Open AI Search (Support Deep Research)

Build your conversation-based search with LLM, support DeepResearch / DeepSeek R1.

Live Demo

English | 中文 | 日本語

Repositories: GitHub CNB

Features

• 🔍 New! Support "Deep Research" like OpenAI/Gemini/Perplexity.
• Built-in support for LLM: OpenAI, Google, Lepton, DeepSeek(R1), SiliconFlow, AliYun, Baidu, ChatGLM, Moonshot, Tencent, Lepton, Yi and more.
• Support Ollama, LMStudio
• Built-in support for search engine: Bing, Google, Tavily, SearXNG
• Customizable pretty UI interface
• Support light&dark mode/mobile
• Support i18n
• Support Continue Q&A with contexts.
• Support Cache results, Force reload.
• Support images search.

About DeepResearch

Support "Deep Research" like OpenAI/Gemini/Perplexity, through search engine, web scraping and LLM to iterate on any topic or question, and generate a comprehensive report. Project reference deep-research, thanks to author dzhng.

deepresearch.mp4

Note:

• Warning: It will cost a lot of Tokens.
• Need to support Function Calling.
• Use JINA.ai to extract web page content (No need to configure KEY, limited: 20RPM).

Workflow:

1. Analyze user's query.
2. Generate follow-up questions to refine the research direction.
3. Generate and execute search queries.
4. Process and analyze search results.
5. Recursive exploration leads to deeper exploration base on step 4.
6. Generate a comprehensive report.

More details can be found in DeepResearch discussion.

Deploy with Docker (recommended)

Install Docker.

docker pull docker.cnb.cool/aigc/aisearch

1.Get the code.

git clone https://github.com/yokingma/search_with_ai.git
cd search_with_ai

2.Edit .env.docker file. in deploy directory.

After modifying the .env.docker file, restart the Docker container to apply changes.

You must set at least one KEY.

...
# OpenAI's key
OPENAI_KEY=#your key

# Searxng hostname.
SEARXNG_HOSTNAME=http://searxng:8080

3.Edit model.json file. [Optional]

{
  "provider": "openai",
  "type": "openai",
  "baseURL": "https://api.openai.com/v1",
  "models": ["o1-preview", "o1-mini", "gpt-4o", "gpt-4o-mini"]
}

4.Run with Docker Compose.

docker compose up -d

Then visit http://localhost:3000

5.Update

• Delete old images.
• Run docker compose down
• Run docker compose up -d

Search Engine

Built-in support for search engine: SearXNG, Bing, Google, Tavily, etc.

SearXNG (Free, No Key required)

Install SearXNG with searxng-docker

Make sure to activate the json format to use the API. This can be done by adding the following line to the settings.yml file:

search:
    formats:
        - html
        - json

And set limiter to false:

server:
   limiter: false # default is true

apps/server/.env:

# SEARXNG_HOSTNAME=<host>

Bing Search

To use the Bing Web Search API, please visit this link to obtain your Bing subscription key.

Google Search

You have three options for Google Search: you can use the SearchApi Google Search API from SearchApi, Serper Google Search API from Serper, or opt for the Programmable Search Engine provided by Google.

Tavily Search

Tavily is a search engine optimized for LLMs.

Jina Reader URL API

Jina Reader URL API, supporting full web content extraction. used in [DeepResearch] mode. JINA KEY is optional (limited to 20RPM).

# JINA API KEY
JINA_KEY=#your key

Deploy & Development

• Node.js >= 20

• Turborepo

• PackageManager: [email protected]

• Directory Structure

apps/
  | server # backend
  | web # frontend
deploy/
  | docker-compose.yaml # docker deployment file
  | .env.docker # backend configuration file
  | model.json # backend model configuration file
  ...

• Development & Build In the root of the project:

turbo dev
# or
turbo build

• Update In the root of the project:

git pull

License

This repository's source code is available under the MIT License.

🚀Back to top