An AI-powered search engine with a generative UI
TypeScript generative-aigenerative-uinextjsollamareactsearxngshadcn-uitailwindcsstavilytypescriptupstashvercel-ai-sdk
feat: update documentation for v1.0 release
Yoshiki Miura8a205e28a6cc
diff --git a/README.md b/README.mdindex 23068849..0e3fee43 100644--- a/README.md+++ b/README.md@@ -1,8 +1,22 @@+<div align="center">+# MorphicAn AI-powered search engine with a generative UI.-+[](https://deepwiki.com/miurla/morphic) [](https://github.com/miurla/morphic/stargazers) [](https://github.com/miurla/morphic/network/members)++<a href="https://vercel.com/oss">+ <img alt="Vercel OSS Program" src="https://vercel.com/oss/program-badge.svg" />+</a>++<br />++<a href="https://trendshift.io/repositories/9207" target="_blank"><img src="https://trendshift.io/api/badge/repositories/9207" alt="miurla%2Fmorphic | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>++<img src="./public/screenshot-2025-05-04.png" />++</div>## ποΈ Overview@@ -23,61 +37,53 @@ An AI-powered search engine with a generative UI.- AI-powered search with GenerativeUI- Natural language question understanding-- Multiple search providers support (Tavily, SearXNG, Exa)-- Model selection from UI (switch between available AI models)- - Reasoning models with visible thought process+- Multiple search providers support (Tavily, Brave, SearXNG, Exa)+- Search modes: Quick, Planning, and Adaptive+- Model type selection: Speed vs Quality+- Inspector panel for tool execution and AI processing details### Authentication- User authentication powered by [Supabase Auth](https://supabase.com/docs/guides/auth)-- Supports Email/Password sign-up and sign-in-- Supports Social Login with Google### Chat & History-- Chat history stored in PostgreSQL database-- Share search results (Optional)+- Chat history automatically stored in PostgreSQL database+- Share search results with unique URLs+- Message feedback system+- File upload support### AI Providers-The following AI providers are supported:-- OpenAI (Default)-- Google Generative AI-- Azure OpenAI-- Anthropic-- Ollama-- Groq-- DeepSeek-- Fireworks-- xAI (Grok)-- OpenAI Compatible--Models are configured in `public/config/models.json`. Each model requires its corresponding API key to be set in the environment variables. See [Configuration Guide](docs/CONFIGURATION.md) for details.+- Anthropic Claude+- Google Gemini+- Vercel AI Gateway++Models are configured in `config/models/*.json` with profile-based settings. When using non-OpenAI providers, update the model configuration files with compatible model IDs. See [Configuration Guide](docs/CONFIGURATION.md) for details.### Search Capabilities- URL-specific search-- Video search support (Optional)-- SearXNG integration with:- - Customizable search depth (basic/advanced)- - Configurable engines- - Adjustable results limit- - Safe search options- - Custom time range filtering+- Content extraction with Tavily or Jina+- Citation tracking and display+- Self-hosted search with SearXNG support### Additional Features- Docker deployment ready- Browser search engine integration+- LLM observability with Langfuse (optional)+- Todo tracking for complex tasks+- Changelog system for updates## π§± Stack### Core Framework-- [Next.js](https://nextjs.org/) - App Router, React Server Components-- [TypeScript](https://www.typescriptlang.org/) - Type safety-- [Vercel AI SDK](https://sdk.vercel.ai/docs) - Text streaming / Generative UI+- [Next.js](https://nextjs.org/) - React framework with App Router+- [TypeScript](https://www.typescriptlang.org/) - Type-safe development+- [Vercel AI SDK](https://sdk.vercel.ai/docs) - TypeScript toolkit for building AI-powered applications### Authentication & Authorization (Updated Category)@@ -85,15 +91,18 @@ Models are configured in `public/config/models.json`. Each model requires its co### AI & Search-- [OpenAI](https://openai.com/) - Default AI provider (Optional: Google AI, Anthropic, Groq, Ollama, Azure OpenAI, DeepSeek, Fireworks)-- [Tavily AI](https://tavily.com/) - Default search provider-- Alternative providers:+- [OpenAI](https://openai.com/) - Default