llama-github 0.2.0__tar.gz → 0.2.2__tar.gz

{llama_github-0.2.0 → llama_github-0.2.2}/CHANGELOG.md

@@ -5,6 +5,16 @@ 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).
 
+## [0.2.2] - 2024-11-19
+
+### Optimized
+- more precise model specification (stick to mistral-large-2407 and mistral-nemo-latest)
+
+## [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
@@ -113,4 +123,4 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 [0.1.3]: https://github.com/JetXu-LLM/llama-github/compare/v0.1.2...v0.1.3
 [0.1.2]: https://github.com/JetXu-LLM/llama-github/compare/v0.1.1...v0.1.2
 [0.1.1]: https://github.com/JetXu-LLM/llama-github/compare/v0.1.0...v0.1.1
-[0.1.0]: https://github.com/JetXu-LLM/llama-github/releases/tag/v0.1.0
+[0.1.0]: https://github.com/JetXu-LLM/llama-github/releases/tag/v0.1.0

{llama_github-0.2.0/llama_github.egg-info → llama_github-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-github
-Version: 0.2.0
+Version: 0.2.2
 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
@@ -156,6 +156,16 @@ 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).
 
+## [0.2.2] - 2024-11-19
+
+### Optimized
+- more precise model specification (stick to mistral-large-2407 and mistral-nemo-latest)
+
+## [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

{llama_github-0.2.0 → llama_github-0.2.2}/llama_github/data_retrieval/github_entities.py

@@ -159,14 +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', '.gitignore',
+            
+            # 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
@@ -557,7 +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() == '':
@@ -721,4 +795,4 @@ class RepositoryPool:
                     repo = Repository(full_name, self.github_instance, **kwargs)
                 self._pool[full_name] = repo
 
-        return self._pool[full_name]
+        return self._pool[full_name]

{llama_github-0.2.0 → llama_github-0.2.2}/llama_github/llm_integration/initial_load.py

@@ -68,8 +68,8 @@ class LLMManager:
             self.model_type = "Custom_langchain_llm"
         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-codestral-mamba")
+            self.llm = ChatMistralAI(mistral_api_key=mistral_api_key, model="mistral-large-2407")
+            self.llm_simple = ChatMistralAI(mistral_api_key=mistral_api_key, model="open-mistral-nemo")
             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...")
@@ -172,4 +172,4 @@ class LLMManager:
         Returns:
             The initialized embedding model.
         """
-        return self.embedding_model
+        return self.embedding_model

llama_github-0.2.2/llama_github/version.py

@@ -0,0 +1 @@
+__version__ = '0.2.2'

{llama_github-0.2.0 → llama_github-0.2.2/llama_github.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-github
-Version: 0.2.0
+Version: 0.2.2
 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
@@ -156,6 +156,16 @@ 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).
 
+## [0.2.2] - 2024-11-19
+
+### Optimized
+- more precise model specification (stick to mistral-large-2407 and mistral-nemo-latest)
+
+## [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

{llama_github-0.2.0 → llama_github-0.2.2}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = llama-github
-version = 0.2.0
+version = 0.2.2
 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-0.2.0/llama_github/version.py

@@ -1 +0,0 @@
-__version__ = '0.2.0'