An AI-powered academic literature review assistant that helps agricultural biology researchers analyze cucumber salt tolerance mechanisms using PDF upload, RAG with citations, and a three-color fact-anchoring system.

Stars

6

7-day growth

No data

Forks

0

Open issues

0

License

No data

Last updated

2026-07-28

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It combines a modern React frontend with a FastAPI backend and ChromaDB vector storage to deliver paragraph generation with precise source citations, specifically tailored to a narrow but important agricultural research domain.

Who it is for

  • Graduate students studying cucumber salt tolerance
  • Agricultural biology research teams
  • Developers building domain-specific RAG applications

Use cases

  • Uploading research PDFs on cucumber salt tolerance
  • Generating literature review paragraphs with inline citations
  • Visually validating facts with green/yellow/red anchoring
  • Saving or rolling back generated paragraphs atomically

Strengths

  • PDF text and coordinate extraction via PyMuPDF
  • ChromaDB vector storage with page/line provenance
  • Headless UI architecture separating hooks from components
  • Dynamic prompt registry using YAML (no hardcoded prompts)

Considerations

  • v0.1 early stage; only DeepSeek LLM currently supported
  • Only works with text-based PDFs; scanned PDFs are rejected
  • Requires a DeepSeek API key to run

README quick start

Quick Start

Description

Cucumber Literature Agent — 面向农业生物学研究的 AI 驱动文献综述助手。专为黄瓜耐盐性机制研究设计,支持 PDF 上传后自动向量化构建 RAG 知识库,通过 LLM 按章节大纲生成带 [Ref: file.pdf, Page: X, Line: Y] 精确引用的段落,并对每句声明进行三色事实核查(绿/黄/红),锚定原文页码,有效遏制大模型幻觉。内置可配置 Prompt 模板库,支持 DeepSeek / Claude / GPT 多模型切换。已支撑发表 2 篇 SCI 二区 + 1 篇中文核心论文。

Related repositories

Similar projects matched by category, topics, and programming language.

makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958
hahhforest
Featured
hahhforest GitHub avatar

pi-textbook

A hands-on course that walks through building a Pi-style coding agent from scratch across 15 checkpoints, starting from an offline agent trajectory.

AI & Machine LearningLarge Language Models
625
deerwork-ai
Featured
deerwork-ai GitHub avatar

deer-workflow

An open-source Dynamic Workflow runtime that combines deterministic TypeScript orchestration with replaceable Agent runtimes.

AI & Machine LearningLarge Language Models
312