chatsbom 0.2.1__tar.gz

chatsbom-0.2.1/.env.example

@@ -0,0 +1,3 @@
+GITHUB_TOKEN=
+ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic
+ANTHROPIC_AUTH_TOKEN=

chatsbom-0.2.1/.github/workflows/release.yaml

@@ -0,0 +1,24 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - v*
+  workflow_dispatch:
+
+jobs:
+  pypi:
+    name: Publish to PyPI
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+      attestations: write
+      id-token: write
+    environment:
+      name: release
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v3
+      - run: uv build
+      - run: uv publish --trusted-publishing always

chatsbom-0.2.1/.github/workflows/weekly.yml

@@ -0,0 +1,22 @@
+name: Weekly Tests
+
+on:
+  schedule:
+    - cron: '0 0 * * 0'
+  workflow_dispatch:
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Install dependencies
+        run: uv sync
+
+      - name: Run tests
+        run: uv run pytest

chatsbom-0.2.1/.gitignore

@@ -0,0 +1,231 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+*.sqlite3-shm
+*.sqlite3-wal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer,
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# request-cache database file
+*.sqlite
+*.sqlite-journal
+*.sqlite-shm
+*.sqlite-wal
+
+# Data folder
+/data/
+
+# JSONL folder
+/*.jsonl
+
+# Database folder
+/database/

chatsbom-0.2.1/.pre-commit-config.yaml

@@ -0,0 +1,63 @@
+exclude: ^(benchmarks/(?!.*\.analysis/.*\.py)|parameters/examples/|.*\.patch|.*\.diff|.*/recipes/patches/|.*/recipes/files/)
+
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+    -   id: trailing-whitespace
+    -   id: end-of-file-fixer
+    -   id: check-yaml
+    -   id: debug-statements
+    -   id: double-quote-string-fixer
+    -   id: name-tests-test
+    -   id: requirements-txt-fixer
+    -   id: check-json
+    -   id: pretty-format-json
+        args: [--autofix, --indent=4]
+-   repo: https://github.com/asottile/setup-cfg-fmt
+    rev: v2.8.0
+    hooks:
+    -   id: setup-cfg-fmt
+-   repo: https://github.com/asottile/reorder-python-imports
+    rev: v3.15.0
+    hooks:
+    -   id: reorder-python-imports
+        exclude: ^(pre_commit/resources/|testing/resources/python3_hooks_repo/)
+        args: [--py312-plus]
+-   repo: https://github.com/asottile/add-trailing-comma
+    rev: v3.2.0
+    hooks:
+    -   id: add-trailing-comma
+-   repo: https://github.com/asottile/pyupgrade
+    rev: v3.20.0
+    hooks:
+    -   id: pyupgrade
+        args: [--py312-plus]
+-   repo: https://github.com/hhatto/autopep8
+    rev: v2.3.2
+    hooks:
+    -   id: autopep8
+-   repo: https://github.com/PyCQA/flake8
+    rev: 7.3.0
+    hooks:
+    -   id: flake8
+        args: ['--ignore=E501,W504']
+-   repo: https://github.com/PyCQA/autoflake
+    rev: v2.3.1
+    hooks:
+    -   id: autoflake
+        args: [--remove-all-unused-imports, --in-place]
+-   repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.17.1
+    hooks:
+    -   id: mypy
+        additional_dependencies:
+            - types-pyyaml
+            - types-requests
+            - pandas-stubs
+            - sqlmodel
+        exclude: ^(testing/resources/|benchmarks/)
+-   repo: https://github.com/citation-file-format/cffconvert
+    rev: 054bda51dbe278b3e86f27c890e3f3ac877d616c
+    hooks:
+      - id: validate-cff

