llama-github 0.1.9__tar.gz → 0.2.1__tar.gz

{llama_github-0.1.9 → llama_github-0.2.1}/CHANGELOG.md

@@ -5,7 +5,17 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.1.9] - 2024-10-31
+## [0.2.1] - 2024-11-16
+
+### Optimized
+- approperately handle more file types when calculate file changes in PR
+
+## [0.2.0] - 2024-11-16
+
+### Optimized
+- fix bugs for generate repo from pool by using Github_install_id
+
+## [0.1.9] - 2024-11-04
 
 ### Optimized
 - fix bugs for get pr content

{llama_github-0.1.9/llama_github.egg-info → llama_github-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-github
-Version: 0.1.9
+Version: 0.2.1
 Summary: Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Agents to conduct Retrieval from actively selected GitHub public projects. It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.
 Home-page: https://github.com/JetXu-LLM/llama-github
 Author: Jet Xu
@@ -96,6 +96,22 @@ For more advanced usage and examples, please refer to the [documentation](docs/u
 
 - **🛠️ Logging and Error Handling**: We understand the importance of smooth operations and easy troubleshooting. That's why llama-github comes equipped with comprehensive logging and error handling mechanisms. Gain deep insights into the library's behavior, quickly diagnose issues, and maintain a stable and reliable development workflow.
 
+## 🤖 Try Our AI-Powered PR Review Assistant: LlamaPReview
+
+If you find llama-github useful, you might also be interested in our AI-powered GitHub PR review assistant, LlamaPReview. It's designed to complement your development workflow and further enhance code quality.
+
+### Key Features of LlamaPReview:
+- 🚀 One-click installation, zero configuration required, fully auto-run
+- 💯 Currently free to use - no credit card or payment info needed
+- 🧠 AI-powered, automatic PR reviews with deep code understanding
+- 🌐 Supports multiple programming languages
+
+**LlamaPReview utilizes llama-github's advanced context retrieval and LLM-powered analysis** to provide intelligent, context-aware code reviews. It's like having a senior developer, armed with the full context of your repository, review every PR automatically!
+
+👉 [Install LlamaPReview Now](https://github.com/marketplace/llamapreview/) (Free)
+
+By using llama-github for context retrieval and LlamaPReview for code reviews, you can create a powerful, AI-enhanced development environment.
+
 ## Vision and Roadmap
 
 ### Vision
@@ -140,7 +156,17 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.1.9] - 2024-10-31
+## [0.2.1] - 2024-11-16
+
+### Optimized
+- approperately handle more file types when calculate file changes in PR
+
+## [0.2.0] - 2024-11-16
+
+### Optimized
+- fix bugs for generate repo from pool by using Github_install_id
+
+## [0.1.9] - 2024-11-04
 
 ### Optimized
 - fix bugs for get pr content

{llama_github-0.1.9 → llama_github-0.2.1}/README.md

@@ -60,6 +60,22 @@ For more advanced usage and examples, please refer to the [documentation](docs/u
 
 - **🛠️ Logging and Error Handling**: We understand the importance of smooth operations and easy troubleshooting. That's why llama-github comes equipped with comprehensive logging and error handling mechanisms. Gain deep insights into the library's behavior, quickly diagnose issues, and maintain a stable and reliable development workflow.
 
+## 🤖 Try Our AI-Powered PR Review Assistant: LlamaPReview
+
+If you find llama-github useful, you might also be interested in our AI-powered GitHub PR review assistant, LlamaPReview. It's designed to complement your development workflow and further enhance code quality.
+
+### Key Features of LlamaPReview:
+- 🚀 One-click installation, zero configuration required, fully auto-run
+- 💯 Currently free to use - no credit card or payment info needed
+- 🧠 AI-powered, automatic PR reviews with deep code understanding
+- 🌐 Supports multiple programming languages
+
+**LlamaPReview utilizes llama-github's advanced context retrieval and LLM-powered analysis** to provide intelligent, context-aware code reviews. It's like having a senior developer, armed with the full context of your repository, review every PR automatically!
+
+👉 [Install LlamaPReview Now](https://github.com/marketplace/llamapreview/) (Free)
+
+By using llama-github for context retrieval and LlamaPReview for code reviews, you can create a powerful, AI-enhanced development environment.
+
 ## Vision and Roadmap
 
