本地容器化部署r.jina.ai

背景

需要通过r.jina.ai解析网页或pdf文件送到下游的LLM进行分析处理，近期r.jina.ai的响应越来越慢，经常出现404错误，计划本地进行处理

部署

https://github.com/intergalacticalvariable/reader

docker pull ghcr.io/intergalacticalvariable/reader:latest

docker run -d -p 3000:3000 -v /path/to/local-storage:/app/local-storage --name reader-container ghcr.io/intergalacticalvariable/reader:latest

docker-compose.yml

version: '3'
services:
  reader-service:
    image: ghcr.io/intergalacticalvariable/reader:latest
    container_name: r_jina_ai
    ports:
      - "5005:3000"
    volumes:
      - /data/docker_data/r_jina_ai:/app/local-storage
    restart: unless-stopped

使用

Once the Docker container is running, you can use curl to make requests. Here are examples for different response types:

📝 Markdown (bypasses readability processing):

curl -H "X-Respond-With: markdown" 'https://jina.0ms.net/https://google.com'

🌐 HTML (returns documentElement.outerHTML):

curl -H "X-Respond-With: html" 'https://jina.0ms.net/https://google.com'

📄 Text (returns document.body.innerText):

curl -H "X-Respond-With: text" 'https://jina.0ms.net/https://google.com'

📸 Screen-Size Screenshot (returns the URL of the webpage’s screenshot):

curl -H "X-Respond-With: screenshot" 'https://jina.0ms.net/https://google.com'

📸 Full-Page Screenshot (returns the URL of the webpage’s screenshot):

curl -H "X-Respond-With: pageshot" 'https://jina.0ms.net/https://google.com'