https://github.com/yokingma/search_with_ai
Open AI Search, Support DeepResearch, DeepSeek R1, Ollama/LMStudio, SearXNG, Docker. AI搜索引擎，支持DeepResearch, 本地模型、深度思考模型（DeepSeek R1）、聚合搜索引擎SearXNG，支持Docker一键部署。
https://github.com/yokingma/search_with_ai
deep-research deepresearch deepseek-r1 firecrawl perplexity rag search searxng tavily
Last synced: 21 days ago
JSON representation
Open AI Search, Support DeepResearch, DeepSeek R1, Ollama/LMStudio, SearXNG, Docker. AI搜索引擎，支持DeepResearch, 本地模型、深度思考模型（DeepSeek R1）、聚合搜索引擎SearXNG，支持Docker一键部署。
- Host: GitHub
- URL: https://github.com/yokingma/search_with_ai
- Owner: yokingma
- License: mit
- Created: 2024-03-08T12:15:29.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-27T13:45:25.000Z (7 months ago)
- Last Synced: 2025-05-15T09:02:23.860Z (5 months ago)
- Topics: deep-research, deepresearch, deepseek-r1, firecrawl, perplexity, rag, search, searxng, tavily
- Language: TypeScript
- Homepage: https://isou.chat
- Size: 10 MB
- Stars: 924
- Watchers: 15
- Forks: 173
- Open Issues: 12
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- StarryDivineSky - yokingma/search_with_ai
- awesome-ChatGPT-repositories - search_with_ai - 🤖 Free Search with AI, 💡 Open-Source Perplexity, 📍 Support Ollama/SearXNG, Support Docker deployment. 让AI大模型和搜索引擎回答你的问题，支持本地大模型(Ollama)、聚合搜索引擎SearXNG，支持Docker一键部署。 (Langchain)
README
# Open AI Search (Support Deep Research)
Build your conversation-based search with LLM, support DeepResearch / DeepSeek R1.
**English** | [中文](./README_ZH_CN.md) | [日本語](./README_JP.md)
Repositories: [GitHub](https://github.com/yokingma/search_with_ai) [CNB](https://cnb.cool/isou/AiSearch)
## 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](https://github.com/lmstudio-ai/lms)
* Built-in support for search engine: Bing, Google, [Tavily](https://tavily.com/), [SearXNG](https://github.com/searxng/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 [dzhng/deep-research](https://github.com/dzhng/deep-research).
https://github.com/user-attachments/assets/da5e038d-5e0a-4a6f-bae2-b1a58eee193e
**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.
> [!NOTE]
> If you want to integrate DeepResearch capabilities into your own (Node.js) project, we recommend using the following npm package, built on LangGraph, with detailed usage instructions: [DeepResearch](https://github.com/yokingma/deepresearch)
```shell
npm install deepsearcher
```
## Deploy with Docker (recommended)
[Install Docker](https://docs.docker.com/install/).
```shell
docker pull docker.cnb.cool/aigc/aisearch
```
1.**Get the code.**
```shell
git clone https://github.com/yokingma/search_with_ai.git
cd search_with_ai
```
2.**Edit** [.env.docker](https://github.com/yokingma/search_with_ai/blob/main/.env) **file.** in ```deploy``` directory.
> After modifying the .env.docker file, restart the Docker container to apply changes.
You must set at least one KEY.
```shell
...
# OpenAI's key
OPENAI_KEY=#your key
# Searxng hostname.
SEARXNG_HOSTNAME=http://searxng:8080
```
3.**Edit** [model.json](https://github.com/yokingma/search_with_ai/blob/main/deploy/model.json) **file.** [Optional]
```json
{
"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.**
```shell
docker compose up -d
```
Then visit
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](https://github.com/searxng/searxng) with [searxng-docker](https://github.com/searxng/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:
```yaml
search:
formats:
- html
- json
```
And set limiter to false:
```yaml
server:
limiter: false # default is true
```
`apps/server/.env`:
```shell
# SEARXNG_HOSTNAME=
```
#### Bing Search
To use the Bing Web Search API, please visit [this link](https://www.microsoft.com/en-us/bing/apis/bing-web-search-api) 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](https://www.searchapi.io/), [Serper](https://www.serper.dev/) Google Search API from Serper, or opt for the [Programmable Search Engine](https://developers.google.com/custom-search) provided by Google.
#### Tavily Search
[Tavily](https://tavily.com/) is a search engine optimized for LLMs.
#### Jina Reader URL API
[Jina](https://jina.ai/) Reader URL API, supporting full web content extraction. used in [DeepResearch] mode.
JINA KEY is optional (limited to 20RPM).
```shell
# JINA API KEY
JINA_KEY=#your key
```
## Deploy & Development
* Node.js >= 20
* Turborepo
* PackageManager: yarn@3.5.1
* **Directory Structure**
```text
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:
```shell
turbo dev
# or
turbo build
```
* **Update**
In the root of the project:
```shell
git pull
```
## CDN acceleration and security protection for this project are sponsored by Tencent EdgeOne
EdgeOne offers a long-term free plan with unlimited traffic and requests, covering Mainland China nodes, with no overage charges. Interested friends can click the link below to claim it
Best Asian CDN, Edge, and Secure Solutions - Tencent EdgeOne
## License
This repository's source code is available under the [MIT License](LICENSE).
[🚀Back to top](#top)