 ### Vision

{llama_github-0.1.9 → llama_github-0.2.1}/llama_github/data_retrieval/github_entities.py

@@ -98,6 +98,11 @@ class Repository:
     @property
     def repo(self):
         return self.get_repo()
+    
+    def set_github(self, github_instance: ExtendedGithub):
+        self._github = github_instance
+        with self._repo_lock:  # Locking for write action
+            self._repo = self._github.get_repo(self.full_name)
 
     def get_repo(self):
         """
@@ -118,8 +123,8 @@ class Repository:
                         self.default_branch = self._repo.default_branch
                         self.updated_at = self._repo.updated_at
                     except GithubException as e:
-                        logger.exception(
-                            f"Error retrieving repository '{self.full_name}':")
+                        logger.error(
+                            f"Error retrieving repository '{self.full_name}':{str(e)}")
                         return None
         self.update_last_read_time()
         return self._repo
@@ -154,14 +159,88 @@ class Repository:
         """
         file_key = f"{file_path}/{sha}" if sha is not None else file_path
 
-        # Skip binary and system files
+        # Skip files that don't need processing
         if any(file_path.endswith(ext) for ext in [
-            '.exe', '.dll', '.so', '.dylib', '.bin', 
-            '.png', '.jpg', '.jpeg', '.gif', '.ico',
-            '.mp3', '.mp4', '.avi', '.mov', '.pdf',
-            '.DS_Store'
-        ]) or '/.' in file_path:
-            logger.debug(f"Skipping binary or system file: {file_path}")
+            # Package manager and dependencies
+            '.lock', '.pnpm-lock.yaml', 'package-lock.json', 'Gemfile.lock', 
+            'poetry.lock', 'Cargo.lock', 'composer.lock',
+            '.pyc', '.pyo', 'requirements.txt',
+            
+            # Binaries and compiled files
+            '.exe', '.dll', '.so', '.dylib', '.bin', '.obj', '.o', '.a', 
+            '.lib', '.jar', '.war', '.ear', '.class', '.pdb', '.ilk', '.exp',
+            '.apk', '.aab', '.ipa',  # Mobile apps
+            '.wasm',  # WebAssembly
+            
+            # Media and compressed files
+            '.png', '.jpg', '.jpeg', '.gif', '.ico', '.bmp', '.tiff', '.webp',
+            '.svg', '.eps', '.psd', '.ai', '.sketch',
+            '.mp3', '.mp4', '.wav', '.flac', '.ogg', '.m4a',
+            '.avi', '.mov', '.mkv', '.webm', '.wmv', '.flv',
+            '.pdf', '.doc', '.docx', '.xls', '.xlsx', '.ppt', '.pptx',
+            '.zip', '.rar', '.7z', '.tar', '.gz', '.bz2', '.xz', '.tgz',
+            
+            # System and hidden files
+            '.DS_Store', 'Thumbs.db', '.dockerignore',
+            '.gitattributes', '.gitmodules',
+            
+            # Documentation and resource files
+            '.min.js', '.min.css', '.map', '.po', '.mo', '.pot',
+            '.ttf', '.otf', '.eot', '.woff', '.woff2',  # Fonts
+            
+            # Configuration and data files
+            '.conf', '.config', '.cfg', '.ini',
+            '.sqlite', '.db', '.mdb', '.sql',
+            '.pb', '.pbtxt',  # Protocol buffers
+            '.ipynb',  # Jupyter notebooks
+            '.pkl', '.pickle',  # Python serialized objects
+            '.tfrecords', '.tf',  # TensorFlow files
+            '.onnx',  # ONNX models
+            '.h5', '.hdf5',  # HDF5 files
+            '.npy', '.npz',  # NumPy files
+            
+            # Build outputs
+            '.min.js', '.min.css',
+            '.bundle.js', '.bundle.css',
+            '.chunk.js', '.chunk.css'
+            
+        ]) or any(pattern in file_path for pattern in [
+            # Special directories
+            '/node_modules/',
+            '/__pycache__/',
+            '/.git/',
+            '/.idea/',
+            '/.vscode/',
+            '/.vs/',
+            '/.svn/',
+            '/.hg/',
+            '/dist/',
+            '/build/',
+            '/target/',
+            '/out/',
+            '/bin/',
+            '/obj/',
+            '/Debug/',
+            '/Release/',
+            '/.next/',
+            '/.nuxt/',
+            '/vendor/',
+            '/venv/',
+            '/.env',
+            '/coverage/',
+            '/logs/',
+            '/.github/',
+            '/assets/',
+            '/public/assets/',
+            '/static/assets/',
+            '/.pytest_cache/',
+            '/.sass-cache/',
+            '/.parcel-cache/',
+            '/.cache/',
+            '/tmp/',
+            '/temp/'
+        ]):
+            logger.debug(f"Skipping non-processable file: {file_path}")
             return None
 
