Academic Research
Search 250M+ academic works via OpenAlex. No API key required.
Built by Topanga — AI Research Consultant
Quick Start
Search papers by topic
CODEBLOCK0
Search by author
CODEBLOCK1
Look up by DOI
CODEBLOCK2
Get citation chain (papers that cite a work)
CODEBLOCK3
Deep read (fetch abstract + full text when available)
CODEBLOCK4
JSON output for programmatic use
CODEBLOCK5
Literature Review Workflow
Automated multi-step literature review:
CODEBLOCK6
This will:
- 1. Search for papers across multiple query variations
- Deduplicate and rank by relevance + citations
- Identify thematic clusters
- Generate a structured synthesis in markdown
Options:
- -
--papers N — Target number of papers (default: 20) - INLINECODE1 — Write review to file (default: stdout)
- INLINECODE2 — Restrict publication year range
- INLINECODE3 — Output structured JSON instead of markdown
Output Format
All search commands return structured data per paper:
- - Title and publication year
- Authors (up to 5)
- Abstract (when available)
- Citation count
- DOI
- Open access URL (when available)
- Source journal/venue
Tips
- - OpenAlex sorts by relevance by default; use
--sort citations for most-cited - Combine
search + deep for quick triage: search first, deep-read promising hits - The literature review script caches results in
/tmp/litreview_cache/ to avoid re-fetching - For full-text PDFs, pipe DOIs to your PDF extraction tool
学术研究
通过OpenAlex检索超过2.5亿篇学术著作。无需API密钥。
由Topanga——AI研究顾问构建
快速入门
按主题搜索论文
bash
python3 scripts/scholar-search.py search transformer架构 --limit 10
按作者搜索
bash
python3 scripts/scholar-search.py author Yann LeCun --limit 5
通过DOI查询
bash
python3 scripts/scholar-search.py doi 10.1038/s41586-021-03819-2
获取引用链(引用某篇论文的文献)
bash
python3 scripts/scholar-search.py citations 10.1038/s41586-021-03819-2 --direction both
深度阅读(获取摘要及全文(如可用))
bash
python3 scripts/scholar-search.py deep 10.1038/s41586-021-03819-2
程序化使用的JSON输出
bash
python3 scripts/scholar-search.py search CRISPR --json
文献综述工作流
自动化多步骤文献综述:
bash
python3 scripts/literature-review.py 教育中的算法素养 --papers 30 --output review.md
此命令将:
- 1. 通过多种查询变体搜索论文
- 去重并按相关性+引用量排序
- 识别主题聚类
- 生成结构化的Markdown综合报告
选项:
- - --papers N — 目标论文数量(默认:20)
- --output FILE — 将综述写入文件(默认:标准输出)
- --years 2020-2025 — 限制出版年份范围
- --json — 输出结构化JSON而非Markdown
输出格式
所有搜索命令均返回每篇论文的结构化数据:
- - 标题和出版年份
- 作者(最多5位)
- 摘要(如可用)
- 引用次数
- DOI
- 开放获取URL(如可用)
- 来源期刊/会议
提示
- - OpenAlex默认按相关性排序;使用--sort citations按引用量排序
- 结合使用search和deep进行快速筛选:先搜索,再深度阅读有前景的结果
- 文献综述脚本将结果缓存至/tmp/litreview_cache/以避免重复获取
- 如需全文PDF,可将DOI导入您的PDF提取工具