v0.2.3 Python Package Release

Python Package Available at PyPI

• You can now install storm via pip install knowledge-storm. (#80)
• We update the README.md to explain our current API.
• If you prefer using the source code, note that pulling the new release will lead to breaking change as we rename src/ to knowledge_storm/.

Ollama Support

#81, credit to: @zhjain

Roadmap & Contribution

Our team is actively working on:

1. Human-in-the-Loop Functionalities: Supporting user participation in the knowledge curation process.
2. Information Abstraction: Developing abstractions for curated information to support presentation formats beyond the Wikipedia-style report.

PRs for integrating more language models into knowledge_storm/lm.py and search engines/retrievers into knowledge_storm/rm.py are highly appreciated!

v0.2.0 New UI release; support customized documents retrieval

Support retrieving information from customized documents

• Add VectorRM to support grounding on user-provided documents, complementing existing support of search engines (YouRM, BingSearch). (#58)
• We provide an example script here and detailed instructions here.

UI updates

• We release a new UI for users to directly interact with STORM, available at https://storm.genie.stanford.edu/. This update brings improved stability and a new feature of discovering popular topics. (Thanks dekunma from Yale for the collaboration)
• We release demo light for developers, a minimal user interface built with streamlit framework in Python, handy for local development and demo hosting (#54)

Miscs

• In-person talk in San Francisco: Our team member will give an invited talk at Wikipedians Meetup @ San Francisco on July 11. Come to chat with us in person!
• Upcoming major update: A major update supporting human-AI collaboration mode will be released over the summer. Stay tuned!

v0.1.0 Refactored codebase

Pipeline Refactoring and Module Interfaces

We release the refactored code for STORM pipeline to make it easier to run/customize/develop STORM.
Interfaces for pipeline modules and data classes have been defined, allowing for better modularity and extensibility.

Language Model Customization Support

STORM now supports the customization of language models across various families and clients, including:

• GPT family
• Claude family
• VLLM client
• TGI client
• Together Client

Examples demonstrating language model customization are provided in the examples/ directory. For more details, please refer to the README.

Retriever Module Customization Support

STORM introduces the ability to customize the Retriever module. As a knowledge curation engine, STORM consumes information provided by the Retriever module.
More information about retriever module customization can be found in the README.

---

This release focuses on enhancing the modularity and flexibility of the STORM pipeline, enabling users to seamlessly integrate and customize language models and retriever modules according to their specific requirements. Contributions to integrating more language model support, search engine/retrieval model support are highly appreciated!