pawnai-matrix 0.2.0__tar.gz

pawnai_matrix-0.2.0/.dockerignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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
+db.sqlite3
+db.sqlite3-journal
+
+# 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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/
+
+
+config.yaml
+bob.db
+store

pawnai_matrix-0.2.0/.github/workflows/publish.yml

@@ -0,0 +1,66 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - "v[0-9]+.[0-9]+.[0-9]*"
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    name: Build distribution
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          # Full history is required for setuptools-scm to derive the version
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install build tools
+        run: python -m pip install --upgrade build
+
+      - name: Build sdist and wheel
+        run: python -m build
+
+      - name: Upload distribution artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    name: Publish to PyPI
+    needs: build
+    runs-on: ubuntu-latest
+
+    # Trusted Publishing: no API token needed — configure this environment
+    # on PyPI under your project's "Publishing" settings:
+    #   Publisher: GitHub Actions
+    #   Owner:     <your-github-org-or-user>
+    #   Repo:      matrix-bob
+    #   Workflow:  publish.yml
+    #   Environment: pypi
+    environment:
+      name: pypi
+      url: https://pypi.org/p/pawnai-matrix
+
+    permissions:
+      id-token: write  # required for OIDC Trusted Publishing
+
+    steps:
+      - name: Download distribution artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

pawnai_matrix-0.2.0/.gitignore

@@ -0,0 +1,172 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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
+db.sqlite3
+db.sqlite3-journal
+
+# 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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.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/
+
+
+config.yaml
+bob.db
+jobs.sqlite
+store
+tmp
+.db
+.idea
+
+# Generated by setuptools-scm at build time
+pawnai_matrix/_version.py

pawnai_matrix-0.2.0/.gitlab-ci.yml

@@ -0,0 +1,100 @@
+stages:
+  - maintenance
+  - build
+  - deploy
+
+restart_ollama:
+  stage: maintenance
+  variables:
+    GIT_STRATEGY: none
+    GIT_CHECKOUT: "false"    
+  tags:
+    - ollama
+    - shell
+  script:
+    - sudo systemctl restart ollama
+    - sleep 5
+    - sudo systemctl status ollama
+  when: manual
+
+restart_pawnai_matrix:
+  stage: maintenance
+  variables:
+    GIT_STRATEGY: none
+    GIT_CHECKOUT: "false"  
+  tags:
+    - matrix-bob
+    - shell
+  script:
+    - sudo systemctl restart matrix-bob
+    - sleep 5
+    - sudo systemctl status matrix-bob
+  when: manual  
+
+get_pawnai_matrix_logs:
+  stage: maintenance
+  variables:
+    GIT_STRATEGY: none
+    GIT_CHECKOUT: "false"  
+  tags:
+    - matrix-bob
+    - shell
+  script:
+    - sudo journalctl -u matrix-bob -n 1000
+  when: manual 
+
+restart_qdrant:
+  stage: maintenance
+  variables:
+    GIT_STRATEGY: none
+    GIT_CHECKOUT: "false"  
+  tags:
+    - matrix-bob
+    - shell
+  script:
+    - sudo systemctl restart docker-qdrant
+    - sleep 5
+    - sudo systemctl status docker-qdrant
+  when: manual  
+
+build_package:
+  stage: build
+  image: python:3.12
+  script:
+    - pip install build twine bump
+    - bump
+    - python -m build
+    - TWINE_PASSWORD=${CI_JOB_TOKEN} TWINE_USERNAME=gitlab-ci-token python -m twine upload --repository-url ${CI_API_V4_URL}/projects/${CI_PROJECT_ID}/packages/pypi dist/*
+    - git config --global user.email "${GITLAB_USER_EMAIL}"
+    - git config --global user.name "${GITLAB_USER_NAME}"
+    - git remote set-url origin "https://gitlab-ci-token:${DEPLOY_TOKEN}@gitlab.com/${CI_PROJECT_NAMESPACE}/${CI_PROJECT_NAME}.git"
+    - git add .
+    - git commit -m "bump version"
+    - git push -o ci.skip --tags origin HEAD:${CI_COMMIT_REF_NAME}
+  only:
+    - master
+
+deploy:
+  stage: deploy
+  variables:
+    GIT_STRATEGY: none
+    GIT_CHECKOUT: "false"  
+  tags:
+    - matrix-bob
+    - shell
+  before_script:
+    - |
+      echo "
+      machine gitlab.com
+      login gitlab-ci-token
+      password $CI_JOB_TOKEN
+      " > ~/.netrc 
+  script:
+    - cd /opt/matrix-bob
+    - source .venv/bin/activate
+    - pip install "matrix-bob" --upgrade --index-url ${CI_API_V4_URL}/projects/${CI_PROJECT_ID}/packages/pypi/simple
+    - sudo systemctl restart matrix-bob
+    - sleep 5
+    - sudo systemctl status matrix-bob
+  only:
+    - master

pawnai_matrix-0.2.0/.vscode/launch.json

@@ -0,0 +1,27 @@
+{
+  // Use IntelliSense to learn about possible attributes.
+  // Hover to view descriptions of existing attributes.
+  // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "name": "Python Debugger: Run Bob",
+      "type": "debugpy",
+      "request": "launch",
+      "program": "${workspaceFolder}/bin/bob",
+      "console": "integratedTerminal",
+      "cwd": "${workspaceFolder}/bin",
+      "justMyCode": true
+    },
+    {
+      "name": "Python Debugger: scripts/import_yaml_config.py",
+      "type": "debugpy",
+      "request": "launch",
+      "program": "${workspaceFolder}/scripts/import_yaml_config.py",
+      "args": ["${workspaceFolder}/bin/config.yaml"],
+      "console": "integratedTerminal",
+      "cwd": "${workspaceFolder}/bin",
+      "justMyCode": true
+    }    
+  ]
+}

