Update codeexecutor.py

codeexecutor.py

@@ -1,160 +1,115 @@
-import gradio as gr
-import ctranslate2
-from transformers import AutoTokenizer
-from huggingface_hub import snapshot_download
-from codeexecutor import postprocess_completion, get_majority_vote
+import os
+import re
+import subprocess
+import tempfile
+import multiprocessing
+from collections import Counter
+from contextlib import contextmanager
+from dataclasses import dataclass
 
-# Define the model and tokenizer loading
-model_prompt = "Solve the following mathematical problem: "
-tokenizer = AutoTokenizer.from_pretrained("AI-MO/NuminaMath-7B-TIR")
-model_path = snapshot_download(repo_id="Makima57/deepseek-math-Numina")
-generator = ctranslate2.Generator(model_path, device="cpu", compute_type="int8")
-iterations = 10
 
-# Function to generate predictions using the model
-def get_prediction(question):
-    input_text = model_prompt + question
-    input_tokens = tokenizer.tokenize(input_text)
-    results = generator.generate_batch([input_tokens])
-    output_tokens = results[0].sequences[0]
-    predicted_answer = tokenizer.convert_tokens_to_string(output_tokens)
-    return predicted_answer
+class PythonREPL:
+    def __init__(self, timeout=5):
+        self.timeout = timeout
 
-# Function to perform majority voting and solve the problem with steps
-def majority_vote_with_steps(question, num_iterations=10):
-    all_predictions = []
-    all_answer = []
-    steps_to_solve = []
-    
-    for _ in range(num_iterations):
-        prediction = get_prediction(question)
-        # Process prediction to get steps and answer
-        answer, success = postprocess_completion(prediction, True, True)
-        all_predictions.append(prediction)
-        all_answer.append(answer)
-        if success:
-            steps_to_solve.append(answer)  # Add the steps if code executes successfully
-    
-    majority_voted_ans = get_majority_vote(all_answer)
-    
-    # If steps to solve exist, return them, else fallback to "No steps found"
-    steps_solution = steps_to_solve[0] if steps_to_solve else "No steps found"
-    
-    return majority_voted_ans, steps_solution
+    @staticmethod
+    def _run_code(temp_file_path):
+        result = subprocess.run(
+            ["python3", temp_file_path],
+            capture_output=True,
+            check=False,
+            text=True
+        )
+        if result.returncode == 0:
+            return True, result.stdout.strip()
+        else:
+            error_msg = result.stderr.strip()
+            msgs = error_msg.split("\n")
+            new_msgs = []
+            want_next = False
+            for m in msgs:
+                if "Traceback" in m:
+                    new_msgs.append(m)
+                elif m == msgs[-1]:
+                    new_msgs.append(m)
+                elif temp_file_path in m:
+                    st = m.index('"/') + 1 if '"/' in m else 0
+                    ed = m.index(temp_file_path) + 1 if temp_file_path in m else None
+                    clr = m[st:ed] if not ed else m[st:]
+                    m = m.replace(clr, "")
+                    new_msgs.append(m)
+                    want_next = True
+                elif want_next:
+                    new_msgs.append(m)
+                    want_next = False
+            return False, "\n".join(new_msgs).strip()
 
-# Gradio interface for user input and output
-def gradio_interface(question, correct_answer):
-    final_answer, steps_solution = majority_vote_with_steps(question, iterations)
-    return {
-        "Question": question,
-        "Majority-Voted Answer": final_answer,
-        "Steps to Solve": steps_solution,
-        "Correct Solution": correct_answer
-    }
+    def __call__(self, query):
+        query = "import math\nimport numpy as np\nimport sympy as sp\n" + query
+        query = query.strip().split("\n")
+        if "print(" not in query[-1]:
+            if "#" in query[-1]:
+                query[-1] = query[-1].split("#")[0]
+            query[-1] = "print(" + query[-1] + ")"
+        query = "\n".join(query)
+        
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_file_path = os.path.join(temp_dir, "tmp.py")
+            with open(temp_file_path, "w", encoding="utf-8") as f:
+                f.write(query)
 
