what

analyzer.py

@@ -14,9 +14,16 @@ def analyze_code(code: str) -> str:
         "Return your response strictly in JSON format with the following keys: "
         "'strength', 'weaknesses', 'speciality', 'relevance rating'. "
         "Do not include any other text outside the JSON."
+        "the reply should just be the following format:"
+        "{"
+        "  'strength': '...', "
+        "  'weaknesses': '...', "
+        "  'speciality': '...', "
+        "  'relevance rating': '...'"
+        "}"
     )
     response = client.chat.completions.create(
-        model="gpt-4-1106-preview",  # GPT-4.1 mini
+        model="gpt-4o-mini",  # GPT-4.1 mini
         messages=[
             {"role": "system", "content": system_prompt},
             {"role": "user", "content": code}

app.py

@@ -7,6 +7,9 @@ from hf_utils import download_space_repo
 
 # from hf_utils import download_space_repo
 
+def read_csv_as_text(csv_filename):
+    return pd.read_csv(csv_filename, dtype=str)
+
 def process_repo_input(text):
     if not text:
         return pd.DataFrame(columns=["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
@@ -20,7 +23,7 @@ def process_repo_input(text):
         for repo_id in repo_ids:
             writer.writerow([repo_id, "", "", "", ""])
     # Read the CSV into a DataFrame to display
-    df = pd.read_csv(csv_filename)
+    df = read_csv_as_text(csv_filename)
     return df
 
 # Store the last entered repo ids and the current index in global variables for button access
@@ -42,7 +45,7 @@ def process_repo_input_and_store(text):
         writer.writerow(["repo id", "strength", "weaknesses", "speciality", "relevance rating"])
         for repo_id in repo_ids:
             writer.writerow([repo_id, "", "", "", ""])
-    df = pd.read_csv(csv_filename)
+    df = read_csv_as_text(csv_filename)
     return df
 
 def show_combined_repo_and_llm():
@@ -50,18 +53,18 @@ def show_combined_repo_and_llm():
     if not last_repo_ids:
         return "No repo ID available. Please submit repo IDs first.", "", pd.DataFrame()
     if current_repo_idx >= len(last_repo_ids):
-        return "All repo IDs have been processed.", "", pd.read_csv("repo_ids.csv")
+        return "All repo IDs have been processed.", "", read_csv_as_text("repo_ids.csv")
     repo_id = last_repo_ids[current_repo_idx]
     try:
         download_space_repo(repo_id, local_dir="repo_files")
     except Exception as e:
-        return f"Error downloading repo: {e}", "", pd.read_csv("repo_ids.csv")
+        return f"Error downloading repo: {e}", "", read_csv_as_text("repo_ids.csv")
     txt_path = combine_repo_files_for_llm()
     try:
         with open(txt_path, "r", encoding="utf-8") as f:
             combined_content = f.read()
     except Exception as e:
-        return f"Error reading {txt_path}: {e}", "", pd.read_csv("repo_ids.csv")
+        return f"Error reading {txt_path}: {e}", "", read_csv_as_text("repo_ids.csv")
     llm_output = analyze_combined_file(txt_path)
     llm_json = parse_llm_json_response(llm_output)
     # Update CSV for the current repo id
@@ -70,8 +73,7 @@ def show_combined_repo_and_llm():
     strengths = ""
     weaknesses = ""
     try:
-        df = pd.read_csv(csv_filename)
-        # Cast columns to string to avoid dtype issues
+        df = read_csv_as_text(csv_filename)
         for col in ["strength", "weaknesses", "speciality", "relevance rating"]:
             df[col] = df[col].astype(str)
         for idx, row in df.iterrows():
@@ -89,7 +91,7 @@ def show_combined_repo_and_llm():
                 break
         df.to_csv(csv_filename, index=False)
     except Exception as e:
-        df = pd.read_csv(csv_filename)
+        df = read_csv_as_text(csv_filename)
         extraction_status = f"CSV update error: {e}"
     # Move to next repo for next click
     current_repo_idx += 1