OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Extractor

Extractor is a TypeScript library that uses LangChain chat models, natural-language prompts and Zod schemas to extract structured data from HTML, Markdown or plain text, and convert HTML into LLM-ready Markdown.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Extractor — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a TypeScript workflow needs LLM-based structured extraction from supplied page content, or HTML-to-Markdown preprocessing before an LLM step.

Who it is for

  • TypeScript developers adding web-content extraction to applications or data pipelines.
  • Teams preprocessing HTML for LLM use or collecting structured fields from product pages.

Documented uses

  • Extract schema-defined fields from HTML, Markdown or plain text.
  • Convert HTML to Markdown and optionally focus on main content or clean tracking parameters from URLs.
  • Recover malformed JSON output and handle relative or invalid URLs in extracted content.
  • Load pages with Playwright before extraction, or pair with a separate browser agent when page interaction is needed.
Before you choose

Requirements & limits

The project is an open-source TypeScript library under the Apache-2.0 license. Its README identifies `@langchain/core` as a required peer dependency.

  • HTML input requires a source URL to handle relative URLs correctly.
  • The extraction function requires an LLM instance, content, content format and Zod schema.
  • A LangChain provider integration must be installed separately; the README names OpenAI, Google Gemini, Anthropic and Ollama integrations.
  • The optional input-token limit can truncate content when the configured threshold is exceeded.
  • Repository integration tests require valid provider API keys; unit tests do not make API calls.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Extractor and configure an LLM provider

Set up the library and provider dependencies for a TypeScript project.

Before you start

  • A TypeScript project with Node package installation available.
  • A LangChain chat-model provider to use with the library.
  • Provider API credentials if the selected model requires them.

Steps

  1. Install @lightfeed/extractor and @langchain/core.

  2. Install the LangChain integration package for the chosen provider, such as @langchain/openai, @langchain/google-genai, @langchain/anthropic or @langchain/ollama.

  3. Configure the provider’s model instance and credentials for the project.

Expected outcome

The project has the documented library and provider dependencies needed to configure an LLM for extraction.

Guide limitations

  • The README setup steps do not by themselves perform an extraction.
  • Provider credentials and model configuration depend on the selected integration.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
lightfeed/extractor · Official homepage title · retained in its source language
How we review sourcesSuggest a correction