AI provider (Optional: Google AI, Anthropic)+- [Tavily AI](https://tavily.com/) - AI-optimized search with context+- [Brave Search](https://brave.com/search/api/) - Traditional web search results+- Tavily alternatives:- [SearXNG](https://docs.searxng.org/) - Self-hosted search- - [Exa](https://exa.ai/) - Neural search+ - [Exa](https://exa.ai/) - Meaning-based search powered by embeddings### Data Storage-- [Neon](https://neon.tech/) - Serverless PostgreSQL database+- [PostgreSQL](https://www.postgresql.org/) - Primary database (supports Neon, Supabase, or standard PostgreSQL)+- [Drizzle ORM](https://orm.drizzle.team/) - Type-safe database ORM+- [Cloudflare R2](https://developers.cloudflare.com/r2/) - File storage (optional)### UI & Styling@@ -128,14 +137,13 @@ cp .env.local.example .env.localFill in the required environment variables in `.env.local`:```bash-# Required for Core Functionality-OPENAI_API_KEY= # Get from https://platform.openai.com/api-keys-TAVILY_API_KEY= # Get from https://app.tavily.com/home-DATABASE_URL= # PostgreSQL connection string (Neon recommended)--# Required for Authentication (Beta)-NEXT_PUBLIC_SUPABASE_URL= # Your Supabase project URL-NEXT_PUBLIC_SUPABASE_ANON_KEY= # Your Supabase anonymous key+# Required Configuration+DATABASE_URL= # PostgreSQL connection string+OPENAI_API_KEY= # Get from https://platform.openai.com/api-keys+TAVILY_API_KEY= # Get from https://app.tavily.com/home+BRAVE_SEARCH_API_KEY= # Get from https://brave.com/search/api/+NEXT_PUBLIC_SUPABASE_URL= # Your Supabase project URL+NEXT_PUBLIC_SUPABASE_ANON_KEY= # Your Supabase anonymous key```For optional features configuration (SearXNG, alternative AI providers, etc.), see [CONFIGURATION.md](./docs/CONFIGURATION.md)@@ -166,61 +174,11 @@ Visit http://localhost:3000 in your browser.## π Deploy-Host your own live version of Morphic with Vercel, Cloudflare Pages, or Docker.+Host your own live version of Morphic with Vercel or Docker.### Vercel-[](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fmiurla%2Fmorphic&env=OPENAI_API_KEY,TAVILY_API_KEY,UPSTASH_REDIS_REST_URL,UPSTASH_REDIS_REST_TOKEN)--### Docker Prebuilt Image--Prebuilt Docker images are available on GitHub Container Registry:--```bash-docker pull ghcr.io/miurla/morphic:latest-```--You can use it with docker-compose:--```yaml-services:- morphic:- image: ghcr.io/miurla/morphic:latest- env_file: .env.local- ports:- - '3000:3000'- volumes:- - ./models.json:/app/public/config/models.json # Optional: Override default model configuration-```--The default model configuration is located at `public/config/models.json`. For Docker deployment, you can create `models.json` alongside `.env.local` to override the default configuration.--## π Search Engine--### Setting up the Search Engine in Your Browser--If you want to use Morphic as a search engine in your browser, follow these steps:--1. Open your browser settings.-2. Navigate to the search engine settings section.-3. Select "Manage search engines and site search".-4. Under "Site search", click on "Add".-5. Fill in the fields as follows:- - **Search engine**: Morphic- - **Shortcut**: morphic- - **URL with %s in place of query**: `https://morphic.sh/search?q=%s`-6. Click "Add" to save the new search engine.-7. Find "Morphic" in the list of site search, click on the three dots next to it, and select "Make default".--This will allow you to use Morphic as your default search engine in the browser.--## π Sponsors--This project is proudly supported by:--<a href="https://vercel.com/oss">- <img alt="Vercel OSS Program" src="https://vercel.com/oss/program-badge.svg" />-</a>+[](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2Fmiurla%2Fmorphic&env=DATABASE_URL,OPENAI_API_KEY,TAVILY_API_KEY,BRAVE_SEARCH_API_KEY,NEXT_PUBLIC_SUPABASE_URL,NEXT_PUBLIC_SUPABASE_ANON_KEY)## π₯ Contributingdiff --git a/docs/CONFIGURATION.md b/docs/CONFIGURATION.mdindex 9e070277..9c87e681 100644--- a/docs/CONFIGURATION.md+++ b/docs/CONFIGURATION.md@@ -4,40 +4,10 @@ This guide covers the optional features and their configuration in Morphic.