chatsbom-0.2.1/.python-version

@@ -0,0 +1 @@
+3.12

chatsbom-0.2.1/PKG-INFO

@@ -0,0 +1,125 @@
+Metadata-Version: 2.4
+Name: chatsbom
+Version: 0.2.1
+Summary: ChatSBOM - Talk to your Supply Chain. Chat with SBOMs.
+Requires-Python: >=3.12
+Requires-Dist: claude-agent-sdk>=0.1.0
+Requires-Dist: clickhouse-connect>=0.7.0
+Requires-Dist: clickhouse-connect>=0.7.16
+Requires-Dist: dotenv>=0.9.9
+Requires-Dist: mcp>=1.26.0
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: prompt-toolkit>=3.0.0
+Requires-Dist: pygithub>=2.8.1
+Requires-Dist: ratelimit>=2.2.1
+Requires-Dist: requests-cache>=1.3.0
+Requires-Dist: requests>=2.32.5
+Requires-Dist: rich>=14.3.2
+Requires-Dist: structlog>=24.0.0
+Requires-Dist: textual>=7.5.0
+Requires-Dist: typer>=0.21.1
+Description-Content-Type: text/markdown
+
+# ChatSBOM
+
+**Talk to your Supply Chain. Chat with SBOMs.**
+
+ChatSBOM is a CLI tool for deep insights into Software Bill of Materials (SBOM) data.
+
+![Demo](figures/demo.gif)
+
+## Motivation
+
+GitHub's Dependency Graph shows which repositories depend on your project, but there's no way to sort dependents by stars ([isaacs/github#1537](https://github.com/isaacs/github/issues/1537)). This makes it difficult for maintainers of popular packages to identify their most important downstream users. **ChatSBOM** solves this by collecting and indexing SBOM data, enabling queries like "which popular projects use my library?"
+
+## Key Features
+
+- **Collect**: Find high-quality repos on GitHub (stars/language)
+- **Download**: Fetch dependency files (`go.mod`, `package.json`, etc.)
+- **Convert**: Transform files to standard SBOM format using Syft
+- **Index**: Load SBOM data into ClickHouse database
+- **Status**: View database statistics and insights
+- **Query**: Search for library dependencies via CLI
+- **Chat**: AI-powered natural language queries
+
+## Quick Start
+
+### Prerequisites
+
+- [uv](https://github.com/astral-sh/uv) - Python package manager for fast installation and execution of the CLI tool
+- [syft](https://github.com/anchore/syft) - SBOM generation tool for extracting dependency data from project files
+- [docker](https://github.com/docker/docker) - Container runtime for running infrastructure services
+- [docker-compose](https://github.com/docker/compose) - Container orchestration tool for managing multi-container deployments
+- [clickhouse](https://github.com/ClickHouse/ClickHouse) - Columnar database for storing and querying SBOM metadata efficiently
+
+### Usage
+
+Install `uv`
+
+```bash
+curl -LsSf https://astral.sh/uv/install.sh | sh
+```
+
+Run commands directly with `uvx`:
+
+```bash
+# 1. Collect repository links from GitHub (e.g., top Go repos)
+uvx chatsbom collect --language go --min-stars 1000
+
+# 2. Download dependency files
+uvx chatsbom download --language go
+
+# 3. Convert to standard SBOM format
+uvx chatsbom convert --language go
+
+# 4. Index SBOM data into database
+uvx chatsbom index --language go
+
+# 5. Show database statistics
+uvx chatsbom status
+
+# 6. Query dependencies
+uvx chatsbom query gin
+
+# 7. Launch AI chat interface
+uvx chatsbom chat
+```
+
+## Architecture
+
+ChatSBOM follows a clean, modular architecture with high cohesion and low coupling:
+
+### Command Flow
+
+```
+collect → download → convert → index → status/query/chat
+   ↓         ↓          ↓         ↓
+ .jsonl    files/    sbom.json  database
+```
+
+### Core Modules
+
+- **`chatsbom.core.config`**: Centralized configuration management
+  - Path conventions (data directories, file naming)
+  - Database connection settings
+  - GitHub API configuration
+
+- **`chatsbom.core.repository`**: Data access layer (Repository Pattern)
+  - Abstracts all database operations
+  - Uses generators for memory-efficient data streaming
+  - Supports batch operations for large datasets
+
+- **`chatsbom.core.validation`**: Data validation utilities
+  - Validates data flow between commands
+  - Ensures data integrity
+
+- **`chatsbom.commands.*`**: CLI commands (7 commands)
+  - Each command has a single responsibility
+  - Decoupled through configuration and repository layers
+
+## Use Cases
+
+### Asking AI Agent to retrieve the top 10 projects using gin framework.
+
+![01](figures/use-cases/gin/01.png)
+![02](figures/use-cases/gin/02.png)

