services/vibe-bot
1
0
Fork 0
Code Issues 3 Pull Requests Actions Packages Projects Releases Wiki Activity

everything working again after cleanup

Browse Source
This commit is contained in:
Reese Wells
2026-05-23 23:56:03 -04:00
parent 6ec9fbe85f
commit 87a578f1de
13 changed files with 380 additions and 200 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+171 -117
View File
@@ -1,217 +1,271 @@
# Vibe Discord Bot with RAG Chat History
A Discord bot that stores long-term chat history using SQLite database with RAG (Retrieval-Augmented Generation) capabilities powered by custom embedding models.
A Discord bot that stores long-term chat history using SQLite with RAG (Retrieval-Augmented Generation) capabilities. It supports custom bots with personalities, text-to-speech via Kokoro, image generation, and image editing.
- [Vibe Discord Bot with RAG Chat History](#vibe-discord-bot-with-rag-chat-history)
- [Quick Start - Available Commands](#quick-start---available-commands)
- [Pre-built Bots](#pre-built-bots)
- [Available Commands](#available-commands)
- [Custom Bot Management](#custom-bot-management)
- [Using Custom Bots](#using-custom-bots)
- [Text-to-Speech](#text-to-speech)
- [Image Commands](#image-commands)
- [Bot Conversations](#bot-conversations)
- [Features](#features)
- [Setup](#setup)
- [Prerequisites](#prerequisites)
- [Environment Variables](#environment-variables)
- [Installation](#installation)
- [Running the Bot](#running-the-bot)
- [How It Works](#how-it-works)
- [Database Structure](#database-structure)
- [RAG Process](#rag-process)
- [Configuration Options](#configuration-options)
- [Usage](#usage)
- [File Structure](#file-structure)
- [Build](#build)
- [Using uv](#using-uv)
- [Building](#building)
- [Local](#local)
- [Container](#container)
- [Docs](#docs)
- [Open AI](#open-ai)
- [Models](#models)
- [Qwen3.5](#qwen35)
- [Testing](#testing)
- [Configuration](#configuration)
## Quick Start - Available Commands
### Pre-built Bots
| Command | Description | Example Usage |
| ------------ | ----------------------------- | ------------------------------------------ |
| `!doodlebob` | Generate images from text | `!doodlebob a cat sitting on a moon` |
| `!retcon` | Edit images with text prompts | `!retcon <image attachment> Make it sunny` |
## Available Commands
### Custom Bot Management
| Command | Description | Example Usage |
| ------------------------------ | --------------------------------------------- | ------------------------------------------------ |
| `!custom <name> <personality>` | Create a custom bot with specific personality | `!custom alfred you are a proper british butler` |
| `!list-custom-bots` | List all available custom bots | `!list-custom-bots` |
| `!delete-custom-bot <name>` | Delete your custom bot | `!delete-custom-bot alfred` |
| Command | Description | Example Usage |
| ---------------------------------- | -------------------------------------- | ---------------------------------------------------- |
| `!custom-bot <name> <personality>` | Create a custom bot with a personality | `!custom-bot alfred you are a proper british butler` |
| `!list-custom-bots` | List all available custom bots | `!list-custom-bots` |
| `!delete-custom-bot <name>` | Delete your custom bot (owner only) | `!delete-custom-bot alfred` |
### Using Custom Bots
Once you create a custom bot, you can interact with it directly by prefixing your message with the bot name:
Once you create a custom bot, interact with it by prefixing your message with the bot name:
```bash
```text
!<bot_name> <your message>
```
**Example:**
1. Create a bot: `!custom alfred you are a proper british butler`