## Table of Contents-- [Chat History Storage](#chat-history-storage)- [Search Providers](#search-providers)- [Additional AI Providers](#additional-ai-providers)- [Other Features](#other-features)-## Chat History Storage--### Using Upstash Redis (Recommended for production)--Follow the detailed setup guide at [Building your own RAG chatbot with Upstash](https://upstash.com/blog/rag-chatbot-upstash#setting-up-upstash-redis)--1. Create a database at [Upstash Console](https://console.upstash.com/redis)-2. Navigate to the Details tab and find the "Connect your database" section-3. Copy the REST API credentials from the .env section-4. Configure your `.env.local`:--```bash-NEXT_PUBLIC_ENABLE_SAVE_CHAT_HISTORY=true-USE_LOCAL_REDIS=false-UPSTASH_REDIS_REST_URL=[YOUR_UPSTASH_REDIS_REST_URL]-UPSTASH_REDIS_REST_TOKEN=[YOUR_UPSTASH_REDIS_REST_TOKEN]-```--### Using Local Redis--1. Ensure Redis is installed and running locally-2. Configure your `.env.local`:--```bash-NEXT_PUBLIC_ENABLE_SAVE_CHAT_HISTORY=true-USE_LOCAL_REDIS=true-LOCAL_REDIS_URL=redis://localhost:6379-```-## Search Providers### SearXNG Configuration@@ -121,102 +91,97 @@ docker-compose logs searxng## Additional AI Providers-Models are configured in `public/config/models.json`. Each model requires its corresponding API key to be set in the environment variables.+Models are configured in `config/models/*.json` files. Each provider requires its corresponding API key to be set in the environment variables.### Model Configuration-The `models.json` file contains an array of model configurations with the following structure:+Model configuration files use the following structure:```json{- "models": [- {+ "version": 1,+ "models": {+ "types": {+ "speed": {+ "id": "model-id",+ "name": "Model Name",+ "provider": "Provider Name",+ "providerId": "provider-id",+ "providerOptions": {}+ },+ "quality": {+ "id": "model-id",+ "name": "Model Name",+ "provider": "Provider Name",+ "providerId": "provider-id",+ "providerOptions": {}+ }+ },+ "relatedQuestions": {"id": "model-id","name": "Model Name","provider": "Provider Name",- "providerId": "provider-id",- "enabled": true,- "toolCallType": "native|manual",- "toolCallModel": "tool-call-model-id" // optional, only needed if toolCallType is "manual" and you need to specify a different model for tool calls+ "providerId": "provider-id"}- ]+ }}```-### Provider API Keys--### Google Generative AI--```bash-GOOGLE_GENERATIVE_AI_API_KEY=[YOUR_API_KEY]-```--### Anthropic+### Supported Providers-```bash-ANTHROPIC_API_KEY=[YOUR_API_KEY]-```--### Groq+#### OpenAI (Default)```bash-GROQ_API_KEY=[YOUR_API_KEY]+OPENAI_API_KEY=[YOUR_API_KEY]```-### Ollama+#### Google Generative AI```bash-OLLAMA_BASE_URL=http://localhost:11434+GOOGLE_GENERATIVE_AI_API_KEY=[YOUR_API_KEY]```-### Azure OpenAI+#### Anthropic```bash-AZURE_API_KEY=[YOUR_API_KEY]-AZURE_RESOURCE_NAME=[YOUR_RESOURCE_NAME]+ANTHROPIC_API_KEY=[YOUR_API_KEY]```-### DeepSeek--```bash-DEEPSEEK_API_KEY=[YOUR_API_KEY]-```+#### Vercel AI Gateway-### Fireworks+[Vercel AI Gateway](https://vercel.com/docs/ai-gateway) allows you to use multiple AI providers through a single endpoint with automatic failover and load balancing.```bash-FIREWORKS_API_KEY=[YOUR_API_KEY]+AI_GATEWAY_API_KEY=[YOUR_AI_GATEWAY_API_KEY]```-### xAI+## Other Features-```bash-XAI_API_KEY=[YOUR_XAI_API_KEY]-```+### LLM Observability-### OpenAI Compatible Model+Enable tracing and monitoring with Langfuse:```bash-OPENAI_COMPATIBLE_API_KEY=[YOUR_API_KEY]-OPENAI_COMPATIBLE_API_BASE_URL=[YOUR_API_BASE_URL]+LANGFUSE_SECRET_KEY=[YOUR_SECRET_KEY]+LANGFUSE_PUBLIC_KEY=[YOUR_PUBLIC_KEY]+LANGFUSE_HOST=https://cloud.langfuse.com```-## Other Features+### File Upload-### Share Feature+Enable file upload with Cloudflare R2:```bash-NEXT_PUBLIC_ENABLE_SHARE=true-```--### Video Search--```bash-SERPER_API_KEY=[YOUR_API_KEY]+CLOUDFLARE_R2_ACCESS_KEY_ID=[YOUR_ACCESS_KEY]+CLOUDFLARE_R2_SECRET_ACCESS_KEY=[YOUR_SECRET_KEY]+CLOUDFLARE_R2_ACCOUNT_ID=[YOUR_ACCOUNT_ID]+CLOUDFLARE_R2_BUCKET_NAME=[YOUR_BUCKET_NAME]```### Alternative Fetch Tool+Use Jina for enhanced content extraction:+```bashJINA_API_KEY=[YOUR_API_KEY]```