         if file_key not in self._file_contents:  # Check if file content has already been fetched
@@ -303,8 +382,8 @@ class Repository:
             # Full GitHub issue/PR URL pattern
             rf'(?:https?://)?github\.com/{re.escape(self.full_name)}/(?:issues|pull)/(\d+)',
             
-            # Standard #123 reference with proper boundaries
-            r'(?:^|[^\w/])#(\d+)(?=[^\w/]|$)',
+            # # Standard #123 reference with proper boundaries
+            # r'(?:^|[^\w/])#(\d+)(?=[^\w/]|$)',
             
             # Closing keywords (fixes #123)
             fr'(?:^|[^\w/])(?:{"|".join(closing_keywords)}):?\s+#(\d+)(?=[^\w/]|$)',
@@ -377,7 +456,7 @@ class Repository:
             return dt.astimezone(timezone.utc).replace(microsecond=0).isoformat().replace('+00:00', 'Z')
         return None
 
-    def get_pr_content(self, number, pr=None, context_lines=10) -> Dict[str, Any]:
+    def get_pr_content(self, number, pr=None, context_lines=10, force_update=False) -> Dict[str, Any]:
         """
         Retrieves and processes the content of a pull request.
 
@@ -386,9 +465,9 @@ class Repository:
         :param context_lines: Number of context lines for diffs.
         :return: A dictionary containing detailed PR information.
         """
-        if number not in self._prs:  # Check if issue has already been fetched
+        if number not in self._prs or force_update:  # Check if issue has already been fetched
             with self._pr_lock:  # Locking for write action
-                if number not in self._prs:  # Check if issue has already been fetched after get lock
+                if number not in self._prs or force_update:  # Check if issue has already been fetched after get lock
                     try:
                         logger.debug(f"Processing PR #{number}")
                         if pr is None:
@@ -552,7 +631,7 @@ class Repository:
 
                             # Generate custom diff with specified context lines
                             if base_content is None and head_content is None:
-                                custom_diff = ''
+                                custom_diff = '[SKIPPED] File type not suitable for diff analysis'
                             else:
                                 custom_diff = DiffGenerator.generate_custom_diff(base_content, head_content, context_lines)
                                 if not custom_diff or custom_diff.strip() == '':
@@ -691,13 +770,29 @@ class RepositoryPool:
                 self._locks_registry[full_name] = Lock()
             return self._locks_registry[full_name]
 
-    def get_repository(self, full_name, **kwargs) -> Repository:
-        """Retrieve a repository from the pool or create a new one if it doesn't exist."""
+    def get_repository(self, full_name, github_instance=None, **kwargs) -> Repository:
+        """
+        Retrieve a repository from the pool or create a new one if it doesn't exist.
+        
+        If you are using github_install_id to generate a new repository object, you should pass new github_instance to the function.
+        Otherwise the default github_instance within the pool might not fit to the new repository object.
+        """
+
         if full_name in self._pool:
+            # repo = self._pool[full_name]
+            # repo.update_last_read_time()
+            # if github_instance is not None:
+            #     repo.set_github(github_instance)
+            # return repo
             return self._pool[full_name]
+        
         repo_lock = self._get_repo_lock(full_name)
         with repo_lock:
             if full_name not in self._pool:
-                self._pool[full_name] = Repository(
-                    full_name, self.github_instance, **kwargs)
-        return self._pool[full_name]
+                if github_instance is not None:
+                    repo = Repository(full_name, github_instance, **kwargs)
+                else:
+                    repo = Repository(full_name, self.github_instance, **kwargs)
+                self._pool[full_name] = repo
+
+        return self._pool[full_name]

