
     )
     gr.LoginButton()
     run_button = gr.Button("Run Evaluation & Submit All Answers")
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
     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__":
-    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID")  # Get SPACE_ID at startup
-    if space_host_startup:
-        print(f"\u2705 SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("\u2139\ufe0f SPACE_HOST environment variable not found (running locally?).")
-    if space_id_startup:  # Print repo URLs if SPACE_ID is found
-        print(f"\u2705 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("\u2139\ufe0f SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-    print("-" * (60 + len(" App Starting ")) + "\n")
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    print("Starting Gradio app...")
+    demo.launch(debug=True, share=False)