yifanfeng97/Hyper-Extract

# Anthropic (Claude) — LLM only
he config llm -p anthropic -k YOUR_ANTHROPIC_API_KEY
he config embedder -p openai -k YOUR_OPENAI_API_KEY

# Google Gemini — LLM only (default: gemini-3.8-flash)
he config llm -p google -k YOUR_GOOGLE_API_KEY
he config embedder -p openai -k YOUR_OPENAI_API_KEY

# Alibaba Bailian (Qwen, LLM + embeddings in one key)
he config init -p bailian -k YOUR_BAILIAN_API_KEY

OpenAI and Bailian provide both LLM and embedding models in one API. Anthropic, Google Gemini, and DeepSeek are LLM-only (pair them with an OpenAI-compatible embedder). DeepSeek is the most cost-effective option (~$0.001-0.005/page).

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()

🔗 More examples: examples/en

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/

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?"

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",
)

Documents change. Hyper-Extract tracks every source so you can update, roll back, or audit without starting over.

# 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# Document is obsolete?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

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:

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

Anthropic: Claude is used for the LLM (set ANTHROPIC_API_KEY, extra: pip install 'hyperextract[anthropic]'). No embeddings API:

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

Google Gemini: Gemini is used for the LLM (set GOOGLE_API_KEY or GEMINI_API_KEY, extra: pip install 'hyperextract[google]'). Default model is gemini-3.8-flash. No mature embedder path in this repo:

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

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