hyperextract 0.9.0

Smart Knowledge Extraction CLI

Transform documents into structured knowledge with one command.

📖 English Version · 中文版

"Stop reading. Start understanding."
"告别文档焦虑，让信息一目了然"

⚡ 30-Second Quick Start

1. Install:

# Install uv first (if you haven't)
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install Hyper-Extract CLI
uv tool install hyperextract
# or: pipx install hyperextract

2. Configure your provider (pick one):

OpenAI:

he config init -p openai -k YOUR_OPENAI_API_KEY

Anthropic (Claude):

he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
he config embedder -p openai -k YOUR_OPENAI_API_KEY

DeepSeek:

he config llm -p deepseek -k YOUR_DEEPSEEK_API_KEY
he config embedder -p openai -k YOUR_OPENAI_API_KEY

Bailian (Alibaba Cloud):

he config init -p bailian -k YOUR_BAILIAN_API_KEY

Local vLLM:

he config llm -p vllm -u http://localhost:8000/v1 -k dummy -m Qwen/Qwen3.5-9B
he config embedder -p vllm -u http://localhost:8001/v1 -k dummy -m BAAI/bge-m3

3. Extract, query & visualize:

# 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/

# Export to an Obsidian vault (Markdown notes + [[wikilinks]])
he export obsidian ./output/ -o ./vault/

# Your sources change? Feed updates under the same source — old facts roll back automatically
he feed ./output/ updated-tesla.md --source tesla.md

# Tag and scope your searches
he tag ./output/ --source tesla.md --add biography
he search ./output/ "inventions" --tag biography

# Audit: which documents contributed what?
he info ./output/ --sources

Which provider should I use? OpenAI and Bailian provide both LLM and embedding models in one API. Anthropic and DeepSeek are LLM-only (pair them with an OpenAI embedder for search/chat). Local vLLM is free but requires a GPU. DeepSeek is the most cost-effective option (~$0.001-0.005/page vs ~$0.01-0.05/page for OpenAI gpt-4o-mini).

uv pip install hyperextract

from hyperextract import Template

ka = Template.create("general/biography_graph")

with open("examples/en/tesla.md") as f:
    result = ka.parse(f.read())

result.show()

✨ Core Features

🎯 What Can You Do With It?

he parse paper.pdf -t general/academic_graph -o ./paper_kb/
he show ./paper_kb/

he parse earnings.md -t finance/earnings_graph -o ./finance_kb/
he search ./finance_kb/ "What are the key risk factors?"

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",
)

# Ingest with attribution — every fact is traceable to its source
he feed ./ka/ contract-v1.md --source contract-v1
he tag ./ka/ --source contract-v1 --add legal --add acme

# Document updated? Re-feed under the same source — old facts roll back automatically
he feed ./ka/ contract-v2.md --source contract-v1

# Document is obsolete? Roll back everything it contributed
he remove ./ka/ --document contract-v1

# Remove a single wrong fact (LLM-assisted, with dry-run preview)
he remove ./ka/ --edit-node Apple --fact "founded by Steve Jobs" --dry-run

# Search only within legal-tagged documents
he search ./ka/ "termination clause" --tag legal

# Audit: which documents contributed what?
he info ./ka/ --sources

🚀 Supported Platforms & Models

Hyper-Extract uses LangChain structured output with function calling. The model must support tool/function calling.

Embedding models (semantic search) work with any OpenAI-compatible endpoint: text-embedding-3-small, text-embedding-v4 (Bailian), bge-m3 (local vLLM).

DeepSeek note: DeepSeek V4 models default to "thinking" mode, which Hyper-Extract auto-disables so structured extraction works. Set DEEPSEEK_API_KEY. DeepSeek has no embeddings API — pair it with an OpenAI-compatible embedder:

from hyperextract import create_client
llm, emb = create_client(llm="deepseek", embedder="openai:text-embedding-3-small")

Anthropic note: Claude is used for the LLM (set ANTHROPIC_API_KEY). Anthropic has no embeddings API, so pair it with an OpenAI-compatible embedder:

from hyperextract import create_client
llm, emb = create_client(llm="anthropic", embedder="openai:text-embedding-3-small")

Requires the extra: pip install 'hyperextract[anthropic]'.

