| Research preview | Paper | Website |

Latest News 🔥

• [2024/07] We add VectorRM to support grounding on user-provided documents, complementing existing support of search engines (YouRM, BingSearch). (check out #58)
• [2024/07] We release demo light for developers a minimal user interface built with streamlit framework in Python, handy for local development and demo hosting (checkout #54)
• [2024/06] We will present STORM at NAACL 2024! Find us at Poster Session 2 on June 17 or check our presentation material.
• [2024/05] We add Bing Search support in rm.py. Test STORM with GPT-4o - we now configure the article generation part in our demo using GPT-4o model.
• [2024/04] We release refactored version of STORM codebase! We define interface for STORM pipeline and reimplement STORM-wiki (check out src/storm_wiki) to demonstrate how to instantiate the pipeline. We provide API to support customization of different language models and retrieval/search integration.

While the system cannot produce publication-ready articles that often require a significant number of edits, experienced Wikipedia editors have found it helpful in their pre-writing stage.

Try out our live research preview to see how STORM can help your knowledge exploration journey and please provide feedback to help us improve the system 🙏!

STORM breaks down generating long articles with citations into two steps:

1. Pre-writing stage: The system conducts Internet-based research to collect references and generates an outline.
2. Writing stage: The system uses the outline and references to generate the full-length article with citations.

STORM identifies the core of automating the research process as automatically coming up with good questions to ask. Directly prompting the language model to ask questions does not work well. To improve the depth and breadth of the questions, STORM adopts two strategies:

1. Perspective-Guided Question Asking: Given the input topic, STORM discovers different perspectives by surveying existing articles from similar topics and uses them to control the question-asking process.
2. Simulated Conversation: STORM simulates a conversation between a Wikipedia writer and a topic expert grounded in Internet sources to enable the language model to update its understanding of the topic and ask follow-up questions.

Based on the separation of the two stages, STORM is implemented in a highly modular way using dspy.

Below, we provide a quick start guide to run STORM locally.

1. Clone the git repository.

   git clone https://github.com/stanford-oval/storm.git
   cd storm

2. Install the required packages.

   conda create -n storm python=3.11
   conda activate storm
   pip install -r requirements.txt

3. Set up OpenAI API key (if you want to use OpenAI models to power STORM) and You.com search API key. Create a file secrets.toml under the root directory and add the following content:

   # Set up OpenAI API key.
   OPENAI_API_KEY="your_openai_api_key"
   # If you are using the API service provided by OpenAI, include the following line:
   OPENAI_API_TYPE="openai"
   # If you are using the API service provided by Microsoft Azure, include the following lines:
   OPENAI_API_TYPE="azure"
   AZURE_API_BASE="your_azure_api_base_url"
   AZURE_API_VERSION="your_azure_api_version"
   # Set up You.com search API key.
   YDC_API_KEY="your_youcom_api_key"

To run STORM with gpt family models with default configurations: Make sure you have set up the OpenAI API key and run the following command.

python examples/run_storm_wiki_gpt.py \
    --output-dir $OUTPUT_DIR \
    --retriever you \
    --do-research \
    --do-generate-outline \
    --do-generate-article \
    --do-polish-article

• --do-research: if True, simulate conversation to research the topic; otherwise, load the results.
• --do-generate-outline: If True, generate an outline for the topic; otherwise, load the results.
• --do-generate-article: If True, generate an article for the topic; otherwise, load the results.
• --do-polish-article: If True, polish the article by adding a summarization section and (optionally) removing duplicate content.

We provide more example scripts under examples to demonstrate how you can run STORM using your favorite language models or grounding on your own corpus.

Besides running scripts in examples, you can customize STORM based on your own use case. STORM engine consists of 4 modules:

1. Knowledge Curation Module: Collects a broad coverage of information about the given topic.
2. Outline Generation Module: Organizes the collected information by generating a hierarchical outline for the curated knowledge.
3. Article Generation Module: Populates the generated outline with the collected information.
4. Article Polishing Module: Refines and enhances the written article for better presentation.

The interface for each module is defined in src/interface.py, while their implementations are instantiated in src/storm_wiki/modules/*. These modules can be customized according to your specific requirements (e.g., generating sections in bullet point format instead of full paragraphs).

🌟 You can share your customization of Engine by making PRs to this repo!

As a knowledge curation engine, STORM grabs information from the Retriever module. The Retriever modules are implemented in src/rm.py. Currently, STORM supports the following retrievers:

• YouRM: You.com search engine API
• BingSearch: Bing Search API
• VectorRM: a retrieval model that retrieves information from user provide corpus

🌟 PRs for integrating more search engines/retrievers are highly appreciated!

STORM provides the following language model implementations in src/lm.py:

• OpenAIModel
• ClaudeModel
• VLLMClient
• TGIClient
• TogetherClient

🌟 PRs for integrating more language model clients are highly appreciated!

💡 For a good practice,

• choose a cheaper/faster model for conv_simulator_lm which is used to split queries, synthesize answers in the conversation.
• if you need to conduct the actual writing step, choose a more powerful model for article_gen_lm. Based on our experiments, weak models are bad at generating text with citations.
• for open models, adding one-shot example can help it better follow instructions.

Please refer to the scripts in the examples directory for concrete guidance on customizing the language model used in the pipeline.

Please switch to the branch NAACL-2024-code-backup

python -m scripts.run_prewriting --input-source file --input-path ../FreshWiki/topic_list.csv  --engine gpt-4 --do-research --max-conv-turn 5 --max-perspective 5

python -m scripts.run_prewriting --input-source console --engine gpt-4 --max-conv-turn 5 --max-perspective 5 --do-research

python -m scripts.run_writing --input-source file --input-path ../FreshWiki/topic_list.csv --engine gpt-4 --do-polish-article --remove-duplicate

python -m scripts.run_writing --input-source console --engine gpt-4 --do-polish-article --remove-duplicate

python eval_outline_quality.py --input-path ../FreshWiki/topic_list.csv --gt-dir ../FreshWiki --pred-dir ../results --pred-file-name storm_gen_outline.txt --result-output-path ../results/storm_outline_quality.csv

python eval_article_quality.py --input-path ../FreshWiki/topic_list.csv --gt-dir ../FreshWiki --pred-dir ../results --gt-dir ../FreshWiki --output-dir ../results/storm_article_eval_results --pred-file-name storm_gen_article_polished.txt

If you have any questions or suggestions, please feel free to open an issue or pull request. We welcome contributions to improve the system and the codebase!

Contact person: Yijia Shao and Yucheng Jiang

We would like to thank Wikipedia for their excellent open-source content. The FreshWiki dataset is sourced from Wikipedia, licensed under the Creative Commons Attribution-ShareAlike (CC BY-SA) license.

We are very grateful to Michelle Lam for designing the logo for this project and Dekun Ma for leading the UI development.

Please cite our paper if you use this code or part of it in your work:

@inproceedings{shao2024assisting,
      title={{Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models}}, 
      author={Yijia Shao and Yucheng Jiang and Theodore A. Kanell and Peter Xu and Omar Khattab and Monica S. Lam},
      year={2024},
      booktitle={Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)}
}