1. Create a bot: `!custom-bot alfred you are a proper british butler`
2. Use the bot: `alfred Could you fetch me some tea?`
3. The bot will respond in character as a British butler
### Text-to-Speech
| Command | Description | Example Usage |
| -------------------------- | --------------------------------------- | ------------------------------- |
| `!speak <text>` | Convert text to speech (MP3 attachment) | `!speak hello world` |
| `!speak <bot_name> <text>` | Have a custom bot respond and speak | `!speak alfred what time is it` |
### Image Commands
| Command | Description | Example Usage |
| ------------ | ------------------------------------ | ------------------------------------------ |
| `!doodlebob` | Generate an image from a text prompt | `!doodlebob a cat sitting on the moon` |
| `!retcon` | Edit an attached image with text | `!retcon <image attachment> Make it sunny` |
### Bot Conversations
| Command | Description | Example Usage |
| -------------------------------------- | ------------------------------------------- | ------------------------------------------------ |
| `!talkforme <bot1> <bot2> <n> <topic>` | Have two bots discuss a topic for n replies | `!talkforme alfred jarvis 4 the meaning of life` |
## Features
- **Long-term chat history storage**: Persistent storage of all bot interactions
- **Long-term chat history storage**: Persistent storage of all bot interactions in SQLite
- **RAG-based context retrieval**: Smart retrieval of relevant conversation history using vector embeddings
- **Custom embedding model**: Uses qwen3-embed-4b for semantic search capabilities
- **Efficient message management**: Automatic cleanup of old messages based on configurable limits
- **Long-term chat history storage**: Persistent storage of all bot interactions
- **RAG-based context retrieval**: Smart retrieval of relevant conversation history using vector embeddings
- **Custom embedding model**: Uses qwen3-embed-4b for semantic search capabilities
- **Efficient message management**: Automatic cleanup of old messages based on configurable limits
- **Custom bots**: Create unlimited bots with unique personalities
- **Text-to-speech**: Kokoro TTS engine converts bot responses to MP3 audio
- **Image generation**: Generate images from text prompts via OpenAI-compatible API
- **Image editing**: Edit uploaded images with text instructions
- **Bot conversations**: Two custom bots can discuss a topic autonomously
- **Automatic message cleanup**: Configurable limits on stored messages
## Setup
### Prerequisites
- Python 3.10 or higher
- Python 3.13 or higher
- [uv](https://docs.astral.sh/uv/) package manager
- Embedding API key
- Discord bot token
- OpenAI-compatible API endpoints (for chat, embeddings, and image generation)
### Environment Variables
Create a `.env` file or export the following variables:
Create a `.env` file with the following variables:
```bash
# Discord Bot Token
export DISCORD_TOKEN=your_discord_bot_token
# Discord Bot Token (required)
DISCORD_TOKEN=your_discord_bot_token
# Embedding API Configuration
export OPENAI_API_KEY=your_embedding_api_key
export OPENAI_API_ENDPOINT=https://llama-embed.reeselink.com/embedding
# Chat/Completion API (required)
CHAT_ENDPOINT=https://your-api.com/v1
COMPLETION_ENDPOINT=https://your-api.com/v1
CHAT_ENDPOINT_KEY=your_api_key
COMPLETION_ENDPOINT_KEY=your_api_key
CHAT_MODEL=your_model_name
COMPLETION_MODEL=your_model_name
# Image Generation (optional)
export IMAGE_GEN_ENDPOINT=http://toybox.reeselink.com:1234/v1
export IMAGE_EDIT_ENDPOINT=http://toybox.reeselink.com:1235/v1
# Image Generation (required)
IMAGE_GEN_ENDPOINT=https://your-api.com/v1
IMAGE_EDIT_ENDPOINT=https://your-api.com/v1
