butoon

analyzer.py

@@ -2,6 +2,7 @@ import openai
 import os
 import json
 import re
+from typing import Tuple
 
 def analyze_code(code: str) -> str:
     """
@@ -206,3 +207,150 @@ def analyze_combined_file(output_file="combined_repo.txt", user_requirements: st
         return debug_output
     except Exception as e:
         return f"Error analyzing combined file: {e}"
+
+def analyze_repo_chunk_for_context(chunk: str, repo_id: str) -> str:
+    """
+    Analyze a repository chunk to create conversational context for the chatbot.
+    This creates summaries focused on helping users understand the repository.
+    """
+    try:
+        from openai import OpenAI
+        client = OpenAI(api_key=os.getenv("modal_api"))
+        client.base_url = os.getenv("base_url")
+        
+        context_prompt = f"""You are analyzing a chunk of code from the repository '{repo_id}' to create a conversational summary for a chatbot assistant.
+
+Create a concise but informative summary that helps understand:
+- What this code section does
+- Key functions, classes, or components
+- Important features or capabilities
+- How it relates to the overall repository purpose
+- Any notable patterns or technologies used
+
+Focus on information that would be useful for answering user questions about the repository.
+
+Repository chunk:
+{chunk}
+
+Provide a clear, conversational summary in 2-3 paragraphs:"""
+        
+        response = client.chat.completions.create(
+            model="Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ",
+            messages=[
+                {"role": "system", "content": "You are an expert code analyst creating conversational summaries for a repository assistant chatbot."},
+                {"role": "user", "content": context_prompt}
+            ],
+            max_tokens=600,  # Increased for more detailed analysis with larger chunks
+            temperature=0.3
+        )
+        
+        return response.choices[0].message.content
+    
+    except Exception as e:
+        logger.error(f"Error analyzing chunk for context: {e}")
+        return f"Code section analysis unavailable: {e}"
+
+def create_repo_context_summary(repo_content: str, repo_id: str) -> str:
+    """
+    Create a comprehensive context summary by analyzing the repository in chunks.
+    Returns a detailed summary that the chatbot can use to answer questions.
+    """
+    try:
+        lines = repo_content.split('\n')
+        chunk_size = 1200  # Increased for better context and fewer API calls
+        chunk_summaries = []
+        
+        logger.info(f"Analyzing repository {repo_id} in chunks for chatbot context")
+        
+        for i in range(0, len(lines), chunk_size):
+            chunk = '\n'.join(lines[i:i+chunk_size])
+            if chunk.strip():  # Only analyze non-empty chunks
+                summary = analyze_repo_chunk_for_context(chunk, repo_id)
+                chunk_summaries.append(f"=== Section {len(chunk_summaries) + 1} ===\n{summary}")
+        
+        # Create final comprehensive summary
+        try:
+            from openai import OpenAI
+            client = OpenAI(api_key=os.getenv("modal_api"))
+            client.base_url = os.getenv("base_url")
+            
+            final_prompt = f"""Based on the following section summaries of repository '{repo_id}', create a comprehensive overview that a chatbot can use to answer user questions.
+
+Section Summaries:
+{chr(10).join(chunk_summaries)}
+
+Create a well-structured overview covering:
+1. Repository Purpose & Main Functionality
+2. Key Components & Architecture
+3. Important Features & Capabilities
+4. Technology Stack & Dependencies
+5. Usage Patterns & Examples
+
+Make this comprehensive but conversational - it will be used by a chatbot to answer user questions about the repository."""
+            
+            response = client.chat.completions.create(
+                model="Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ",
+                messages=[
+                    {"role": "system", "content": "You are creating a comprehensive repository summary for a chatbot assistant."},
+                    {"role": "user", "content": final_prompt}
+                ],
+                max_tokens=1500,  # Increased for more comprehensive summaries
+                temperature=0.3
+            )
+            
+            final_summary = response.choices[0].message.content
+            
+            # Combine everything for the chatbot context
+            full_context = f"""=== REPOSITORY ANALYSIS FOR {repo_id.upper()} ===
+
+{final_summary}
+
+=== DETAILED SECTION SUMMARIES ===
+{chr(10).join(chunk_summaries)}"""
+            
+            logger.info(f"Created comprehensive context summary for {repo_id}")
+            return full_context
+            
+        except Exception as e:
+            logger.error(f"Error creating final summary: {e}")
+            # Fallback to just section summaries
+            return f"=== REPOSITORY ANALYSIS FOR {repo_id.upper()} ===\n\n" + '\n\n'.join(chunk_summaries)
+    
+    except Exception as e:
+        logger.error(f"Error creating repo context summary: {e}")
+        return f"Repository analysis unavailable: {e}"
+
+def handle_load_repository(repo_id: str) -> Tuple[str, str]:
+    """Load a specific repository and prepare it for exploration with chunk-based analysis."""
+    if not repo_id.strip():
+        return "Status: Please enter a repository ID.", ""
+    
+    try:
+        logger.info(f"Loading repository for exploration: {repo_id}")
+        
+        # Download and process the repository
+        try:
+            download_filtered_space_files(repo_id, local_dir="repo_files", file_extensions=['.py', '.md', '.txt'])
+            combined_text_path = combine_repo_files_for_llm()
+        
+        except Exception as e:
+            logger.error(f"Error downloading repository {repo_id}: {e}")
+            error_status = f"❌ Error downloading repository: {e}"
+            return error_status, ""
+        
+        with open(combined_text_path, "r", encoding="utf-8") as f:
+            repo_content = f.read()
+        
+        status = f"✅ Repository '{repo_id}' loaded successfully!\\n📁 Files processed and ready for exploration.\\n🔄 Analyzing repository in chunks for comprehensive context...\\n💬 You can now ask questions about this repository."
+        
+        # Create comprehensive context summary using chunk analysis
+        logger.info(f"Creating context summary for {repo_id}")
+        context_summary = create_repo_context_summary(repo_content, repo_id)
+        
+        logger.info(f"Repository {repo_id} loaded and analyzed successfully for exploration")
+        return status, context_summary
+        
+    except Exception as e:
+        logger.error(f"Error loading repository {repo_id}: {e}")
+        error_status = f"❌ Error loading repository: {e}"
+        return error_status, ""

