updare to app.py

app.py

@@ -3,107 +3,84 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+import re
+import json
+import textwrap
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-# --- Enhanced Agent (replace the old BasicAgent with this) ---
-import re
-import json
-import textwrap
 
+# --- Enhanced BasicAgent (local model version) ---
 class BasicAgent:
     """
-    Calls a small LLM on the Hugging Face Inference API and post-processes the output
-    to return a concise, exact-match-friendly answer.
-    Reads HF API token from the HF Space secret HF_TOKEN.
+    Loads and runs a small LLM *locally* inside the Hugging Face Space
+    instead of calling the Hugging Face Inference API (which is blocked).
     """
+
     def __init__(self):
-        self.model_url = "https://api-inference.huggingface.co/models/HuggingFaceTB/SmolLM3-3B"
-        self.headers = {
-            "Authorization": f"Bearer {os.getenv('HF_TOKEN', '')}",
-            "Content-Type": "application/json",
-        }
-        if not os.getenv("HF_TOKEN"):
-            print("⚠️  HF_TOKEN not set — requests to the Inference API will fail.")
-        print("🚀 Enhanced BasicAgent initialized.")
+        # ✅ Small model to fit free Spaces — change to another instruct model if needed
+        model_id = "HuggingFaceTB/SmolLM3-1.7B"
+        print(f"🚀 Loading model locally: {model_id}")
+
+        # Load tokenizer and model
+        self.tokenizer = AutoTokenizer.from_pretrained(model_id)
+        self.model = AutoModelForCausalLM.from_pretrained(
+            model_id,
+            torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+            device_map="auto",
+        )
+
+        print("✅ Local model ready.")
 
     def _clean(self, raw: str) -> str:
-        """
-        Post-process the model output to a short, exact value:
-        - Keep only the final line after common prefixes.
-        - Strip quotes/backticks and trailing punctuation.
-        """
+        """Post-process the model output to a short, exact value."""
         txt = raw.strip()
-
-        # If the model echoed the prompt, take the last line
         lines = [l.strip() for l in txt.splitlines() if l.strip()]
         if lines:
             txt = lines[-1]
-
-        # Remove common prefixes
         txt = re.sub(r"^(final answer|answer|prediction)\s*[:\-]\s*", "", txt, flags=re.I)
-
-        # Strip code fences/quotes and trailing punctuation
         txt = txt.strip("`'\" \t\n\r")
         txt = re.sub(r"[ \t]*[.;,:-]+$", "", txt)
-
-        # Keep it short (exact match tasks usually want a short string/number)
         return txt[:200]
 
     def __call__(self, question: str) -> str:
         print(f"🧠 Agent received question: {question[:120]}...")
-        # A very simple, direct prompt to reduce rambling
+
+        # Simple concise prompt
         prompt = textwrap.dedent(f"""
         You must answer the question with a single, concise value
-        (number, word, date, short phrase) and nothing else.
-
+        (number, word, date, or short phrase) and nothing else.
         Question: {question}
         Final answer:
         """).strip()
 
-        payload = {
-            "inputs": prompt,
-            "parameters": {
-                "max_new_tokens": 96,
-                "temperature": 0.2,
-                "return_full_text": False,
-            },
-            "options": {"wait_for_model": True},
-        }
+        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)
+        outputs = self.model.generate(
+            **inputs, max_new_tokens=96, temperature=0.2, do_sample=True
+        )
 
-        try:
-            r = requests.post(self.model_url, headers=self.headers, data=json.dumps(payload), timeout=60)
-            r.raise_for_status()
-            data = r.json()
-            # Inference API (text-generation) usually returns a list with "generated_text"
-            if isinstance(data, list) and data and "generated_text" in data[0]:
-                generated = data[0]["generated_text"]
-            else:
-                # Fallback: stringify whatever came back
-                generated = str(data)
-            answer = self._clean(generated)
-            print(f"✅ Cleaned answer: {answer}")
-            # Ensure we never submit an empty string (server rejects)
-            return answer if answer else "N/A"
-        except Exception as e:
-            print(f"❌ Error generating answer: {e}")
-            return "N/A"
+        text = self.tokenizer.decode(
+            outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True
+        )
+        answer = self._clean(text)
+        print(f"✅ Cleaned answer: {answer}")
+        return answer or "N/A"
 
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+# --- Evaluation Runner ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs the BasicAgent locally, submits 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
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -113,38 +90,35 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # --- Instantiate Agent ---
     try:
         agent = BasicAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
-    # 2. Fetch Questions
+    # --- Fetch Questions ---
     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("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}")
-         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
+        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
 
-    # 3. Run your Agent
+    # --- Run Agent ---
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -156,22 +130,40 @@ def run_and_submit_all( profile: gr.OAuthProfile | 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})
+            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": agent_code, "answers": answers_payload}
+    # --- Submit ---
+    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)
 
-    # 5. Submit
     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
@@ -187,85 +179,53 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
+        status_message = f"Submission Failed: {e}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 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.
-
+        1. Log in to your Hugging Face account.
+        2. Click 'Run Evaluation & Submit All Answers'.
         ---
-        **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.
+        The agent now runs *locally* inside the Space instead of using the API.
         """
     )
 
     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]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
+
 
+# --- Launch ---
 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"✅ 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?).")
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
+    space_host = os.getenv("SPACE_HOST")
+    space_id = os.getenv("SPACE_ID")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
-        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")
+    if space_host:
+        print(f"✅ SPACE_HOST found: {space_host}")
+        print(f"   Runtime URL should be: https://{space_host}.hf.space")
     else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+        print("ℹ️  SPACE_HOST not found (running locally?).")
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    if space_id:
+        print(f"✅ SPACE_ID found: {space_id}")
+        print(f"   Repo URL: https://huggingface.co/spaces/{space_id}")
+        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id}/tree/main")
+    else:
+        print("ℹ️  SPACE_ID not found (running locally?).")
 
+    print("-" * (60 + len(" App Starting ")) + "\n")
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)