-# Custom CSS for enhanced design
-custom_css = """
-    body {
-        background-color: #fafafa;
-        font-family: 'Open Sans', sans-serif;
-    }
-    .gradio-container {
-        background-color: #ffffff;
-        border: 3px solid #007acc;
-        border-radius: 15px;
-        padding: 20px;
-        box-shadow: 0 8px 20px rgba(0, 0, 0, 0.15);
-        max-width: 800px;
-        margin: 50px auto;
-    }
-    h1 {
-        font-family: 'Poppins', sans-serif;
-        color: #007acc;
-        font-weight: bold;
-        font-size: 32px;
-        text-align: center;
-        margin-bottom: 20px;
-    }
-    p {
-        font-family: 'Roboto', sans-serif;
-        font-size: 18px;
-        color: #333;
-        text-align: center;
-        margin-bottom: 15px;
-    }
-    input, textarea {
-        font-family: 'Montserrat', sans-serif;
-        font-size: 16px;
-        padding: 10px;
-        border: 2px solid #007acc;
-        border-radius: 10px;
-        background-color: #f1f8ff;
-        margin-bottom: 15px;
-    }
-    #math_question, #correct_answer {
-        font-size: 20px;
-        font-family: 'Poppins', sans-serif;
-        font-weight: 500px;  /* Apply bold */
-        color: #007acc;
-        margin-bottom: 5px;
-        display: inline-block;
-    }
-    
-    textarea {
-        min-height: 150px;
-    }
-    .gr-button-primary {
-        background-color: #007acc !important;
-        color: white !important;
-        border-radius: 10px !important;
-        font-size: 18px !important;
-        font-weight: bold !important;
-        padding: 10px 20px !important;
-        font-family: 'Montserrat', sans-serif !important;
-        transition: background-color 0.3s ease !important;
-    }
-    .gr-button-primary:hover {
-        background-color: #005f99 !important;
-    }
-    .gr-button-secondary {
-        background-color: #f44336 !important;
-        color: white !important;
-        border-radius: 10px !important;
-        font-size: 18px !important;
-        font-weight: bold !important;
-        padding: 10px 20px !important;
-        font-family: 'Montserrat', sans-serif !important;
-        transition: background-color 0.3s ease !important;
-    }
-    .gr-button-secondary:hover {
-        background-color: #c62828 !important;
-    }
-    .gr-output {
-        background-color: #e0f7fa;
-        border: 2px solid #007acc;
-        border-radius: 10px;
-        padding: 15px;
-        font-size: 16px;
-        font-family: 'Roboto', sans-serif;
-        font-weight: bold;
-        color: #00796b;
-    }
-"""
+            with multiprocessing.Pool(1) as pool:
+                result = pool.apply_async(self._run_code, (temp_file_path,))
+                try:
+                    success, output = result.get(self.timeout)
+                except multiprocessing.TimeoutError:
+                    pool.terminate()
+                    return False, f"Timed out after {self.timeout} seconds."
+        return success, output
 
-# Gradio app setup
-interface = gr.Interface(
-    fn=gradio_interface,
-    inputs=[
-        gr.Textbox(label="🧠 Math Question", placeholder="Enter your math question here...", elem_id="math_question"),
-        gr.Textbox(label="✅ Correct Answer", placeholder="Enter the correct answer here...", elem_id="correct_answer"),
-    ],
-    outputs=[
-        gr.JSON(label="📊 Results"),  # Display the results in a JSON format
-    ],
-    title="🔢 Math Question Solver",
-    description="Enter a math question to get the model's majority-voted answer and steps to solve the problem.",
-    css=custom_css  # Apply custom CSS
-)
 
-if __name__ == "__main__":
-    interface.launch()
+def execute_completion(executor, completion, return_status, last_code_block):
+    executions = re.findall(r"```python(.*?)```", completion, re.DOTALL)
+    if len(executions) == 0:
+        return completion, False if return_status else completion
+    if last_code_block:
+        executions = [executions[-1]]
+    outputs = []
+    successes = []
+    for code in executions:
+        success = False
+        for lib in ("subprocess", "venv"):
+            if lib in code:
+                output = f"{lib} is not allowed"
+                outputs.append(output)
+                successes.append(success)
+                continue
+        try:
+            success, output = executor(code)
+        except TimeoutError as e:
+            print("Code timed out")
+            output = e
+        if not success and not return_status:
+            output = ""
+        outputs.append(output)
+        successes.append(success)
+    output = str(outputs[-1]).strip()
+    success = successes[-1]
+    if return_status:
+        return output, success
+    return output
+
+
+def postprocess_completion(text, return_status, last_code_block):
+    executor = PythonREPL()
+    result = execute_completion(executor, text, return_status=return_status, last_code_block=last_code_block)
+    del executor
+    return result
+
+
+def get_majority_vote(answers):
+    if not len(answers):
+        return 0
+    c = Counter(answers)
+    value, _ = c.most_common()[0]
+    return value