Jina Reader
Jina Reader is a tool that converts web pages, PDF, MS Office documents, and images into Markdown format that is suitable for AI models. API supports the functions of reading web content and performing search queries via endpoint. The project can cache with MinIO or S3 compatible storage areas as it can run in stateless mode.
jina-ai · Web Scraping & Automation
Common commercial products in this category: Bright Data, Apify, ScrapingBee
- You can convert any web page or document into a Markdown format that AI models can process.
- By sending search queries, you can access up-to-date web data and transfer that data to LLM systems as inputs.
- You can translate images and office files into descriptive text that text-based models can understand.
- • No published release
- • NeutralGitHub Issue
npm run build failed because shared files are not found
“Error: ```javascript $ npm run build > build > tsc -p . src/cloud-functions/crawler.ts:3:79 - error TS2307: Cannot find module '../shared' or its corresponding type declarations. 3 import { CloudHTTPv2, Ctx, Logger, OutputServerEventStream, RPCReflect } from '../shared';…”