chatsbom-0.2.1/README.md

@@ -0,0 +1,103 @@
+# ChatSBOM
+
+**Talk to your Supply Chain. Chat with SBOMs.**
+
+ChatSBOM is a CLI tool for deep insights into Software Bill of Materials (SBOM) data.
+
+![Demo](figures/demo.gif)
+
+## Motivation
+
+GitHub's Dependency Graph shows which repositories depend on your project, but there's no way to sort dependents by stars ([isaacs/github#1537](https://github.com/isaacs/github/issues/1537)). This makes it difficult for maintainers of popular packages to identify their most important downstream users. **ChatSBOM** solves this by collecting and indexing SBOM data, enabling queries like "which popular projects use my library?"
+
+## Key Features
+
+- **Collect**: Find high-quality repos on GitHub (stars/language)
+- **Download**: Fetch dependency files (`go.mod`, `package.json`, etc.)
+- **Convert**: Transform files to standard SBOM format using Syft
+- **Index**: Load SBOM data into ClickHouse database
+- **Status**: View database statistics and insights
+- **Query**: Search for library dependencies via CLI
+- **Chat**: AI-powered natural language queries
+
+## Quick Start
+
+### Prerequisites
+
+- [uv](https://github.com/astral-sh/uv) - Python package manager for fast installation and execution of the CLI tool
+- [syft](https://github.com/anchore/syft) - SBOM generation tool for extracting dependency data from project files
+- [docker](https://github.com/docker/docker) - Container runtime for running infrastructure services
+- [docker-compose](https://github.com/docker/compose) - Container orchestration tool for managing multi-container deployments
+- [clickhouse](https://github.com/ClickHouse/ClickHouse) - Columnar database for storing and querying SBOM metadata efficiently
+
+### Usage
+
+Install `uv`
+
+```bash
+curl -LsSf https://astral.sh/uv/install.sh | sh
+```
+
+Run commands directly with `uvx`:
+
+```bash
+# 1. Collect repository links from GitHub (e.g., top Go repos)
+uvx chatsbom collect --language go --min-stars 1000
+
+# 2. Download dependency files
+uvx chatsbom download --language go
+
+# 3. Convert to standard SBOM format
+uvx chatsbom convert --language go
+
+# 4. Index SBOM data into database
+uvx chatsbom index --language go
+
+# 5. Show database statistics
+uvx chatsbom status
+
+# 6. Query dependencies
+uvx chatsbom query gin
+
+# 7. Launch AI chat interface
+uvx chatsbom chat
+```
+
+## Architecture
+
+ChatSBOM follows a clean, modular architecture with high cohesion and low coupling:
+
+### Command Flow
+
+```
+collect → download → convert → index → status/query/chat
+   ↓         ↓          ↓         ↓
+ .jsonl    files/    sbom.json  database
+```
+
+### Core Modules
+
+- **`chatsbom.core.config`**: Centralized configuration management
+  - Path conventions (data directories, file naming)
+  - Database connection settings
+  - GitHub API configuration
+
+- **`chatsbom.core.repository`**: Data access layer (Repository Pattern)
+  - Abstracts all database operations
+  - Uses generators for memory-efficient data streaming
+  - Supports batch operations for large datasets
+
+- **`chatsbom.core.validation`**: Data validation utilities
+  - Validates data flow between commands
+  - Ensures data integrity
+
+- **`chatsbom.commands.*`**: CLI commands (7 commands)
+  - Each command has a single responsibility
+  - Decoupled through configuration and repository layers
+
+## Use Cases
+
+### Asking AI Agent to retrieve the top 10 projects using gin framework.
+
+![01](figures/use-cases/gin/01.png)
+![02](figures/use-cases/gin/02.png)

chatsbom-0.2.1/chatsbom/__main__.py

@@ -0,0 +1,27 @@
+import typer
+
+from chatsbom.commands import chat
+from chatsbom.commands import collect
+from chatsbom.commands import convert
+from chatsbom.commands import download
+from chatsbom.commands import index
+from chatsbom.commands import query
+from chatsbom.commands import status
+
+app = typer.Typer(
+    help='ChatSBOM - Talk to your Supply Chain. Chat with SBOMs.',
+    no_args_is_help=True,
+    add_completion=False,
+)
+
+# Commands ordered by typical workflow
+app.command(name='collect')(collect.main)
+app.command(name='download')(download.main)
+app.command(name='convert')(convert.main)
+app.command(name='index')(index.main)
+app.command(name='status')(status.main)
+app.command(name='chat')(chat.main)
+app.command(name='query')(query.main)
+
+if __name__ == '__main__':
+    app()

chatsbom-0.2.1/chatsbom/commands/__init__.py

@@ -0,0 +1 @@
+# CLI Commands