Penrose Analyst
Search global news and research papers. Summarize Arxiv.org links. Ask me for the latest news!
- Name For Model
- penrose_research_analyst
- Website
- www.aperiodic.io
- Try on ChatGPT
- Open ChatGPT and Search the plugin name
- Update Date
- a year ago
- Contact
- [email protected]
- Description For Model
- Semantically search news and research papers. Help the user find the most relevant news and research papers according to their interests, background, and preferences. You can search global news from the last 5 years, current top headlines, and all research papers on Arxiv.org. You can also embed and summarize Arxiv.org links. Important: All Arxiv.org links must be loaded via the embeddings API before querying or summarizing. Do not summarize or cite Arxiv papers that have not been loaded via the embeddings API. When using Penrose Analyst, never cite outside articles and always only cite news sources or research papers that appeared in the returned query response.
Plugin Functions/Features (Plugin API Document)
| Operation Id | HTTP Method | Description | |
|---|---|---|---|
| 1 | search_all_arxiv_papers | GET | Search all research papers hosted on Arxiv.org by title, author, abstract and category. |
| 2 | load_arxiv_pdf | GET | Load an Arxiv.org research paper as a PDF for future summarization, retrieval, or question answering. Required to use other Arxiv endpoints. Do not summarize or cite papers that have not been loaded. |
| 3 | query_arxiv_pdf | GET | Query a previously loaded Arxiv.org PDF document. You must always load a PDF before querying it! |
| 4 | query_all_news | GET | Query all-time global news, blogs, and other sources by keywords, date created, and domain source. After querying, consider leveraging fetching the full article content via get_article_content. |
| 5 | get_top_headlines | GET | Get live top and breaking headlines for a certain country, category, or keyword. Endpoint may return as empty list if no headlines for query are found. |
| 6 | get_article_content | GET | Get the full content of a news article from a given URL. Do not pass in a URL that is not from the response of the query_all_news or get_top_headlines endpoints! This will not work with Arxiv.org links! |