Reinitialize repository at backend level with ai_evaluator and services

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

tinyllama_inference.py

@@ -14,15 +14,27 @@ def load_model():
         model = AutoModelForCausalLM.from_pretrained(model_name)
     return tokenizer, model
 
+def extract_json(response_text):
+    # Attempt to extract all JSON blocks (non-greedy, with DOTALL)
+    matches = re.findall(r'\{.*?\}', response_text, re.DOTALL)
+    for m in reversed(matches):
+        try:
+            temp = json.loads(m)
+            if isinstance(temp, dict) and "stars" in temp and "feedback" in temp:
+                return temp
+        except Exception:
+            continue
+    return None
+
 def evaluate_code(question, code):
-    # Revised prompt with explicit instructions about arithmetic correctness.
+    # Revised prompt that explicitly states the expected arithmetic operation for square.
     prompt = f"""You are an expert code evaluator.
 Evaluate the following solution for the given problem.
 The problem asks for a function that returns the square of a number.
 A correct solution must multiply the number by itself (using x*x or x**2).
 If the solution uses any other operation (such as addition), it is completely incorrect.
 Rate the solution as follows:
-  - 5 stars: Perfect solution; the solution is correct, efficient, and follows best practices.
+  - 5 stars: Perfect solution; correct, efficient, and follows best practices.
   - 4 stars: Correct solution with minor issues.
   - 3 stars: Partially correct solution with noticeable issues.
   - 2 stars: Incorrect solution with some correct elements.
@@ -49,22 +61,12 @@ Your response:"""
     response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
     print("Raw model response:", response_text)  # Debug output
 
-    # Extract JSON: use regex to capture all JSON blocks and select one with expected keys
-    matches = re.findall(r'\{.*?\}', response_text, re.DOTALL)
-    result = None
-    for m in reversed(matches):
-        try:
-            temp = json.loads(m)
-            if isinstance(temp, dict) and "stars" in temp and "feedback" in temp:
-                result = temp
-                break
-        except Exception:
-            continue
+    result = extract_json(response_text)
     if result is None:
         result = {"stars": 0, "feedback": "Evaluation failed. Unable to extract valid JSON from AI response."}
-    
     return result
 
+# For direct command-line testing.
 if __name__ == "__main__":
     import sys
     if len(sys.argv) < 3: