downloads

analyzer.py

@@ -73,13 +73,13 @@ def parse_llm_json_response(response: str):
 
 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.
+    Combines all .py, .md, and .txt files in the given directory (recursively) into a single text file.
     Returns the path to the combined file.
     """
     combined_content = []
     seen_files = set()
     # Priority files
-    priority_files = ["app.py", "README.md"]
+    priority_files = ["app.py", "README.md", "requirements.txt"]
     for pf in priority_files:
         pf_path = os.path.join(repo_dir, pf)
         if os.path.isfile(pf_path):
@@ -90,10 +90,10 @@ def combine_repo_files_for_llm(repo_dir="repo_files", output_file="combined_repo
                 seen_files.add(os.path.abspath(pf_path))
             except Exception as e:
                 combined_content.append(f"\n# Could not read {pf_path}: {e}\n")
-    # All other .py and .md files
+    # All other .py, .md, and .txt files
     for root, _, files in os.walk(repo_dir):
         for file in files:
-            if file.endswith(".py") or file.endswith(".md"):
+            if file.endswith(".py") or file.endswith(".md") or file.endswith(".txt"):
                 file_path = os.path.join(root, file)
                 abs_path = os.path.abspath(file_path)
                 if abs_path in seen_files:

app.py

@@ -196,7 +196,7 @@ def analyze_and_update_single_repo(repo_id: str, user_requirements: str = "") ->
     """
     try:
         logger.info(f"Starting analysis for repo: {repo_id}")
-        download_space_repo(repo_id, local_dir="repo_files")
+        download_space_repo(repo_id, local_dir="repo_files", file_extensions=['.py', '.md', '.txt'])
         txt_path = combine_repo_files_for_llm()
         
         with open(txt_path, "r", encoding="utf-8") as f:

hf_utils.py

@@ -2,15 +2,20 @@ from huggingface_hub import snapshot_download
 import os
 import shutil
 
-def download_space_repo(space_id: str, local_dir: str = "repo_files"):
+def download_space_repo(space_id: str, local_dir: str = "repo_files", file_extensions: list = None):
     """
-    Downloads all files from a Hugging Face Space repository.
+    Downloads files from a Hugging Face Space repository, optionally filtering by file extensions.
 
     Args:
         space_id (str): The ID of the Hugging Face Space (e.g., "naman1102/Final_Assignment_Template").
         local_dir (str): Local directory to store the downloaded files.
+        file_extensions (list): Optional list of file extensions to download (e.g., ['.py', '.md']).
+                               If None, downloads all files.
     """
     print(f"Downloading Space '{space_id}'...")
+    
+    if file_extensions:
+        print(f"Filtering for file types: {', '.join(file_extensions)}")
 
     # Download the snapshot of the space repo
     repo_path = snapshot_download(repo_id=space_id, repo_type="space")
@@ -19,13 +24,36 @@ def download_space_repo(space_id: str, local_dir: str = "repo_files"):
     if os.path.exists(local_dir):
         shutil.rmtree(local_dir)
 
-    # Copy contents to target directory
-    shutil.copytree(repo_path, local_dir)
-
-    print(f"All files from Space '{space_id}' downloaded to: {local_dir}")
+    if file_extensions is None:
+        # Download all files (original behavior)
+        shutil.copytree(repo_path, local_dir)
+        print(f"All files from Space '{space_id}' downloaded to: {local_dir}")
+    else:
+        # Filter and copy only specified file types
+        os.makedirs(local_dir, exist_ok=True)
+        copied_files = 0
+        
+        for root, dirs, files in os.walk(repo_path):
+            for file in files:
+                # Check if file has one of the desired extensions
+                if any(file.lower().endswith(ext.lower()) for ext in file_extensions):
+                    source_path = os.path.join(root, file)
+                    # Maintain directory structure
+                    relative_path = os.path.relpath(source_path, repo_path)
+                    dest_path = os.path.join(local_dir, relative_path)
+                    
+                    # Create destination directory if it doesn't exist
+                    os.makedirs(os.path.dirname(dest_path), exist_ok=True)
+                    
+                    # Copy the file
+                    shutil.copy2(source_path, dest_path)
+                    copied_files += 1
+        
+        print(f"Filtered download complete: {copied_files} files with extensions {file_extensions} from Space '{space_id}' downloaded to: {local_dir}")
 
 # Example usage
-# download_space_repo("finegrain/finegrain-image-enhancer")
+# download_space_repo("finegrain/finegrain-image-enhancer")  # Downloads all files
+# download_space_repo("finegrain/finegrain-image-enhancer", file_extensions=['.py', '.md', '.txt'])  # Downloads only .py, .md, and .txt files
 
 from huggingface_hub import list_spaces
 

repo_explorer.py

@@ -206,11 +206,17 @@ def handle_load_repository(repo_id: str) -> Tuple[str, str]:
     try:
         logger.info(f"Loading repository for exploration: {repo_id}")
         
-        # Download and combine repository files
-        download_space_repo(repo_id, local_dir="repo_files")
-        txt_path = combine_repo_files_for_llm()
+        # Download and process the repository
+        try:
+            download_space_repo(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(txt_path, "r", encoding="utf-8") as f:
+        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."