awslabs.git-repo-research-mcp-server 0.0.1__py3-none-any.whl

awslabs/__init__.py

@@ -0,0 +1,12 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance
+# with the License. A copy of the License is located at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# or in the 'license' file accompanying this file. This file is distributed on an 'AS IS' BASIS, WITHOUT WARRANTIES
+# OR CONDITIONS OF ANY KIND, express or implied. See the License for the specific language governing permissions
+# and limitations under the License.
+# This file is part of the awslabs namespace.
+# It is intentionally minimal to support PEP 420 namespace packages.

awslabs/git_repo_research_mcp_server/__init__.py

@@ -0,0 +1,13 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance
+# with the License. A copy of the License is located at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# or in the 'license' file accompanying this file. This file is distributed on an 'AS IS' BASIS, WITHOUT WARRANTIES
+# OR CONDITIONS OF ANY KIND, express or implied. See the License for the specific language governing permissions
+# and limitations under the License.
+"""awslabs.git-repo-research-mcp-server"""
+
+__version__ = '0.0.0'

awslabs/git_repo_research_mcp_server/defaults.py

@@ -0,0 +1,347 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance
+# with the License. A copy of the License is located at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# or in the 'license' file accompanying this file. This file is distributed on an 'AS IS' BASIS, WITHOUT WARRANTIES
+# OR CONDITIONS OF ANY KIND, express or implied. See the License for the specific language governing permissions
+# and limitations under the License.
+"""Default constants for Git Repository Research MCP Server."""
+
+
+class Constants:
+    """Constants used throughout the Git Repository Research MCP Server."""
+
+    # Text file patterns for repository file filtering
+    TEXT_FILE_INCLUDE_PATTERNS = [
+        '*.py',
+        '*.js',
+        '*.ts',
+        '*.jsx',
+        '*.tsx',
+        '*.html',
+        '*.htm',
+        '*.css',
+        '*.scss',
+        '*.sass',
+        '*.less',
+        '*.json',
+        '*.xml',
+        '*.yaml',
+        '*.yml',
+        '*.md',
+        '*.rst',
+        '*.txt',
+        '*.java',
+        '*.c',
+        '*.cpp',
+        '*.h',
+        '*.hpp',
+        '*.cs',
+        '*.rb',
+        '*.php',
+        '*.go',
+        '*.rs',
+        '*.swift',
+        '*.sh',
+        '*.bash',
+        '*.zsh',
+        '*.sql',
+        '*.kt',
+        '*.kts',
+        '*.dart',
+        '*.lua',
+        '*.r',
+        '*.pl',
+        '*.ps1',
+        '*.config',
+        '*.conf',
+        '*.cfg',
+        '*.ini',
+        '*.toml',
+        '*.graphql',
+        '*.proto',
+        'Dockerfile',
+        'docker-compose.yml',
+        'Makefile',
+        'README*',
+        'LICENSE*',
+        'CONTRIBUTING*',
+    ]
+
+    TEXT_FILE_EXCLUDE_PATTERNS = [
+        # Binary image files
+        '*.jpg',
+        '*.jpeg',
+        '*.png',
+        '*.gif',
+        '*.bmp',
+        '*.tiff',
+        '*.ico',
+        '*.svg',
+        '*.webp',
+        # Document and media files
+        '*.pdf',
+        '*.docx',
+        '*.xlsx',
+        '*.pptx',
+        '*.doc',
+        '*.xls',
+        '*.ppt',
+        '*.mp3',
+        '*.mp4',
+        '*.wav',
+        '*.avi',
+        '*.mov',
+        '*.ogg',
+        '*.flac',
+        # Archive files
+        '*.zip',
+        '*.tar',
+        '*.gz',
+        '*.rar',
+        '*.7z',
+        '*.bz2',
+        '*.xz',
+        '*.tgz',
+        # Binary executable, object and library files
+        '*.exe',
+        '*.dll',
+        '*.so',
+        '*.dylib',
+        '*.class',
+        '*.jar',
+        '*.war',
+        '*.ear',
+        '*.pyc',
+        '*.pyo',
+        '*.o',
+        '*.obj',
+        '*.a',
+        '*.lib',
+        '*.bin',
+        '*.whl',
+        # Data files
+        '*.dat',
+        '*.db',
+        '*.sqlite',
+        '*.sqlite3',
+        '*.mdb',
+        '*.ldb',
+        '*.frm',
+        # Lock files and package-specific files
+        '*.lock',
+        'package-lock.json',
+        'yarn.lock',
+        'poetry.lock',
+        # Common dependency directories
+        'node_modules/**',
+        'bower_components/**',
+        'jspm_packages/**',
+        'vendor/**',
+        '.gradle/**',
+        '.maven/**',
+        '.nuget/**',
+        # Virtual environments
