hyperextract 0.1.1__tar.gz

hyperextract-0.1.1/.gitignore

@@ -0,0 +1,165 @@
+temp/
+logs/
+.trae/
+.github/agents/
+.claude/
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so may be deleted later.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nosuch/
+.nosuch/
+.pytest_cache/
+v/
+.v/
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.tracker
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the Python version is
+#   usually managed by the user. However, for a specific project, it might be useful to check them in.
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if you want to keep your dependencies next to your project code:
+# Pipfile.lock
+
+# poetry
+#   Similar to Pipenv, poetry.lock is generally recommended to be committed.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+
+# pdm
+#   Similar to Pipenv, pdm.lock is generally recommended to be committed.
+# .pdm-python
+# .pdm-build/
+
+# PEP 582; used by e.g. github.com/fannheyward/coc-pyright
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+.idea/
+
+# VS Code
+.vscode/
+.history/
+
+# OS
+.DS_Store
+Thumbs.db

hyperextract-0.1.1/LICENSE

@@ -0,0 +1,200 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined in Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity exercising
+      permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or Object
+      form, made available under the License, as indicated by a copyright
+      notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original Work and any Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, such as but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any Legal Entity on behalf of
+      whom a Contribution has been received by Licensor and subsequently
+      incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file, then any
+          Derivative Works that You distribute must include a readable
+          copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE from the Work, provided that
+          such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions of this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contribution.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [2026] [Yifan Feng]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

