Update app.py

app.py

@@ -1,35 +1,69 @@
 import os
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
-from huggingface_hub import InferenceClient
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 
-# Constants
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+DEFAULT_HF_MODEL = "mistralai/Mistral-7B-Instruct-v0.1"  # Free model on Hugging Face
 
-# Basic Agent Definition using HF Inference API
+# --- Basic Agent Definition ---
 class BasicAgent:
-    def __init__(self, token: str):
-        print("BasicAgent initialized.")
-        self.client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1", token=token)
-
+    def __init__(self, hf_token=None, model_name=DEFAULT_HF_MODEL):
+        print("Initializing BasicAgent with LLM...")
+        self.hf_token = hf_token
+        self.model_name = model_name
+        self.llm = None
+        self.tokenizer = None
+        
+        if hf_token:
+            try:
+                print(f"Loading model: {model_name}")
+                self.tokenizer = AutoTokenizer.from_pretrained(model_name, token=hf_token)
+                self.model = AutoModelForCausalLM.from_pretrained(model_name, token=hf_token)
+                self.llm = pipeline(
+                    "text-generation",
+                    model=self.model,
+                    tokenizer=self.tokenizer,
+                    device_map="auto"
+                )
+                print("Model loaded successfully")
+            except Exception as e:
+                print(f"Error loading model: {e}")
+                raise Exception(f"Could not load model: {e}")
+        else:
+            print("No HF token provided - agent will use default answers")
+    
     def __call__(self, question: str) -> str:
-        print(f"Agent received question: {question[:50]}...")
+        if not self.llm:
+            return "This is a default answer (no LLM initialized)"
+            
         try:
-            prompt = f"[INST] {question.strip()} [/INST]"
-            response = self.client.text_generation(prompt=prompt, max_new_tokens=300, temperature=0.7)
-            answer = response.strip()
-            print(f"Agent returning answer: {answer}")
-            return answer
+            print(f"Generating answer for question: {question[:50]}...")
+            response = self.llm(
+                question,
+                max_new_tokens=150,
+                do_sample=True,
+                temperature=0.7,
+                top_p=0.9
+            )
+            return response[0]['generated_text']
         except Exception as e:
-            print(f"Error while querying HF model: {e}")
-            return f"Error: {e}"
+            print(f"Error generating answer: {e}")
+            return f"Error generating answer: {e}"
 
-def run_and_submit_all(profile: gr.OAuthProfile | None, token_input: str):
-    space_id = os.getenv("SPACE_ID")
+def run_and_submit_all(profile: gr.OAuthProfile | None, hf_token: str):
+    """
+    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}"
+        username= f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -41,10 +75,13 @@ def run_and_submit_all(profile: gr.OAuthProfile | None, token_input: str):
 
     # 1. Instantiate Agent
     try:
-        agent = BasicAgent(token=token_input)
+        agent = BasicAgent(hf_token=hf_token)
     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}")
@@ -53,15 +90,16 @@ def run_and_submit_all(profile: gr.OAuthProfile | None, token_input: str):
         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("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
+         print(f"Error decoding JSON response from questions endpoint: {e}")
+         print(f"Response text: {response.text[:500]}")
+         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
@@ -81,19 +119,15 @@ def run_and_submit_all(profile: gr.OAuthProfile | None, token_input: str):
             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}"})
+             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}"})
 
     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": f"https://huggingface.co/spaces/{space_id}/tree/main",
-        "answers": answers_payload
-    }
+    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)
 
@@ -113,6 +147,22 @@ def run_and_submit_all(profile: gr.OAuthProfile | None, token_input: str):
         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}."
+        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)
@@ -124,30 +174,63 @@ def run_and_submit_all(profile: gr.OAuthProfile | None, token_input: str):
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
-# Gradio Interface
+
+# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# LLM 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. Paste your Hugging Face token below.
+        1. Get your Hugging Face API token from [your settings](https://huggingface.co/settings/tokens)
+        2. Enter your token below (it will be used only during this session)
+        3. Log in to your Hugging Face account
         4. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+
+        ---
+        **Note:** The first run will take longer as it downloads the model.
         """
     )
 
+    with gr.Row():
+        hf_token_input = gr.Textbox(
+            label="Hugging Face API Token",
+            type="password",
+            placeholder="Enter your HF API token here (required for LLM)",
+            info="Get your token from https://huggingface.co/settings/tokens"
+        )
+    
     gr.LoginButton()
-    token_box = gr.Textbox(label="Enter your Hugging Face token", type="password", placeholder="hf_...")
+
     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,
-        inputs=[gr.OAuthProfile(), token_box],
+        inputs=[gr.OAuthProfile(), hf_token_input],
         outputs=[status_output, results_table]
     )
 
 if __name__ == "__main__":
-    demo.launch(debug=True, share=False)
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    space_host_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID")
+
+    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(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.")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
+
+    print("Launching Gradio Interface for LLM Agent Evaluation...")
+    demo.launch(debug=True, share=False)