IMAGE_GEN_ENDPOINT_KEY=your_api_key
IMAGE_EDIT_ENDPOINT_KEY=your_api_key
IMAGE_GEN_MODEL=gen
IMAGE_EDIT_MODEL=edit
# Database Configuration (optional)
export CHAT_DB_PATH=chat_history.db
export EMBEDDING_MODEL=qwen3-embed-4b
export EMBEDDING_DIMENSION=2048
export MAX_HISTORY_MESSAGES=1000
export SIMILARITY_THRESHOLD=0.7
export TOP_K_RESULTS=5
# Embedding API (required)
EMBEDDING_ENDPOINT=https://your-api.com/v1
EMBEDDING_ENDPOINT_KEY=your_api_key
EMBEDDING_MODEL=your_embed_model
# Optional: TTS Configuration
TTS_MODEL_PATH=kokoro-v1.0.onnx
TTS_VOICES_PATH=voices-v1.0.bin
TTS_VOICE=af_sarah
TTS_SPEED=1.0
# Optional: Database/Chat Settings
DB_PATH=chat_history.db
MAX_COMPLETION_TOKENS=1000
MAX_HISTORY_MESSAGES=1000
SIMILARITY_THRESHOLD=0.7
TOP_K_RESULTS=5
```
### Installation
1. Sync dependencies with uv:
```bash
uv sync
```
1. Clone the repository and sync dependencies:
```bash
uv sync
```
2. Ensure the TTS model files are present in the project root:
- `kokoro-v1.0.onnx`
- `voices-v1.0.bin`
### Running the Bot
2. Run the bot:
```bash
uv run main.py
uv run python -m vibe_bot.main
```
## How It Works
### Database Structure
The system uses two SQLite tables:
The system uses SQLite with three tables:
1. **chat_messages**: Stores message metadata
- message_id, user_id, username, content, timestamp, channel_id, guild_id
- `message_id`, `user_id`, `username`, `content`, `timestamp`, `channel_id`, `guild_id`
2. **message_embeddings**: Stores vector embeddings for RAG
- message_id, embedding (as binary blob)
- `message_id` (PK), `embedding` (binary blob of float32 values)
3. **custom_bots**: Stores custom bot configurations
- `bot_name` (PK), `system_prompt`, `created_by`, `created_at`, `is_active`
### RAG Process
1. When a message is received, it's stored in the database
2. An embedding is generated using OpenAI's embedding API
3. The embedding is stored alongside the message
4. When a new message is sent to the bot:
- The system searches for similar messages using vector similarity
- Relevant context is retrieved and added to the prompt
1. When a message is sent to a custom bot, it's stored in `chat_messages`
2. An embedding is generated via the configured embedding API and stored in `message_embeddings`
3. When a new message is sent:
- The system retrieves recent messages from the same user
- It searches for semantically similar messages using cosine similarity on embeddings
- Relevant context (user + bot message pairs) is prepended to the prompt
- The LLM generates a response with awareness of past conversations
### Configuration Options
- **MAX_HISTORY_MESSAGES**: Maximum number of messages to keep (default: 1000)
- **SIMILARITY_THRESHOLD**: Minimum similarity score for context retrieval (default: 0.7)
- **TOP_K_RESULTS**: Number of similar messages to retrieve (default: 5)
- **EMBEDDING_MODEL**: OpenAI embedding model to use (default: text-embedding-3-small)
## Usage
The bot maintains conversation context automatically. When you ask a question, it will:
1. Search for similar past conversations
2. Include relevant context in the prompt
3. Generate responses that are aware of the conversation history
## File Structure
```text
vibe_discord_bots/
├── main.py # Main bot application
├── database.py # SQLite database with RAG support
├── pyproject.toml # Project dependencies (uv)
├── .env # Environment variables
├── .venv/ # Virtual environment (created by uv)
└── README.md # This file
├── vibe_bot/
│ ├── __init__.py # Package marker
│ ├── main.py # Main bot application (commands, event handlers)
│ ├── config.py # Environment variable loading and validation
│ ├── database.py # SQLite database with RAG + CustomBotManager