hyperextract-0.1.1/PKG-INFO

@@ -0,0 +1,317 @@
+Metadata-Version: 2.4
+Name: hyperextract
+Version: 0.1.1
+Summary: An intelligent, LLM-powered knowledge extraction and evolution framework with semantic search capabilities
+Project-URL: Homepage, https://github.com/yifanfeng97/hyper-extract
+Project-URL: Repository, https://github.com/yifanfeng97/hyper-extract
+Project-URL: Issues, https://github.com/yifanfeng97/hyper-extract/issues
+Author-email: Yifan Feng <evanfeng97@gmail.com>
+License: Apache-2.0
+License-File: LICENSE
+Keywords: faiss,knowledge-extraction,langchain,llm,nlp,pydantic,rag,semantic-search
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Requires-Dist: faiss-cpu>=1.13.2
+Requires-Dist: langchain-community>=0.4.1
+Requires-Dist: langchain-openai>=1.1.7
+Requires-Dist: langchain>=1.2.6
+Requires-Dist: ontomem>=0.2.3
+Requires-Dist: ontosight>=0.1.5
+Requires-Dist: python-dotenv>=1.2.1
+Requires-Dist: rich>=13.7.0
+Requires-Dist: semhash>=0.3.2
+Requires-Dist: structlog>=25.0.0
+Requires-Dist: tomli-w>=1.0.0
+Requires-Dist: typer>=0.13.0
+Provides-Extra: all
+Requires-Dist: langchain-anthropic>=0.3.0; extra == 'all'
+Requires-Dist: langchain-google-genai>=2.1.0; extra == 'all'
+Provides-Extra: anthropic
+Requires-Dist: langchain-anthropic>=0.3.0; extra == 'anthropic'
+Provides-Extra: google
+Requires-Dist: langchain-google-genai>=2.1.0; extra == 'google'
+Description-Content-Type: text/markdown
+
+<div align="center">
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="docs/assets/logo/logo-horizontal-dark.svg">
+  <source media="(prefers-color-scheme: light)" srcset="docs/assets/logo/logo-horizontal.svg">
+  <img alt="Hyper-Extract Logo" src="docs/assets/logo/logo-horizontal.svg" width="600">
+</picture>
+
+<br/>
+<br/>
+
+**Smart Knowledge Extraction CLI**
+
+**Transform documents into structured knowledge with one command.**
+
+[📖 English Version](./README.md) · [中文版](./README_ZH.md)
+
+[![PyPI Version](https://img.shields.io/pypi/v/hyperextract)](https://pypi.org/project/hyperextract/)
+[![Python Version](https://img.shields.io/badge/python-3.11%2B-blue)](https://python.org)
+[![License](https://img.shields.io/badge/license-Apache%202.0-blue)](LICENSE)
+[![Status](https://img.shields.io/badge/status-active-success)]()
+
+<br/>
+
+> **"Stop reading. Start understanding."**  
+> *"告别文档焦虑，让信息一目了然"*
+
+<br/>
+
+<img src="docs/assets/hero.jpg" alt="Hero & Workflow" width="800" style="max-width: 100%;">
+
+<br/>
+</div>
+
+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 formats—ranging from simple **Collections** (Lists/Sets) and **Pydantic Models**, to complex **Knowledge Graphs**, **Hypergraphs**, and even **Spatio-Temporal Graphs**.
+
+## ✨ Core Features
+
+- 🔷 **8 Auto-Types:** From basic `AutoModel`/`AutoList` to advanced `AutoGraph`, `AutoHypergraph`, and `AutoSpatioTemporalGraph`.
+- 🧠 **10+ Extraction Engines:** Out-of-the-box support for cutting-edge retrieval paradigms like `GraphRAG`, `LightRAG`, `Hyper-RAG`, and `KG-Gen`.
+- 📝 **Declarative YAML Templates:** Zero-code extraction definition. Includes 80+ presets across 6 domains.
+- 🔄 **Incremental Evolution:** Feed new documents on the fly to continuously map out and expand the extracted knowledge.
+
+***
+
+## ⚡ Quick Start
+
+### 1. Installation
+
+**For CLI Users** (install `he` command globally):
+
+```bash
+uv tool install hyperextract
+```
+
+**For Python Developers** (use as library):
+
+```bash
+uv pip install hyperextract
+```
+
+### 2. The Command Line Way
+
+Extract, search, and manage directly from CLI.
+
+> By default, the CLI uses `gpt-4o-mini` and `text-embedding-3-small`.
+
+```bash
+# Configure OpenAI API Key
+he config init -k YOUR_OPENAI_API_KEY
+
+# Extract knowledge
+he parse examples/en/tesla.md -t general/biography_graph -o ./output/ -l en
+
+# Query the knowledge abstract
+he search ./output/ "What are Tesla's major achievements?"
+
+# Visualize the knowledge graph
+he show ./output/
+
+# Incrementally supplement knowledge
+he feed ./output/ examples/en/tesla_question.md
+
+# Show the updated knowledge graph
+he show ./output/
+```
+
+<details>
+<summary><b>🐍 The Python API Way</b> (click to expand)</summary>
+<br>
+
+### Installation
+
+```bash
+# Clone the repository
+git clone https://github.com/yifanfeng97/hyper-extract.git
+cd hyper-extract
+
+# Install dependencies
+uv sync
+```
+
+### Configuration
+
+```bash
+# Copy the example env file
+cp .env.example .env
+
+# Edit .env with your API key and base URL
+# OPENAI_API_KEY=your-api-key
+# OPENAI_BASE_URL=https://api.openai.com/v1
+```
+
+### Usage
+
+```python
+import os
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+from hyperextract import Template
+
+# Create a template
+ka = Template.create("general/biography_graph")
+
+# Parse a document
+with open("examples/en/tesla.md", "r", encoding="utf-8") as f:
+    text = f.read()
+result = ka.parse(text)
+
+# Visualize the knowledge graph
+ka.show(result)
+
+# Incrementally supplement knowledge
+with open("examples/en/tesla_question.md", "r", encoding="utf-8") as f:
