OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Hyper Extract

Hyper Extract is a Python command-line tool that uses configured LLM and embedding providers to turn documents or unstructured text into structured knowledge, including graphs, hypergraphs and spatio-temporal extractions.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Hyper Extract — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Hyper Extract when you need a command-line document-ingestion stage that creates structured knowledge for later search, visualization or export.

Who it is for

  • Researchers structuring information from papers
  • Analysts extracting entities and relationships from reports
  • Developers building document-ingestion workflows for search or RAG

Documented uses

  • Extract graph, hypergraph or spatio-temporal knowledge from documents.
  • Search and visualize an extracted collection.
  • Export extracted graphs as Markdown notes with Obsidian wikilinks.
  • Update a collection with revised sources and inspect source attribution.
Before you choose

Requirements & limits

The repository is public and provides installation instructions. The README specifies Python 3.11 or later and identifies Apache 2.0 in its license badge.

  • OpenAI can provide both LLM and embedding services; DeepSeek is documented as LLM-only and requires a separate embedder.
  • The README lists local vLLM as an option requiring local services, with separate LLM and embedding configurations.
  • PDF, Word, PowerPoint, Excel, HTML and EPUB ingestion is listed with the optional hyperextract[ingest] extra.
  • The project lists nine knowledge structures, more than 11 extraction engines and over 80 YAML templates.

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 and configure Hyper Extract with OpenAI

Set up the CLI and configure OpenAI for language-model and embedding work.

Before you start

  • Python 3.11 or later
  • uv or pipx
  • An OpenAI API key

Steps

  1. Install uv if it is not already available, or use pipx as the CLI installer.

  2. Install Hyper Extract with the command below or pipx install hyperextract.

    Documented command
    uv tool install hyperextract

  3. Configure the OpenAI provider with he config init -p openai -k YOUR_OPENAI_API_KEY.

Expected outcome

The CLI is installed and configured to use OpenAI for LLM and embedding services.

Guide limitations

  • The README does not establish support for every OpenAI model or endpoint.
Documentation 1 ↗
Source-based practical guide

Parse, search and visualize a document collection

Create a knowledge collection from the example document and use the documented search and display commands.

Before you start

  • Hyper Extract CLI installed and a provider configured
  • The repository example file examples/en/tesla.md

Steps

  1. Parse the example with he parse examples/en/tesla.md -t general/biography_graph -o ./output/ -l en.

  2. Search the result with he search ./output/ "What are Tesla's major achievements?".

  3. Display the collection with he show ./output/.

Expected outcome

The example is parsed into an output collection that can be queried and displayed.

Guide limitations

  • The commands describe the README example workflow; they do not establish results for other documents or templates.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
yifanfeng97/Hyper-Extract · Official homepage title · retained in its source language
How we review sourcesSuggest a correction