| Name | lorax-ai JSON |
| Version |
0.1.0
JSON |
| download |
| home_page | None |
| Summary | Lorax is AI tool assistant to analyze and visualize trees |
| upload_time | 2025-01-04 05:18:04 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | <3.13,>=3.9 |
| license | None |
| keywords |
egg
bacon
sausage
tomatoes
lobster thermidor
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Treesequence_LLM_Viz
Query based Code Generation and Analysis of Tree-Sequence using LLM.
### Goal
The goal is to leverage Large-language Models(LLM) to generate code and analyze tree-sequences using tskit by simply asking questions in plain English. With Retrieval-Augmented Generation (RAG), users can input questions in plain English, and the system will generate executable tskit code to answer these queries.
### Current Version:
In this initial proof-of-concept, the tskit source code is used as a knowledge base for the Large Language Model (LLM). When users input queries in natural language, the LLM generates the appropriate code based on the knowledge and returns a python function as a response.
Current version is a naive ```prompt:answer``` approach which does not evaluate the accuracy of the generated code.
### Next things to do.
- [x] Code generation can be improved using [Flow Engineering Approach](https://arxiv.org/pdf/2401.08500). Use LangGraph and openai Function Calling to setup the workflow.
- [x] Code execution with error checking.
- [x] Multiple Iterations.
- [x] Terminal chat interface / UI interface (flask-reactjs)
- [ ] human-in-the-loop. (human intervention to review the code or correct it.)
- [ ] Additional node(tool) to ask general tree-sequence question that are not related to code-generation.
- [ ] Accuracy/reliability of the generated answer.
### Exploration
- How to enhance treesequence analysis. one way is [MemoRAG](https://github.com/qhjqhj00/MemoRAG). Memory-based knowledge discovery for long contexts.
Raw data
{
"_id": null,
"home_page": null,
"name": "lorax-ai",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.9",
"maintainer_email": null,
"keywords": "egg, bacon, sausage, tomatoes, Lobster Thermidor",
"author": null,
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/ae/01/82037e35a940a68e814bb68b9f380fc4c08f57096da87b5bdbf1d0e76f9a/lorax_ai-0.1.0.tar.gz",
"platform": null,
"description": "# Treesequence_LLM_Viz\nQuery based Code Generation and Analysis of Tree-Sequence using LLM.\n\n### Goal\nThe goal is to leverage Large-language Models(LLM) to generate code and analyze tree-sequences using tskit by simply asking questions in plain English. With Retrieval-Augmented Generation (RAG), users can input questions in plain English, and the system will generate executable tskit code to answer these queries. \n\n### Current Version:\nIn this initial proof-of-concept, the tskit source code is used as a knowledge base for the Large Language Model (LLM). When users input queries in natural language, the LLM generates the appropriate code based on the knowledge and returns a python function as a response. \n\nCurrent version is a naive ```prompt:answer``` approach which does not evaluate the accuracy of the generated code. \n\n### Next things to do.\n- [x] Code generation can be improved using [Flow Engineering Approach](https://arxiv.org/pdf/2401.08500). Use LangGraph and openai Function Calling to setup the workflow. \n \n- [x] Code execution with error checking.\n- [x] Multiple Iterations.\n- [x] Terminal chat interface / UI interface (flask-reactjs)\n- [ ] human-in-the-loop. (human intervention to review the code or correct it.)\n- [ ] Additional node(tool) to ask general tree-sequence question that are not related to code-generation.\n- [ ] Accuracy/reliability of the generated answer.\n\n### Exploration\n- How to enhance treesequence analysis. one way is [MemoRAG](https://github.com/qhjqhj00/MemoRAG). Memory-based knowledge discovery for long contexts. \n\n",
"bugtrack_url": null,
"license": null,
"summary": "Lorax is AI tool assistant to analyze and visualize trees",
"version": "0.1.0",
"project_urls": null,
"split_keywords": [
"egg",
" bacon",
" sausage",
" tomatoes",
" lobster thermidor"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "449d8454225c3fbc1bb15a65e623db9740d50344f5ff7cd4f6c0db684de55d0a",
"md5": "d09bbf8e6bc1884207926843fff5e654",
"sha256": "2ae2d1fd80f5f5d987978709ca4c13eb56aa8ab9c32d8a1bb8861751b7433040"
},
"downloads": -1,
"filename": "lorax_ai-0.1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "d09bbf8e6bc1884207926843fff5e654",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.13,>=3.9",
"size": 77326259,
"upload_time": "2025-01-04T05:17:51",
"upload_time_iso_8601": "2025-01-04T05:17:51.650250Z",
"url": "https://files.pythonhosted.org/packages/44/9d/8454225c3fbc1bb15a65e623db9740d50344f5ff7cd4f6c0db684de55d0a/lorax_ai-0.1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "ae0182037e35a940a68e814bb68b9f380fc4c08f57096da87b5bdbf1d0e76f9a",
"md5": "125906c7b2ca185d2f3228f45b9c4a1f",
"sha256": "4d8a2192f11ae7843e66310fea23cdd0753830d0bb0090425a58d8f254b44a2e"
},
"downloads": -1,
"filename": "lorax_ai-0.1.0.tar.gz",
"has_sig": false,
"md5_digest": "125906c7b2ca185d2f3228f45b9c4a1f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.9",
"size": 77370628,
"upload_time": "2025-01-04T05:18:04",
"upload_time_iso_8601": "2025-01-04T05:18:04.220670Z",
"url": "https://files.pythonhosted.org/packages/ae/01/82037e35a940a68e814bb68b9f380fc4c08f57096da87b5bdbf1d0e76f9a/lorax_ai-0.1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-04 05:18:04",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "lorax-ai"
}