app.py

@@ -8,10 +8,15 @@ import os
 import time
 
 # Import core logic from other modules, as in app_old.py
-from analyzer import combine_repo_files_for_llm, analyze_combined_file, parse_llm_json_response
+from analyzer import (
+    combine_repo_files_for_llm, 
+    parse_llm_json_response, 
+    analyze_combined_file,
+    handle_load_repository
+)
 from hf_utils import download_filtered_space_files, search_top_spaces
 from chatbot_page import chat_with_user, extract_keywords_from_conversation
-from repo_explorer import create_repo_explorer_tab, setup_repo_explorer_events, handle_load_repository
+from repo_explorer import create_repo_explorer_tab, setup_repo_explorer_events
 
 # --- Configuration ---
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

repo_explorer.py

@@ -2,124 +2,12 @@ import gradio as gr
 import os
 import logging
 from typing import List, Dict, Tuple
-from analyzer import combine_repo_files_for_llm
+from analyzer import combine_repo_files_for_llm, handle_load_repository
 from hf_utils import download_filtered_space_files
 
 # Setup logger
 logger = logging.getLogger(__name__)
 
-def analyze_repo_chunk_for_context(chunk: str, repo_id: str) -> str:
-    """
-    Analyze a repository chunk to create conversational context for the chatbot.
-    This creates summaries focused on helping users understand the repository.
-    """
-    try:
-        from openai import OpenAI
-        client = OpenAI(api_key=os.getenv("modal_api"))
-        client.base_url = os.getenv("base_url")
-        
-        context_prompt = f"""You are analyzing a chunk of code from the repository '{repo_id}' to create a conversational summary for a chatbot assistant.
-
-Create a concise but informative summary that helps understand:
-- What this code section does
-- Key functions, classes, or components
-- Important features or capabilities
-- How it relates to the overall repository purpose
-- Any notable patterns or technologies used
-
-Focus on information that would be useful for answering user questions about the repository.
-
-Repository chunk:
-{chunk}
-
-Provide a clear, conversational summary in 2-3 paragraphs:"""
-        
-        response = client.chat.completions.create(
-            model="Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ",
-            messages=[
-                {"role": "system", "content": "You are an expert code analyst creating conversational summaries for a repository assistant chatbot."},
-                {"role": "user", "content": context_prompt}
-            ],
-            max_tokens=600,  # Increased for more detailed analysis with larger chunks
-            temperature=0.3
-        )
-        
-        return response.choices[0].message.content
-    
-    except Exception as e:
-        logger.error(f"Error analyzing chunk for context: {e}")
-        return f"Code section analysis unavailable: {e}"
-
-def create_repo_context_summary(repo_content: str, repo_id: str) -> str:
-    """
-    Create a comprehensive context summary by analyzing the repository in chunks.
-    Returns a detailed summary that the chatbot can use to answer questions.
-    """
-    try:
-        lines = repo_content.split('\n')
-        chunk_size = 1200  # Increased for better context and fewer API calls
-        chunk_summaries = []
-        
-        logger.info(f"Analyzing repository {repo_id} in chunks for chatbot context")
-        
-        for i in range(0, len(lines), chunk_size):
-            chunk = '\n'.join(lines[i:i+chunk_size])
-            if chunk.strip():  # Only analyze non-empty chunks
-                summary = analyze_repo_chunk_for_context(chunk, repo_id)
-                chunk_summaries.append(f"=== Section {len(chunk_summaries) + 1} ===\n{summary}")
-        
-        # Create final comprehensive summary
-        try:
-            from openai import OpenAI
-            client = OpenAI(api_key=os.getenv("modal_api"))
-            client.base_url = os.getenv("base_url")
-            
-            final_prompt = f"""Based on the following section summaries of repository '{repo_id}', create a comprehensive overview that a chatbot can use to answer user questions.