+        '.venv/**',
+        'venv/**',
+        'env/**',
+        'virtualenv/**',
+        'ENV/**',
+        '.env/**',
+        '.tox/**',
+        # Build and distribution directories
+        'dist/**',
+        'build/**',
+        'target/**',
+        'bin/**',
+        'obj/**',
+        '__pycache__/**',
+        '.pytest_cache/**',
+        '*.egg-info/**',
+        '.eggs/**',
+        '.coverage/**',
+        # Git and version control
+        '.git/**',
+        '.github/**',
+        '.hg/**',
+        '.svn/**',
+        'CVS/**',
+        # IDE and editor directories
+        '.vscode/**',
+        '.idea/**',
+        '.vs/**',
+        '.settings/**',
+        '.project/**',
+        '.classpath/**',
+        '*.sublime-*',
+        # Minified files
+        '*.min.js',
+        '*.min.css',
+        '*.map',
+        # Various config directories
+        '.cache/**',
+        '.config/**',
+        # Logs and temporary files
+        'logs/**',
+        '*.log',
+        '*.tmp',
+        '*.temp',
+        # OS specific files
+        '.DS_Store',
+        'Thumbs.db',
+        'desktop.ini',
+        # Large data files
+        '*.csv',
+        '*.tsv',  # Consider including these if needed for analysis
+        '*.parquet',
+        '*.avro',
+        '*.orc',
+        # Machine learning specific
+        '*.onnx',
+        '*.pb',
+        '*.pt',
+        '*.pth',
+        '*.h5',
+        '*.hdf5',
+        '*.pkl',
+        '*.pickle',
+    ]
+
+    # Default directory for storing indices
+    DEFAULT_INDEX_DIR = '.git_repo_research'
+
+    # Default patterns for file inclusion
+    DEFAULT_INCLUDE_PATTERNS = [
+        '**/*.md',
+        '**/*.py',
+        '**/*.js',
+        '**/*.ts',
+        '**/*.java',
+        '**/*.go',
+        '**/*.rs',
+        '**/*.c',
+        '**/*.cpp',
+        '**/*.h',
+        '**/*.hpp',
+        '**/*.cs',
+        '**/*.rb',
+        '**/*.php',
+        '**/*.scala',
+        '**/*.swift',
+        '**/*.kt',
+        '**/*.groovy',
+        '**/*.sh',
+        '**/*.bash',
+        '**/*.ps1',
+        '**/*.md',
+        '**/*.rst',
+        '**/*.txt',
+        '**/*.html',
+        '**/*.css',
+        '**/*.scss',
+        '**/*.sass',
+        '**/*.less',
+        '**/*.json',
+        '**/*.yml',
+        '**/*.yaml',
+        '**/*.xml',
+        '**/*.toml',
+        '**/*.ini',
+        '**/*.cfg',
+        '**/*.conf',
+        '**/*.properties',
+        '**/*.tf',
+        '**/*.tfvars',
+        '**/*.cdk.ts',
+        '**/*.jsx',
+        '**/*.tsx',
+        '**/*.vue',
+        '**/*.sql',
+        '**/*.graphql',
+        '**/*.proto',
+        '**/*.dockerfile',
+        'Dockerfile',
+        'docker-compose.yml',
+        'Makefile',
+        'CMakeLists.txt',
+        '**/*.gradle',
+        'LICENSE',
+        'README*',
+        'CHANGELOG*',
+        'CONTRIBUTING*',
+        'CODE_OF_CONDUCT*',
+    ]
+
+    # Default patterns for file exclusion
+    DEFAULT_EXCLUDE_PATTERNS = [
+        '**/.git/**',
+        '**/.github/**',
+        '**/.svn/**',
+        '**/.hg/**',
+        '**/.bzr/**',
+        '**/node_modules/**',
+        '**/venv/**',
+        '**/.venv/**',
+        '**/env/**',
+        '**/.env/**',
+        '**/__pycache__/**',
+        '**/.pytest_cache/**',
+        '**/.coverage/**',
+        '**/coverage/**',
+        '**/dist/**',
+        '**/build/**',
+        '**/.DS_Store',
+        '**/*.pyc',
+        '**/*.pyo',
+        '**/*.pyd',
+        '**/*.so',
+        '**/*.dll',
+        '**/*.exe',
+        '**/*.bin',
+        '**/*.obj',
+        '**/*.o',
+        '**/*.a',
+        '**/*.lib',
+        '**/*.dylib',
+        '**/*.ncb',
+        '**/*.sdf',
+        '**/*.suo',
+        '**/*.pdb',
+        '**/*.idb',
+        '**/*.jpg',
+        '**/*.jpeg',
+        '**/*.png',
+        '**/*.gif',
+        '**/*.svg',
+        '**/*.ico',
+        '**/*.mp4',
+        '**/*.mov',
+        '**/*.wmv',
+        '**/*.flv',
+        '**/*.avi',
+        '**/*.mkv',
+        '**/*.mp3',
+        '**/*.wav',
+        '**/*.flac',
+        '**/*.zip',
+        '**/*.tar.gz',
+        '**/*.tar',
+        '**/*.rar',
+        '**/*.7z',
+        '**/*.pdf',
+        '**/*.docx',
+        '**/*.xlsx',
+        '**/*.pptx',
+        '**/logs/**',
+        '**/log/**',
+        '**/.idea/**',
+        '**/.vscode/**',
+        '**/.classpath',
+        '**/.project',
+        '**/.settings/**',
+        '**/.gradle/**',
+        '**/target/**',
+    ]