📖 Full guide: Provider System & Local Model Support

📈 Why Hyper-Extract?

🧩 Supported Knowledge Structures

From simple to complex — pick the right structure for your data:

Example — AutoGraph visualization:

📋 What's under the hood? (Architecture & Templates)

Hyper-Extract follows a three-layer architecture:

• Auto-Types — 9 strongly-typed data structures (Model, List, Set, Graph, Hypergraph, Temporal Graph, Spatial Graph, Spatio-Temporal Graph, Document corpus)
• Methods — Extraction & retrieval algorithms: Chunk-RAG baseline, KG-Gen, GraphRAG, LightRAG, Hyper-RAG, Cog-RAG, and more
• Templates — 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}'

• Browse all 80+ templates
• Create custom templates

📰 What's New

v0.9.0

• 📄 Rich Document Ingestion — he parse / he feed now accept PDF, Word, PowerPoint, Excel, HTML, CSV/JSON/XML, EPUB and more via the optional ingest extra (pip install "hyperextract[ingest]", powered by MarkItDown). Non-UTF-8 text (GBK, etc.) is auto-detected; text-less (scanned) PDFs fail with a clear OCR hint instead of silently ingesting garbage.
• 🧱 chunk_rag Baseline Method — a new zero-extraction method: documents are chunked and embedded as-is, and search returns raw text chunks. Zero LLM cost at ingestion, with full provenance (tags, scoped search, per-document rollback). The chunk-retrieval baseline for corpus Q&A and method benchmarking.
• 🐛 Fixes — he tag crashed on every knowledge abstract (tag_source was never exposed on any type); he search/he talk/he feed/he remove --document crashed on method-built KAs (method/* templates were not resolvable from KA metadata).

v0.8.1 / v0.8.2

• 🏷️ Source Tags & Scoped Search — he tag ./ka/ --source doc-1 --add legal, then he search ./ka/ "query" --tag legal to retrieve only within tagged documents. Works for graph, hypergraph, and set KAs. (#89, #84)
• 🛡️ Input Validation — he parse / he feed now reject unsupported file types (PDF/Office) with a conversion hint instead of silently ingesting garbage. (#88)
• 📦 Document Archive Fix — re-feeding the same source from a differently-named file no longer accumulates stale copies. (#89)

v0.8.0

• 🔄 Document Upsert — re-feed an attributed document and its previous version is rolled back automatically: removed facts disappear, shared keys re-merge from surviving sources. (#84)
• 📁 Per-File Source Attribution — he parse ./docs/ attributes each file by its name automatically; roll back or audit any single file later. An explicit --source still overrides.
• ⏱️ Spatiotemporal Provenance — temporal/spatial/spatio-temporal graphs fully support source attribution and rollback, with deterministic (MERGE_FIELD) replay tests.

Archived

See the full changelog in the GitHub releases.

📚 Documentation & Resources

🔌 MCP Server

Expose your knowledge abstracts to MCP-capable assistants (Claude Desktop, IDE agents) via the Model Context Protocol — read + export only.

pip install 'hyperextract[mcp]'
he-mcp        # stdio MCP server

Tools: list_templates, info, search, ask (RAG), export_obsidian. Full guide: MCP Server docs.

🤝 Contributing & License

Contributions are welcome! Please submit Issues and PRs.
Licensed under Apache-2.0.

🔒 Security

This project has been security assessed by MseeP.ai.

AtomGit Mirror

AtomGit mirror - a synchronized AtomGit mirror of Agent Reach for easier access and cloning in China. Hosted on AtomGit: https://atomgit.com/yifanfeng97/Hyper-Extract