hi

analyzer.py

@@ -1,5 +1,6 @@
 import openai
 import os
+import json
 
 def analyze_code(code: str) -> str:
     """
@@ -8,7 +9,12 @@ def analyze_code(code: str) -> str:
     """
     from openai import OpenAI
     client = OpenAI()
-    system_prompt = "You are a helpful assistant. Analyze the code given to you. Provide insights, strengths, weaknesses, and suggestions for improvement."
+    system_prompt = (
+        "You are a helpful assistant. Analyze the code given to you. "
+        "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."
+    )
     response = client.chat.completions.create(
         model="gpt-4-1106-preview",  # GPT-4.1 mini
         messages=[
@@ -20,6 +26,12 @@ def analyze_code(code: str) -> str:
     )
     return response.choices[0].message.content
 
+def parse_llm_json_response(response: str):
+    try:
+        return json.loads(response)
+    except Exception as e:
+        return {"error": f"Failed to parse JSON: {e}", "raw": response}
+
 def combine_repo_files_for_llm(repo_dir="repo_files", output_file="combined_repo.txt"):
     """
     Combines all .py and .md files in the given directory (recursively) into a single text file.

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import regex as re
 import csv
 import pandas as pd
-from analyzer import combine_repo_files_for_llm, analyze_combined_file
+from analyzer import combine_repo_files_for_llm, analyze_combined_file, parse_llm_json_response
 from hf_utils import download_space_repo
 
 # from hf_utils import download_space_repo
@@ -57,6 +57,22 @@ def show_combined_repo_and_llm():
     except Exception as e:
         return f"Error reading {txt_path}: {e}", ""
     llm_output = analyze_combined_file(txt_path)
+    llm_json = parse_llm_json_response(llm_output)
+    # Update CSV for the first repo id
+    csv_filename = "repo_ids.csv"
+    try:
+        df = pd.read_csv(csv_filename)
+        for idx, row in df.iterrows():
+            if row["repo id"] == first_repo_id:
+                if isinstance(llm_json, dict):
+                    df.at[idx, "strength"] = llm_json.get("strength", "")
+                    df.at[idx, "weaknesses"] = llm_json.get("weaknesses", "")
+                    df.at[idx, "speciality"] = llm_json.get("speciality", "")
+                    df.at[idx, "relevance rating"] = llm_json.get("relevance rating", "")
+                break
+        df.to_csv(csv_filename, index=False)
+    except Exception as e:
+        pass  # Optionally log error
     return combined_content, llm_output
 
 repo_id_input = gr.Textbox(label="Enter repo IDs (comma or newline separated)", lines=5, placeholder="repo1, repo2\nrepo3")