https://github.com/edwards359/telegram-bot-assistant_ed
Telegram‑бот‑ассистент: быстрые сценарии общения с LLM (OpenAI/GigaChat).
https://github.com/edwards359/telegram-bot-assistant_ed
Last synced: 3 months ago
JSON representation
Telegram‑бот‑ассистент: быстрые сценарии общения с LLM (OpenAI/GigaChat).
- Host: GitHub
- URL: https://github.com/edwards359/telegram-bot-assistant_ed
- Owner: Edwards359
- Created: 2025-10-26T18:10:55.000Z (8 months ago)
- Default Branch: master
- Last Pushed: 2026-03-16T18:31:56.000Z (4 months ago)
- Last Synced: 2026-03-17T05:30:57.544Z (4 months ago)
- Language: Python
- Size: 3.46 MB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Roadmap: docs/roadmap.md
Awesome Lists containing this project
README
## 🇷🇺 Обзор (Telegram Bot Assistant)
**Telegram Bot Assistant** — AI‑ассистент в Telegram с поддержкой нескольких LLM‑провайдеров.
- **Задача:** дать пользователям простой интерфейс “написал сообщение → получил умный ответ/действие”.
- **Решение:** бот принимает сообщения, маршрутизирует их в выбранный LLM‑бэкенд и возвращает ответ, который можно адаптировать под сценарий.
- **Пример использования:** ассистент поддержки, внутренний помощник для команды или интерфейс к RAG‑системе.
---
# Telegram Bot Assistant — LLM Powered AI Assistant
Production-ready Telegram AI assistant with support for multiple LLM providers (OpenAI, LangChain, GigaChat).
Designed for experimentation, prompt engineering, and scalable AI chatbot development.
---
## Overview
Telegram Bot Assistant provides a unified interface for interacting with Large Language Models through Telegram.
The project supports multiple LLM backends and provides a modular architecture for:
* AI assistant development
* prompt engineering experiments
* model comparison
* LLM integration research
* conversational AI systems
---
## Key Features
* Telegram-based AI assistant
* multiple LLM providers support
* modular architecture
* extensible prompt system
* backend abstraction layer
* research-friendly design
* production deployment ready structure
---
## Architecture
```
User → Telegram API → Bot Handler → LLM Interface → Provider → Response
```
System components:
* Telegram bot interface
* LLM provider abstraction
* prompt management
* response processing
* configuration management
More details → `/docs/architecture.md`
---
## Supported Providers
* OpenAI
* LangChain integrations
* GigaChat
---
## Quick Start
### Install dependencies
```
pip install -r requirements.txt
```
### Configure environment
Create `.env`:
```
TELEGRAM_TOKEN=
OPENAI_API_KEY=
GIGACHAT_API_KEY=
```
### Run
```
python main_open_ai.py
```
---
## Documentation
Full documentation available in `/docs`:
* architecture → system design
* setup → installation guide
* prompt-design → prompt engineering
* deployment → production deployment
* evaluation → metrics and testing
* roadmap → future development
---
## Project Structure
```
docs/ → documentation
src/ → source code
tests/ → tests
scripts/ → automation
data/ → storage
```
---
## Evaluation & Metrics
* response latency
* model quality
* hallucination rate
* user engagement
* API reliability
See `/docs/evaluation.md`.
---
## Development
```
git clone repo
pip install -r requirements.txt
```
See `/docs/setup.md`.
---
## Contributing
See `CONTRIBUTING.md`.
---
## License
MIT