│ ├── llama_wrapper.py # OpenAI-compatible API wrappers (chat, images, embeddings)
│ ├── tts.py # Kokoro TTS engine
│ └── tests/
│ ├── conftest.py # Shared test fixtures
│ ├── test_main.py # Bot command tests
│ ├── test_config.py # Config loading tests
│ ├── test_database.py # Database + CustomBotManager tests
│ ├── test_llama_wrapper.py # API wrapper tests
│ └── test_tts.py # TTS engine tests
├── pyproject.toml # Project dependencies (uv)
├── uv.lock # Locked dependency versions
├── .env # Environment variables
├── kokoro-v1.0.onnx # Kokoro TTS model
├── voices-v1.0.bin # Kokoro voice definitions
├── Containerfile # Podman/Docker build file
└── README.md # This file
```
## Build
## Building
### Using uv
### Local
```bash
# Set environment variables
export DISCORD_TOKEN=$(cat .token)
export OPENAI_API_KEY=your_api_key
export OPENAI_API_ENDPOINT="https://llama-cpp.reeselink.com"
export IMAGE_GEN_ENDPOINT="http://toybox.reeselink.com:1234/v1"
export IMAGE_EDIT_ENDPOINT="http://toybox.reeselink.com:1235/v1"
# Sync dependencies
uv sync
# Run with uv
uv run main.py
# Run the bot
uv run python -m vibe_bot.main
```
### Container
```bash
# Build
# Build the container image
podman build -t vibe-bot:latest .
# Run
# Run with environment file
podman run --env-file .env localhost/vibe-bot:latest
```
## Docs
## Testing
### Open AI
Run the full test suite:
Chat
```bash
uv run pytest vibe_bot/tests/ -v
```
<https://developers.openai.com/api/reference/resources/chat/subresources/completions/methods/create>
Run linters:
Images
```bash
# Ruff (linter + formatter)
uv run ruff check vibe_bot/
<https://developers.openai.com/api/reference/python/resources/images/methods/edit>
# Mypy (type checking)
uv run mypy vibe_bot/
## Models
# Pyright (type checking)
uv run pyright vibe_bot/
### Qwen3.5
# Black (formatter check)
uv run black --check vibe_bot/
```
> We recommend using the following set of sampling parameters for generation
## Configuration
- Non-thinking mode for text tasks: temperature=1.0, top_p=1.00, top_k=20, min_p=0.0, presence_penalty=2.0, repetition_penalty=1.0
- Non-thinking mode for VL tasks: temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
- Thinking mode for text tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0
- Thinking mode for VL or precise coding (e.g. WebDev) tasks : temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
> Please note that the support for sampling parameters varies according to inference frameworks.
| Variable | Default | Description |
| ----------------------- | ------------------ | ------------------------------------- |
| `DISCORD_TOKEN` | *(required)* | Discord bot authentication token |
| `CHAT_ENDPOINT` | *(required)* | OpenAI-compatible chat API URL |
| `CHAT_MODEL` | *(required)* | Model name for chat completions |
| `IMAGE_GEN_ENDPOINT` | *(required)* | Image generation API URL |
| `IMAGE_EDIT_ENDPOINT` | *(required)* | Image editing API URL |
| `EMBEDDING_ENDPOINT` | *(required)* | Embedding API URL |
| `EMBEDDING_MODEL` | *(required)* | Model name for text embeddings |
| `MAX_COMPLETION_TOKENS` | `1000` | Max tokens in LLM responses |
| `MAX_HISTORY_MESSAGES` | `1000` | Max messages kept in the database |
| `SIMILARITY_THRESHOLD` | `0.7` | Min cosine similarity for RAG context |
| `TOP_K_RESULTS` | `5` | Number of similar messages retrieved |
| `TTS_MODEL_PATH` | `kokoro-v1.0.onnx` | Path to Kokoro ONNX model file |
| `TTS_VOICES_PATH` | `voices-v1.0.bin` | Path to Kokoro voices binary file |
| `TTS_VOICE` | `af_sarah` | Default voice for TTS |
| `TTS_SPEED` | `1.0` | Speech speed multiplier |
| `DB_PATH` | `chat_history.db` | SQLite database file path |