+    new_text = f.read()
+ka.feed(result, new_text)
+
+# Show the updated knowledge graph
+ka.show(result)
+```
+
+> 🔗 For complete examples, see [examples/en](./examples/en/)
+
+</details>
+
+<br>
+
+**Installation Comparison:**
+
+| Use Case | Command | Purpose |
+|----------|---------|---------|
+| CLI Tool | `uv tool install hyperextract` | Install `he` command globally |
+| Python Library | `uv pip install hyperextract` | Use in Python code |
+
+## 🧩 Deep Dive: The 8 Auto-Types
+
+Our framework embraces complexity without making you write boilerplate code.
+
+<img src="docs/assets/autotypes.jpg" alt="Knowledge Structures Matrix" width="750" style="max-width: 100%;">
+
+### Example: AutoGraph Visualization
+
+Here is the knowledge graph visualization after `AutoGraph` extraction:
+
+<img src="docs/assets/en_show.jpg" alt="AutoGraph Visualization" width="750" style="max-width: 100%; border-radius: 8px; box-shadow: 0 4px 12px rgba(0,0,0,0.1);">
+
+## 🛠️ Architecture Overview
+
+Hyper-Extract follows a **three-layer architecture**:
+
+- **Auto-Types** define the data structures for knowledge extraction. With 8 strong-typed structures (AutoModel, AutoList, AutoSet, AutoGraph, AutoHypergraph, AutoTemporalGraph, AutoSpatialGraph, AutoSpatioTemporalGraph), they serve as the output format for all extractions.
+
+- **Methods** provide extraction algorithms built on Auto-Types. This includes Typical methods (KG-Gen, iText2KG, iText2KG*) and RAG-based methods (GraphRAG, LightRAG, Hyper-RAG, HypergraphRAG, Cog-RAG).
+
+- **Templates** offer domain-specific configurations with ready-to-use prompts and data structures. Covering 6 domains (Finance, Legal, Medical, TCM, Industry, General) with 80+ preset templates, users can extract knowledge without dealing with Auto-Types or Methods directly.
+
+Use via **CLI** (`he parse`, `he search`, `he show`...) or **Python API** (`Template.create()`).
+
+<img src="docs/assets/arch.jpg" alt="Architecture" width="750" style="max-width: 100%;">
+
+### 📚 Related Documentation
+
+- **Preset Templates**: Browse [80+ ready-to-use templates](./hyperextract/templates/presets/) across 6 domains
+- **Design Guide**: Learn how to [create custom templates](./hyperextract/templates/DESIGN_GUIDE.md)
+
+<details>
+<summary><b>📋 Template Structure Example (Graph Type)</b></summary>
+
+Here's a complete YAML template example for **Graph** type extraction (entity-relationship extraction):
+
+```yaml
+language: en
+
+name: Knowledge Graph
+type: graph
+tags: [general]
+
+description: 'Extract entities and their relationships to construct a knowledge graph.'
+
+output:
+  entities:
+    fields:
+    - name: name
+      type: str
+      description: 'Entity name'
+    - name: type
+      type: str
+      description: 'Entity type: e.g., person, organization, event'
+    - name: description
+      type: str
+      description: 'Entity description'
+  relations:
+    fields:
+    - name: source
+      type: str
+      description: 'Source entity'
+    - name: target
+      type: str
+      description: 'Target entity'
+    - name: type
+      type: str
+      description: 'Relation type: e.g., invention, collaboration, competition'
+    - name: description
+      type: str
+      description: 'Relation description'
+
+guideline:
+  target: 'Extract entities and their relationships from the text.'
+  rules_for_entities:
+    - 'Extract meaningful entities'
+    - 'Maintain consistent naming'
+  rules_for_relations:
+    - 'Create relations only when explicitly expressed in the text'
+
+identifiers:
+  entity_id: name
+  relation_id: '{source}|{type}|{target}'
+  relation_members:
+    source: source
+    target: target
+
+display:
+  entity_label: '{name} ({type})'
+  relation_label: '{type}'
+```
+
+</details>
+
+## 📈 Comparison with Other Libraries
+
+| Feature          | GraphRAG | LightRAG | KG-Gen | ATOM | **Hyper-Extract** |
+| ---------------- | :------: | :------: | :----: | :--: | :---------------: |
+| Knowledge Graph  |     ✅    |     ✅    |    ✅   |   ✅  |         ✅         |
+| Temporal Graph   |     ✅    |     ❌    |    ❌   |   ✅  |         ✅         |
+| Spatial Graph    |     ❌    |     ❌    |    ❌   |   ❌  |         ✅         |
+| Hypergraph       |     ❌    |     ❌    |    ❌   |   ❌  |         ✅         |
+| Domain Templates |     ❌    |     ❌    |    ❌   |   ❌  |         ✅         |
+| CLI Tool         |     ✅    |     ❌    |    ❌   |   ❌  |         ✅         |
+| Multi-language   |     ✅    |     ❌    |    ❌   |   ❌  |         ✅         |
+
+## 📚 Related Documentation
+
+- [Full Documentation](https://hyper-extract.github.io/en/) - Complete documentation site
+- [中文文档](https://hyper-extract.github.io/zh/) - 中文文档
+- [CLI Guide](https://hyper-extract.github.io/en/guides/cli/) - Command-line interface
+- [Template Gallery](https://hyper-extract.github.io/en/reference/template-gallery/) - Available templates
+- [Example Code](./examples/) - Working examples
+
+## 🤝 Contributing & License
+
+Contributions are welcome! Please submit Issues and PRs.
+Licensed under **Apache-2.0**.