Smart Knowledge Extraction CLI
Transform documents into structured knowledge with one command.
๐ English Version ยท ไธญๆ็
"Stop reading. Start understanding."
"ๅๅซๆๆกฃ็ฆ่๏ผ่ฎฉไฟกๆฏไธ็ฎไบ็ถ"
Hyper-Extract is an intelligent, LLM-powered knowledge extraction and evolution framework. It radically simplifies transforming highly unstructured texts into persistent, predictable, and strongly-typed Knowledge Abstracts. It effortlessly extracts information into a wide spectrum of formatsโranging from simple Collections (Lists/Sets) and Pydantic Models, to complex Knowledge Graphs, Hypergraphs, and even Spatio-Temporal Graphs.
โจ Core Features
| ๐ท 8 Knowledge Structures | From simple Lists to advanced Graphs, Hypergraphs, and Spatio-Temporal Graphs |
| ๐ง 10+ Extraction Engines | GraphRAG, LightRAG, Hyper-RAG, KG-Gen, and more โ ready to use |
| ๐ 80+ YAML Templates | Zero-code extraction across Finance, Legal, Medical, TCM, Industry, and General domains |
| ๐ Incremental Evolution | Feed new documents anytime to expand and refine your knowledge base |
๐ฏ What Can You Do With It?
๐ Researcher โ Turn papers into knowledge graphs
Feed a 20-page academic paper, get an interactive graph of key concepts, authors, and citations.
he parse paper.pdf -t general/academic_graph -o ./paper_kb/
he show ./paper_kb/๐ฆ Financial Analyst โ Extract entities from earnings reports
Automatically identify companies, executives, financial metrics, and their relationships from unstructured reports.
he parse earnings.md -t finance/earnings_graph -o ./finance_kb/
he search ./finance_kb/ "What are the key risk factors?"๐ Local Deployment โ Keep data on-premise with vLLM
Run Qwen3.5-9B + bge-m3 locally via vLLM. No data leaves your machine.
from hyperextract import create_client
llm, emb = create_client(
llm="vllm:Qwen3.5-9B@http://localhost:8000/v1",
embedder="vllm:bge-m3@http://localhost:8001/v1",
api_key="dummy",
)๐ Supported Platforms & Models
Hyper-Extract relies on the LLM's structured output capability (json_schema or Function Calling).
| Platform | Verified Models |
|---|---|
| OpenAI | gpt-4o, gpt-4o-mini, gpt-5 |
| ้ฟ้ไบ็พ็ผ | qwen-plus, qwen-turbo, deepseek-r1 |
| Local vLLM | Qwen3.5-9B (GPTQ-Marlin) |
Embedding models (semantic search) work with any OpenAI-compatible endpoint: text-embedding-3-small, text-embedding-v4 (Bailian), bge-m3 (local vLLM).
๐ Full guide: Provider System & Local Model Support
โก 30-Second Quick Start
# Install
uv tool install hyperextract
# Configure API key
he config init -k YOUR_OPENAI_API_KEY
# Extract knowledge from a document
he parse examples/en/tesla.md -t general/biography_graph -o ./output/ -l en
# Query it
he search ./output/ "What are Tesla's major achievements?"
# Visualize
he show ./output/๐ Python API (click to expand)
uv pip install hyperextractfrom hyperextract import Template
ka = Template.create("general/biography_graph")
with open("examples/en/tesla.md") as f:
result = ka.parse(f.read())
result.show()๐ More examples: examples/en
๐ Why Hyper-Extract?
| Feature | GraphRAG | LightRAG | KG-Gen | ATOM | Hyper-Extract |
|---|---|---|---|---|---|
| Knowledge Graph | โ | โ | โ | โ | โ |
| Temporal Graph | โ | โ | โ | โ | โ |
| Spatial Graph | โ | โ | โ | โ | โ |
| Hypergraph | โ | โ | โ | โ | โ |
| Domain Templates | โ | โ | โ | โ | โ |
| Interactive CLI | โ | โ | โ | โ | โ |
| Multi-language | โ | โ | โ | โ | โ |
๐งฉ Supported Knowledge Structures
From simple to complex โ pick the right structure for your data:
Example โ AutoGraph visualization:
๐ What's under the hood? (Architecture & Templates)
Hyper-Extract follows a three-layer architecture:
- Auto-Types โ 8 strongly-typed data structures (Model, List, Set, Graph, Hypergraph, Temporal Graph, Spatial Graph, Spatio-Temporal Graph)
- Methods โ Extraction algorithms: KG-Gen, GraphRAG, LightRAG, Hyper-RAG, Cog-RAG, and more
- Templates โ 80+ presets across 6 domains. Zero-code setup.
Template example (Graph type):
language: en
name: Knowledge Graph
type: graph
tags: [general]
description: 'Extract entities and their relationships.'
output:
entities:
fields:
- name: name
type: str
- name: type
type: str
- name: description
type: str
relations:
fields:
- name: source
type: str
- name: target
type: str
- name: type
type: str
identifiers:
entity_id: name
relation_id: '{source}|{type}|{target}'๐ Documentation & Resources
| Resource | Link |
|---|---|
| Full Documentation | yifanfeng97.github.io/Hyper-Extract |
| CLI Guide | Command-line interface |
| Provider System | Model compatibility & local deployment |
| Template Gallery | 80+ presets |
| Examples | Working code |
๐ค Contributing & License
Contributions are welcome! Please submit Issues and PRs.
Licensed under Apache-2.0.