pawnai_matrix-0.2.0/.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+  "[python]": {
+    "editor.defaultFormatter": "eeyore.yapf"
+  }
+}

pawnai_matrix-0.2.0/CLAUDE.md

@@ -0,0 +1,96 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+Matrix BOB is a Matrix protocol bot that integrates LLMs, vector search (RAG), audio transcription, and image processing into Matrix chat rooms. It uses `matrix-nio` for the Matrix client, LlamaIndex + Qdrant for RAG, and an OpenAI-compatible API (e.g. Ollama) for LLM inference.
+
+## Development Setup
+
+```bash
+# Install in editable mode
+python -m venv .venv
+source .venv/bin/activate
+pip install --editable .
+
+# Start required services (Qdrant + PostgreSQL + Adminer)
+cd docker && docker-compose up -d
+
+# Run database migrations
+alembic upgrade head
+
+# Start the bot
+./bin/bob [config.yaml]
+```
+
+Config file defaults to `bin/config.yaml`. Use `bin/sample.config.yaml` as a template.
+
+## Code Style
+
+```bash
+flake8 pawnai_matrix/
+isort pawnai_matrix/
+```
+
+Flake8 ignores: W503, W504, E203, E731, E501. isort uses multi-line output mode 3 with trailing commas.
+
+There are no automated tests.
+
+## Architecture
+
+### Global State (`pawnai_matrix/globals.py`)
+
+All major singletons are initialized in `init(config_file_path)` and accessed via getter functions (`settings()`, `config()`, `store()`, `client()`, `room_manager()`). These raise `NotInitializedError` if called before initialization. `config()` returns a flat dict of all bot configuration loaded from the PostgreSQL `BotConfiguration` table (not the YAML directly — YAML populates defaults at startup).
+
+### Configuration System
+
+Two-layer config:
+1. **YAML** (`bin/config.yaml`) — minimal bootstrap: DB connection string, Matrix credentials to seed into DB
+2. **Database** (`BotConfiguration` table) — runtime config as key-value pairs (e.g. `openai.default_model`, `matrix.command_prefix`). Accessed via `config().get('section.key')`. Use `utils/config.py` helpers (`get_value`, `set_value`, `get_config_dict`) for DB-level config access.
+
+### Command Dispatch (`pawnai_matrix/commands/`)
+
+Commands flow: `SystemCommands` → `VisionCommands` → `ConversationCommands`. Each returns a truthy value if it handled the message. Commands use docopt-format docstrings parsed by the `@matrix_command` decorator. Power-user-only commands use `@power_user_function`.
+
+`ConversationCommands` is the catch-all — it sends the message to the LLM chat engine.
+
+### Room Configuration (`pawnai_matrix/room.py`)
+
+`Room` manages per-room state: assigned expert (LLM config preset), echo mode, index-conversation flag, vision two-step mode, and user display name mapping. Config is persisted to `RoomConfiguration` in PostgreSQL and cached in memory. Access via `room_manager().get(matrix_room)`.
+
+### LLM Client (`pawnai_matrix/openai_client.py`)
+
+`OpenAIClient` wraps LlamaIndex with an OpenAI-compatible backend. It manages:
+- LLM + embedding model initialization
+- Qdrant vector store index (collection per room/expert)
+- Chat engine (context mode or ReAct agent mode)
+- `Expert` serialization (save/load named LLM configurations)
+
+The client is lazily initialized and stored in the room's configuration dict.
+
+### Event Flow
+
+```
+Matrix event → Callbacks (callbacks.py)
+  ├── Text message → RoomListener.store_message_text → SystemCommands → VisionCommands → ConversationCommands
+  ├── Audio        → RoomListener.transcribe_audio_message → AudioProcessor (Whisper) → command or index
+  ├── Image        → RoomListener.describe_image → ImageProcessor (vision model) → index
+  └── File         → RoomListener.store_file → LlamaIndex SimpleDirectoryReader → index
+```
+
+### Database Models (`pawnai_matrix/models.py`)
+
+- `Expert` — named LLM configurations (JSON-serialized `OpenAIClient` state)
+- `RoomConfiguration` — per-room expert assignment + config blob
+- `BotConfiguration` — global key-value config store
+- `RoomMessage` — message history (room_id, author, text, timestamp)
+
+Migrations are in `alembic/versions/`.
+
+## Key Patterns
+
+- **Async throughout**: All callbacks and processors are `async`. `nest_asyncio` is applied at startup to allow nested event loops.
+- **Encrypted room support**: `matrix-nio[e2e]` handles E2EE. File downloads use `download_event_resources()` context manager which handles decryption and temp file cleanup.
+- **Reply chains**: `get_related_reply_to_events()` in `utils/chat.py` recursively fetches reply chains to build conversation context.
+- **Debug state**: Processing artifacts (transcriptions, vision descriptions, last error) are stored globally via `set_debug_*` and retrievable via `!bob debug` commands.