telegram-search

 --- <p align="center"> <a href="https://trendshift.io/repositories/13868" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13868" alt="groupultra%2Ftelegram-search | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> </p> <p align="center"> [<a href="https://search.lingogram.app">立即体验</a>] [<a href="./docs/README_EN.md">English</a>] [<a href="./docs/README_JA.md">日本語</a>] </p> <p align="center"> <a href="https://discord.gg/NzYsmJSgCT"> <img alt="Discord" src="https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fdiscord.com%2Fapi%2Finvites%2FNzYsmJSgCT%3Fwith_counts%3Dtrue&query=%24.approximate_member_count&suffix=%20members&logo=discord&logoColor=white&label=%20&color=7389D8&labelColor=6A7EC2" /> </a> <a href="https://t.me/+Gs3SH2qAPeFhYmU9"> <img alt="Telegram" src="https://img.shields.io/badge/Telegram-%235AA9E6?logo=telegram&labelColor=FFFFFF" /> </a> <a href="https://deepwiki.com/groupultra/telegram-search"> <img alt="DeepWiki" src="https://deepwiki.com/badge.svg" /> </a> <br> <a href="https://github.com/groupultra/telegram-search/releases"> <img alt="GitHub Package Version" src="https://img.shields.io/github/package-json/v/groupultra/telegram-search?style=flat&colorA=080f12&colorB=1fa669" /> </a> <a href="https://github.com/groupultra/telegram-search/actions/workflows/release-docker.yaml"> <img alt="Release Docker / OCI" src="https://github.com/groupultra/telegram-search/actions/workflows/release-docker.yaml/badge.svg" /> </a> <a href="https://github.com/groupultra/telegram-search/actions/workflows/ci.yaml"> <img alt="CI" src="https://github.com/groupultra/telegram-search/actions/workflows/ci.yaml/badge.svg" /> </a> </p> > [!TIP] > > > > > > > ## 💖 Sponsors  ## ✅ Key Features ### 📦 Export & Backup - [x] Supports exporting chat history to various databases: compatible with PGlite and PostgreSQL - [x] Media resources can be automatically backed up to MinIO object storage without manual intervention - [x] Message export automatically completes vector embedding and word segmentation processing, helping with subsequent accurate retrieval - [x] Real-time synchronization, automatically pulls and updates the latest conversation content ### 🔍 Chat History Search - [x] Automatic intelligent word segmentation, supports accurate multi-language retrieval - [x] Combines fuzzy matching and vector semantic search for higher search efficiency - [x] RAG Intelligent Q&A: Chat directly with AI and get real-time answers based on historical context ### 🚀 Advanced Features - [x] Unread Message Intelligent Summary: One-click summary of all unread messages, automatically generates concise summaries, making key content clear at a glance ## 🛣️ Roadmap ### 🧠 AI Capability Enhancement - [ ] Automatically generate session summaries - [ ] "Super Brain": Automatically build knowledge graphs of people and events based on historical messages ### 🔗 Media & Link Expansion - [ ] Intelligently organize the "Saved Messages" favorites to improve content management efficiency - [ ] Deep indexing of links and images: web page summaries, image OCR text recognition and intelligent descriptions to help with search and archiving ### 🌐 Multi-Platform Integration - [ ] Add Telegram Bot support to meet diverse message management needs - [ ] Cross-platform expansion: support Discord and other mainstream social/communication platforms to achieve unified retrieval and backup ## 🎉 Get Started Now We provide an online demo version, so you can experience all the features of Telegram Search without deploying it yourself. Visit the following URL to get started: https://search.lingogram.app > [!WARNING] > > > ## 🚀 Quick Start ### Using Docker Compose 1. Create a new empty directory to store Telegram Search's configuration and data: ```bash mkdir telegram-search cd telegram-search ``` 2. Download the Docker Compose file and start all services (including database, MinIO, etc.): ```bash curl -L https://raw.githubusercontent.com/groupultra/telegram-search/refs/heads/main/docker/docker-compose.yml -o docker-compose.yml curl -L https://raw.githubusercontent.com/groupultra/telegram-search/refs/heads/main/docker/.env.example -o .env curl -L https://raw.githubusercontent.com/groupultra/telegram-search/refs/heads/main/docker/init.sql -o init.sql docker compose -f docker-compose.yml up -d ``` 3. Then open **http://localhost:3333** to use 🎉 ### Using Docker Image If MinIO related parameters are not configured, media files will be saved to the local `data/media` directory by default. ```bash docker run -d --name telegram-search -p 3333:3333 ghcr.io/groupultra/telegram-search:latest ``` ### Custom Environment Variables > [!IMPORTANT] > AI Embedding & LLM settings are now configured **per account** within the application (Settings → API). > > After modifying the `.env` file, execute `docker compose -f docker-compose.yml up -d` again to start the service. The following environment variables are all optional, and if not filled in, the default values will be used. | Environment Variable | Description | Example Value | | ------------------- | ---------------------------------------------------------------------------- | ----------------------------------------------------- | | `TELEGRAM_API_ID` | Telegram Application ID obtained from [my.telegram.org](https://my.telegram.org/apps) | `611335` | | `TELEGRAM_API_HASH` | Telegram Application Hash obtained from [my.telegram.org](https://my.telegram.org/apps) | `d524b414d21f4d37f08684c1df41ac9c` | | `DATABASE_TYPE` | Database type, optional `postgres` or `pglite` | `pglite` | | `DATABASE_URL` | PostgreSQL connection string (only fill in when `DATABASE_TYPE=postgres`) | `postgresql://postgres:123456@pgvector:5432/postgres` | | `PROXY_URL` | Proxy address (supports formats such as `socks5://user:pass@host:port`) | `socks5://user:pass@host:port` | | `PORT` | Backend service HTTP/WebSocket listening port | `3333` | | `HOST` | Backend service listening address | `0.0.0.0` | | `BACKEND_URL` | Upstream backend address for `/api` and `/ws` when Nginx is used as a reverse proxy | `http://127.0.0.1:3333` | | `MINIO_URL` | MinIO service address | `http://minio:9000` | | `MINIO_ACCESS_KEY` | MinIO access key | `minioadmin` | | `MINIO_SECRET_KEY` | Secret key corresponding to the MinIO access key | `minioadmin` | | `MINIO_BUCKET` | MinIO bucket name | `telegram-media` | #### Using Docker Image Environment Variables Please modify the environment variables according to your needs. ```bash docker run -d --name telegram-search \ -p 3333:3333 \ -e DATABASE_TYPE=postgres \ -e DATABASE_URL=postgresql://postgres:123456@localhost:5432/postgres \ ghcr.io/groupultra/telegram-search:latest ``` ## 💻 Development Guide ### Pure Browser Mode ```bash git clone https://github.com/groupultra/telegram-search.git cd telegram-search pnpm install cp .env.example .env pnpm run dev ``` ### Server Mode ```bash git clone https://github.com/groupultra/telegram-search.git cd telegram-search pnpm install cp .env.example .env docker compose -f docker/docker-compose.dev.yml up -d pgvector minio pnpm run server:dev pnpm run web:dev ``` 📖 **More development details and architectural details:** [CONTRIBUTING.md](./docs/CONTRIBUTING.md) ## 🚀 Activity  [](https://star-history.com/#groupultra/telegram-search&Date)