Provisional project structure

.dockerignore

@@ -0,0 +1,69 @@
+# Git
+.git
+.gitignore
+
+# CI
+.github/
+
+# Docker
+Dockerfile
+.dockerignore
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# VS Code
+.vscode/
+
+# PyCharm
+.idea/
+
+# Jupyter notebooks
+notebooks/
+
+# Documentation
+docs/
+
+# MacOS
+.DS_Store

.env.template

@@ -0,0 +1,25 @@
+# Copy this file and modify. Do not save or commit the secrets!
+
+# API Configuration
+API_HOST=0.0.0.0
+API_PORT=8000
+DEBUG=false
+
+# MongoDB Configuration
+MONGODB_URI=mongodb+srv://username:[email protected]/database?retryWrites=true&w=majority
+MONGODB_DB_NAME=ctp_slack_bot
+
+# Slack Configuration
+SLACK_BOT_TOKEN=🪙
+SLACK_SIGNING_SECRET=🔏
+SLACK_APP_TOKEN=🦥
+
+# Hugging Face Configuration
+HF_API_TOKEN=🤗
+
+# Logging Configuration
+LOG_LEVEL=INFO
+LOG_FORMAT=json
+
+# APScheduler Configuration
+SCHEDULER_TIMEZONE=UTC

.gitignore

@@ -0,0 +1,98 @@
+# 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/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+*.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
+.hypothesis/
+.pytest_cache/
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# VS Code
+.vscode/
+
+# PyCharm
+.idea/
+
+# Jupyter notebooks
+notebooks/
+
+# MacOS
+.DS_Store

Dockerfile

@@ -0,0 +1,29 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+# Set environment variables.
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PYTHONPATH=/app
+
+# Install system dependencies.
+RUN apt-get update \
+ && apt-get install -y --no-install-recommends build-essential \
+ && apt-get clean \
+ && rm -rf /var/lib/apt/lists/*
+
+# Copy project files.
+COPY pyproject.toml README.md ./
+COPY src/ ./src/
+
+# Install Python dependencies.
+RUN pip install --no-cache-dir --upgrade pip \
+ && pip install --no-cache-dir .
+
+# Create a non-root user and switch to it.
+RUN useradd -m appuser
+USER appuser
+
+# Run the application.
+CMD ["uvicorn", "src.ctp_slack_bot.api.main:app", "--host", "0.0.0.0", "--port", "8000"]

README.MD

@@ -0,0 +1,26 @@
+# CTP Slack Bot
+
+
+## Dependencies
+
+* Python 3.12
+
+### Development-specific
+
+* Docker
+
+## General Project Structure
+
+* `src/`
+    * `ctp_slack_bot/`
+        * `api/`: FastAPI application structure
+        * `core/`: fundamental components like configuration (using pydantic), logging setup (loguru), and custom exceptions
+        * `db/`: database connection
+            * `repositories/`: repository pattern implementation
+        * `models/`: Pydantic models for data validation and serialization
+        * `services/`: business logic
+        * `tasks/`: background scheduled jobs
+        * `utils/`: reusable utilities
+* `tests/`: unit tests
+* `scripts/`: utility scripts for development, deployment, etc.
+* `notebooks/`: Jupyter notebooks for exploration and model development

README.md

@@ -1,2 +0,0 @@
-# 2025-Spring-BAI
-Spring 2025's Building AI Applications 

pyproject.toml

@@ -0,0 +1,90 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "ctp-slack-bot"
+version = "0.1.0"
+description = "A Slack bot for processing and analyzing Zoom transcripts using AI"
+readme = "README.md"
+requires-python = ">=3.12"
+license = {text = "MIT"}
+authors = [
+    {name = "Your Name", email = "[email protected]"}
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.12",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "pydantic>=2.0.0",
+    "fastapi>=0.100.0",
+    "uvicorn>=0.22.0",
+    "loguru>=0.7.0",
+    "python-dotenv>=1.0.0",
+    "httpx>=0.24.1",
+    "tenacity>=8.2.2",
+    "pybreaker>=1.0.2",
+    "apscheduler>=3.10.1",
+    "slack-sdk>=3.21.3",
+    "pymongo>=4.4.1",
+    "webvtt-py>=0.4.6",
+    "langchain>=0.0.200",
+    "transformers>=4.30.0",
+    "torch>=2.0.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.3.1",
+    "pytest-cov>=4.1.0",
+    "mypy>=1.3.0",
+    "black>=23.3.0",
+    "isort>=5.12.0",
+    "ruff>=0.0.270",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/yourusername/ctp-slack-bot"
+"Bug Tracker" = "https://github.com/yourusername/ctp-slack-bot/issues"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.mypy]
+python_version = "3.12"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true
+disallow_incomplete_defs = true
+check_untyped_defs = true
+disallow_untyped_decorators = true
+no_implicit_optional = true
+strict_optional = true
+
+[[tool.mypy.overrides]]
+module = ["apscheduler.*", "webvtt.*"]
+ignore_missing_imports = true
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = "test_*.py"
+python_classes = "Test*"
+python_functions = "test_*"
+
+[tool.black]
+line-length = 88
+target-version = ['py312']
+include = '\.pyi?$'
+
+[tool.isort]
+profile = "black"
+line_length = 88
+
+[tool.ruff]
+line-length = 88
+target-version = "py312"
+select = ["E", "F", "B", "I"]
+ignore = []

src/ctp_slack_bot/models/base.py

@@ -0,0 +1,61 @@
+from abc import ABC, abstractmethod
+from datetime import datetime
+from pydantic import BaseModel, Field, validator
+from typing import Dict, List, Optional, Union, Any, ClassVar
+import hashlib
+import json
+
+
+class Metadata(BaseModel):
+    """A class representing metadata about content."""
+
+    id: str                     # The content’s identity consistent across modifications
+    modification_time: datetime # The content’s modification for detection of alterations
+    hash: str                   # The content’s hash for detection of alterations
+
+
+class Content(BaseModel):
+    """A class representing ingested content."""
+
+    metadata: Metadata
+
+
+
+class Ingestible(ABC, BaseModel):
+    """An abstract base class for ingestible content."""
+
+    metadata: Metadata
+
+    @property
+    @abstractmethod
+    def content(self) -> Content:
+        """
+        Return content ready for vectorization.
+        
+        This could be:
+        - A single string
+        - A list of strings (pre-chunked)
+        - A more complex structure that can be recursively processed
+        """
+        pass
+    
+    def get_chunks(self) -> List[str]:
+        """
+        Split content into chunks suitable for vectorization.
+        Override this in subclasses for specialized chunking logic.
+        """
+        content = self.content
+        if isinstance(content, str):
+            # Simple chunking by character count
+            return [content[i:i+self.chunk_size] 
+                   for i in range(0, len(content), self.chunk_size)]
+        elif isinstance(content, list):
+            # Content is already chunked
+            return content
+        else:
+            raise ValueError(f"Unsupported content type: {type(content)}")
+    
+    @property
+    def key(self) -> str:
+        """Convenience accessor for the metadata key."""
+        return self.metadata.key

src/ctp_slack_bot/models/slack.py

@@ -0,0 +1,16 @@
+from pydantic import BaseModel, Field
+from typing import Optional, List, Dict, Any
+
+class SlackMessage(BaseModel):
+    """Represents a message from Slack after adaptation."""
+    channel_id: str
+    user_id: str
+    text: str
+    thread_ts: Optional[str] = None
+    timestamp: str
+    is_question: bool = False
+    
+    @property
+    def key(self) -> str:
+        """Unique identifier for this message."""
+        return f"slack:{self.channel_id}:{self.timestamp}"