-
-Section Summaries:
-{chr(10).join(chunk_summaries)}
-
-Create a well-structured overview covering:
-1. Repository Purpose & Main Functionality
-2. Key Components & Architecture
-3. Important Features & Capabilities
-4. Technology Stack & Dependencies
-5. Usage Patterns & Examples
-
-Make this comprehensive but conversational - it will be used by a chatbot to answer user questions about the repository."""
-            
-            response = client.chat.completions.create(
-                model="Orion-zhen/Qwen2.5-Coder-7B-Instruct-AWQ",
-                messages=[
-                    {"role": "system", "content": "You are creating a comprehensive repository summary for a chatbot assistant."},
-                    {"role": "user", "content": final_prompt}
-                ],
-                max_tokens=1500,  # Increased for more comprehensive summaries
-                temperature=0.3
-            )
-            
-            final_summary = response.choices[0].message.content
-            
-            # Combine everything for the chatbot context
-            full_context = f"""=== REPOSITORY ANALYSIS FOR {repo_id.upper()} ===
-
-{final_summary}
-
-=== DETAILED SECTION SUMMARIES ===
-{chr(10).join(chunk_summaries)}"""
-            
-            logger.info(f"Created comprehensive context summary for {repo_id}")
-            return full_context
-            
-        except Exception as e:
-            logger.error(f"Error creating final summary: {e}")
-            # Fallback to just section summaries
-            return f"=== REPOSITORY ANALYSIS FOR {repo_id.upper()} ===\n\n" + '\n\n'.join(chunk_summaries)
-    
-    except Exception as e:
-        logger.error(f"Error creating repo context summary: {e}")
-        return f"Repository analysis unavailable: {e}"
-
 def create_repo_explorer_tab() -> Tuple[Dict[str, gr.components.Component], Dict[str, gr.State]]:
     """
     Creates the Repo Explorer tab content and returns the component references and state variables.
@@ -198,41 +86,6 @@ def create_repo_explorer_tab() -> Tuple[Dict[str, gr.components.Component], Dict
     
     return components, states
 
-def handle_load_repository(repo_id: str) -> Tuple[str, str]:
-    """Load a specific repository and prepare it for exploration with chunk-based analysis."""
-    if not repo_id.strip():
-        return "Status: Please enter a repository ID.", ""
-    
-    try:
-        logger.info(f"Loading repository for exploration: {repo_id}")
-        
-        # Download and process the repository
-        try:
-            download_filtered_space_files(repo_id, local_dir="repo_files", file_extensions=['.py', '.md', '.txt'])
-            combined_text_path = combine_repo_files_for_llm()
-        
-        except Exception as e:
-            logger.error(f"Error downloading repository {repo_id}: {e}")
-            error_status = f"❌ Error downloading repository: {e}"
-            return error_status, ""
-        
-        with open(combined_text_path, "r", encoding="utf-8") as f:
-            repo_content = f.read()
-        
-        status = f"✅ Repository '{repo_id}' loaded successfully!\n📁 Files processed and ready for exploration.\n🔄 Analyzing repository in chunks for comprehensive context...\n💬 You can now ask questions about this repository."
-        
-        # Create comprehensive context summary using chunk analysis
-        logger.info(f"Creating context summary for {repo_id}")
-        context_summary = create_repo_context_summary(repo_content, repo_id)
-        
-        logger.info(f"Repository {repo_id} loaded and analyzed successfully for exploration")
-        return status, context_summary
-        
-    except Exception as e:
-        logger.error(f"Error loading repository {repo_id}: {e}")
-        error_status = f"❌ Error loading repository: {e}"
-        return error_status, ""
-
 def handle_repo_user_message(user_message: str, history: List[Dict[str, str]], repo_context_summary: str, repo_id: str) -> Tuple[List[Dict[str, str]], str]:
     """Handle user messages in the repo-specific chatbot."""
     if not repo_context_summary.strip():