awslabs/git_repo_research_mcp_server/embeddings.py

@@ -0,0 +1,66 @@
+# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance
+# with the License. A copy of the License is located at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# or in the 'license' file accompanying this file. This file is distributed on an 'AS IS' BASIS, WITHOUT WARRANTIES
+# OR CONDITIONS OF ANY KIND, express or implied. See the License for the specific language governing permissions
+# and limitations under the License.
+"""Embeddings generation for Git Repository Research MCP Server.
+
+This module provides functionality for generating embeddings from text
+using Amazon Bedrock models via LangChain.
+"""
+
+import os
+from awslabs.git_repo_research_mcp_server.models import EmbeddingModel
+from langchain_aws import BedrockEmbeddings
+from langchain_core.embeddings.embeddings import Embeddings
+from loguru import logger
+from typing import Optional
+
+
+def create_bedrock_embeddings(
+    model_id: str = EmbeddingModel.AMAZON_TITAN_EMBED_TEXT_V2,
+    aws_region: Optional[str] = None,
+    aws_profile: Optional[str] = None,
+) -> Embeddings:
+    """Create and return an instance of BedrockEmbeddings.
+
+    Args:
+        model_id: ID of the embedding model to use
+        aws_region: AWS region to use (optional, uses default if not provided)
+        aws_profile: AWS profile to use (optional, uses default if not provided)
+
+    Returns:
+        BedrockEmbeddings: An instance of BedrockEmbeddings
+    """
+    aws_region = aws_region or os.environ.get('AWS_REGION', 'us-west-2')
+
+    bedrock_embeddings = BedrockEmbeddings(
+        model_id=model_id,
+        region_name=aws_region,
+        credentials_profile_name=aws_profile,
+    )
+    logger.info(f'Created BedrockEmbeddings with model: {model_id}')
+    return bedrock_embeddings
+
+
+def get_embedding_model(
+    model_id: str = EmbeddingModel.AMAZON_TITAN_EMBED_TEXT_V2,
+    aws_region: Optional[str] = None,
+    aws_profile: Optional[str] = None,
+) -> Embeddings:
+    """Factory method to return a LangChain embedding model.
+
+    Args:
+        model_id: ID of the embedding model to use
+        aws_region: AWS region to use (optional, uses default if not provided)
+        aws_profile: AWS profile to use (optional, uses default if not provided)
+
+    Returns:
+        Embeddings instance
+    """
+    return create_bedrock_embeddings(model_id, aws_region, aws_profile)