Data Connectors

A command-line downloader that also collects every detail a video site publishes about a video or a whole channel.

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

A Python toolkit for collecting data from web pages that can find an item again after the page layout changes.

It converts PDFs into clean Markdown or JSON, keeping headings, tables, equations and reading order.

A Python framework for fetching and parsing large numbers of web pages.

A no-code RAG server that keeps answers in sync with your documents. Works with 8 vector databases. Built on Pathway.

LlamaIndex is the document processing platform for AI

A crawling framework for JavaScript that manages the queue, the retries and the rate limits.

A database of what a network and its hardware are supposed to look like, which other programs can read.

It downloads every picture from an album or a profile with one command.

A workbench for cleaning up a messy spreadsheet.

It makes an RSS feed for a website that removed its own.

Fetches the subtitles of a public YouTube video as text, with no key and no browser.

A Python scraper that learns what to extract from one example you give it.

A Python framework for collecting data from web pages that are trying to block automated visitors.

Schema validation for DataFrames — the error that fires before a backtest quietly reports a fictional edge.

A fast command-line toolkit for sorting, joining, checking and describing CSV files.

It converts an Oracle database schema and data into PostgreSQL, and estimates the effort first.

A small Python package that downloads a United States company's official filings to a local folder.

A Python wrapper around the YouTube Data interface that returns channels, videos, playlists and comments as Python objects.