{llama_github-0.1.9 → llama_github-0.2.1}/llama_github/llm_integration/initial_load.py

@@ -69,7 +69,7 @@ class LLMManager:
         elif mistral_api_key is not None and mistral_api_key != "" and self.llm is None:
             logger.info("Initializing Mistral API...")
             self.llm = ChatMistralAI(mistral_api_key=mistral_api_key, model="mistral-large-latest")
-            self.llm_simple = ChatMistralAI(mistral_api_key=mistral_api_key, model="open-mistral-nemo")
+            self.llm_simple = ChatMistralAI(mistral_api_key=mistral_api_key, model="open-codestral-mamba")
             self.model_type = "OpenAI"
         elif openai_api_key is not None and openai_api_key != "" and self.llm is None:
             logger.info("Initializing OpenAI API...")

llama_github-0.2.1/llama_github/version.py

@@ -0,0 +1 @@
+__version__ = '0.2.1'

{llama_github-0.1.9 → llama_github-0.2.1/llama_github.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-github
-Version: 0.1.9
+Version: 0.2.1
 Summary: Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Agents to conduct Retrieval from actively selected GitHub public projects. It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.
 Home-page: https://github.com/JetXu-LLM/llama-github
 Author: Jet Xu
@@ -96,6 +96,22 @@ For more advanced usage and examples, please refer to the [documentation](docs/u
 
 - **🛠️ Logging and Error Handling**: We understand the importance of smooth operations and easy troubleshooting. That's why llama-github comes equipped with comprehensive logging and error handling mechanisms. Gain deep insights into the library's behavior, quickly diagnose issues, and maintain a stable and reliable development workflow.
 
+## 🤖 Try Our AI-Powered PR Review Assistant: LlamaPReview
+
+If you find llama-github useful, you might also be interested in our AI-powered GitHub PR review assistant, LlamaPReview. It's designed to complement your development workflow and further enhance code quality.
+
+### Key Features of LlamaPReview:
+- 🚀 One-click installation, zero configuration required, fully auto-run
+- 💯 Currently free to use - no credit card or payment info needed
+- 🧠 AI-powered, automatic PR reviews with deep code understanding
+- 🌐 Supports multiple programming languages
+
+**LlamaPReview utilizes llama-github's advanced context retrieval and LLM-powered analysis** to provide intelligent, context-aware code reviews. It's like having a senior developer, armed with the full context of your repository, review every PR automatically!
+
+👉 [Install LlamaPReview Now](https://github.com/marketplace/llamapreview/) (Free)
+
+By using llama-github for context retrieval and LlamaPReview for code reviews, you can create a powerful, AI-enhanced development environment.
+
 ## Vision and Roadmap
 
 ### Vision
@@ -140,7 +156,17 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.1.9] - 2024-10-31
+## [0.2.1] - 2024-11-16
+
+### Optimized
+- approperately handle more file types when calculate file changes in PR
+
+## [0.2.0] - 2024-11-16
+
+### Optimized
+- fix bugs for generate repo from pool by using Github_install_id
+
+## [0.1.9] - 2024-11-04
 
 ### Optimized
 - fix bugs for get pr content

{llama_github-0.1.9 → llama_github-0.2.1}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = llama-github
-version = 0.1.9
+version = 0.2.1
 author = Jet Xu
 author_email = Voldemort.xu@foxmail.com
 description = Llama-github is an open-source Python library that empowers LLM Chatbots, AI Agents, and Auto-dev Agents to conduct Retrieval from actively selected GitHub public projects. It Augments through LLMs and Generates context for any coding question, in order to streamline the development of sophisticated AI-driven applications.

llama_github-0.1.9/llama_github/version.py

@@ -1 +0,0 @@
-__version__ = '0.1.9'