storm-server

Context

Based implementation of Storm

Used

FastAPI + Storm + Mysql

Config

cp .env.example .env

Database

./db/init_data.sql

Install

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

Start

python main.py

Docs

• http://127.0.0.1:8080/api/v1/docs

Openapi - check_sensitive_info

{
    "id": "chatcmpl-9wgLzyUVgvTmZ3gOMveN4K4i4F6iA",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null,
            "message": {
                "content": "No",
                "refusal": null,
                "role": "assistant",
                "function_call": null,
                "tool_calls": null
            }
        }
    ],
    "created": 1723772859,
    "model": "gpt-3.5-turbo-0125",
    "object": "chat.completion",
    "service_tier": null,
    "system_fingerprint": null,
    "usage": {
        "completion_tokens": 1,
        "prompt_tokens": 68,
        "total_tokens": 69
    }
}

Output file tree

.
├── conversation_log.json
├── direct_gen_outline.txt
├── llm_call_history.jsonl
├── raw_search_results.json
├── run_config.json
├── storm_gen_article.txt
├── storm_gen_article_polished.txt
├── storm_gen_outline.txt
└── url_to_info.json

Logging

***** Execution time *****
run_knowledge_curation_module: 116.6072 seconds
run_outline_generation_module: 9.6553 seconds
run_article_generation_module: 38.8765 seconds
run_article_polishing_module: 7.7596 seconds
***** Token usage of language models: *****
run_knowledge_curation_module
    gpt-4o-mini-2024-07-18: {'prompt_tokens': 8377, 'completion_tokens': 3306}
    gpt-4o-2024-08-06: {'prompt_tokens': 0, 'completion_tokens': 0}
run_outline_generation_module
    gpt-4o-mini-2024-07-18: {'prompt_tokens': 0, 'completion_tokens': 0}
    gpt-4o-2024-08-06: {'prompt_tokens': 570, 'completion_tokens': 498}
run_article_generation_module
    gpt-4o-mini-2024-07-18: {'prompt_tokens': 0, 'completion_tokens': 0}
    gpt-4o-2024-08-06: {'prompt_tokens': 9253, 'completion_tokens': 3116}
run_article_polishing_module
    gpt-4o-mini-2024-07-18: {'prompt_tokens': 0, 'completion_tokens': 0}
    gpt-4o-2024-08-06: {'prompt_tokens': 3122, 'completion_tokens': 404}
***** Number of queries of retrieval models: *****
run_knowledge_curation_module: {'SerperRM': 9}
run_outline_generation_module: {'SerperRM': 0}
run_article_generation_module: {'SerperRM': 0}
run_article_polishing_module: {'SerperRM': 0}

SSE

data: {"state": "pre_writing", "is_done": false, "code": 200}

data: {"state": "identify_perspective_start", "is_done": false, "code": 200}

data: {"state": "identify_perspective_end", "is_done": false, "code": 200}

data: {"state": "information_gathering_start", "is_done": false, "code": 200}

data: {"state": "dialogue_turn_end", "is_done": false, "code": 200}

data: {"state": "dialogue_turn_end", "is_done": false, "code": 200}

data: {"state": "dialogue_turn_end", "is_done": false, "code": 200}

data: {"state": "information_gathering_start", "is_done": false, "code": 200}

data: {"state": "information_organization_start", "is_done": false, "code": 200}

data: {"state": "direct_outline_generation_end", "is_done": false, "code": 200}

data: {"state": "outline_refinement_end", "is_done": false, "code": 200}

data: {"state": "pre_writing_end", "is_done": false, "code": 200}

data: {"state": "generate_article_end", "is_done": false, "code": 200}

data: {"state": "completed", "is_done": true, "code": 200}

Citations

@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)}
}