father-bot/chatgpt_telegram_bot
Chatgpt Telegram Bot
This project is a Telegram bot that integrates large language models, such as OpenAI and Claude, to provide an AI chat interface within the messaging app. It functions as a multi-model AI gateway that routes prompts to various providers via API keys and YAML configurations.
The implementation includes a provider-agnostic routing system and response streaming to deliver text word-by-word. It distinguishes itself with a token-based cost tracker that calculates the monetary expenditure of API requests and a whitelist-based access control system to restrict usage to authorized users.
The bot supports multimodal workflows, including text-to-image generation, vision model analysis for uploaded images, and voice message transcription. It maintains conversation context across sessions through persistent state mapping in a database and allows for AI persona management to customize behavior and expertise.
The application is provided as a containerized deployment for consistent execution across different environments.
Features
- AI Chat Integrations - Connects a Telegram messaging interface to multiple large language model providers for conversational AI interactions.
- LLM Conversational Bots - Provides a Telegram messaging interface that connects users to OpenAI and Claude models.
- AI Assistants - Implements a self-hosted AI assistant capable of text, image, and voice interactions.
- Conversation State Persistence - Saves and restores conversation context and message history to maintain continuity across sessions.
- Multimodal AI Orchestrators - Coordinates vision, speech, and language models to process multimodal inputs within a unified chat workflow.
- Provider-Agnostic Model Interfaces - Abstracts multiple LLM provider interfaces into a standardized internal format for seamless model routing.
- AI Bot Integrations - Integrates OpenAI and Claude models with a Telegram bot to provide an AI chat interface.
- AI Conversation Contexts - Stores chat history and session data in a database to maintain context across asynchronous messages.
- AI Provider Gateways - Functions as a gateway that routes prompts to various AI providers using API keys and configurations.
- Streaming Chat Responses - Implements incremental text delivery for AI responses to enable a real-time chat experience.
- AI Image Generation - Integrates AI models to generate visual art from text prompts within the chat interface.
- AI Model Configurations - Provides interfaces to update active AI models, API keys, and system behavioral parameters.
- Persona Configurations - Allows customization of AI behavior and expertise through predefined or user-configured chat personas.
- Speech to Text Transcription - Converts recorded voice messages into text using AI speech-to-text models.
- Vision Analysis - Processes uploaded images using vision models to describe or interpret visual content.
- LLM Token Cost Tracking - Tracks and aggregates token usage to monitor and manage the monetary expenditure of LLM APIs.
- AI Response Streams - Delivers AI-generated text fragments to the client in real-time as they are produced by the API.
- Voice and Vision Processing - Processes image inputs via vision models and transcribes voice messages into text.
- Bot Access Controls - Restricts AI bot activity to authorized users through a whitelist-based access control system.
- Username Whitelists - Restricts bot access to a predefined list of authorized Telegram usernames.
- API Expenditure Trackers - Tracks and displays the total financial cost of tokens consumed across various AI providers.
- Token Cost Calculators - Computes the monetary cost of API requests by tracking input and output tokens.
Star history
How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
