Search Papers, for Agents
Retrieves relevant abstracts and paper metadata by a search. Generates an answer using LLMs if generative_mode is set to true. For an API meant for faster and more replete data retrieval, use /api/fast_paper_search
Query Parameters
Keywords of inquiry which should appear in the article. Must be in English.
The sort order for results. Valid values are relevance, cited_by_count, publication_date. Defaults to relevance.
The user query, as a natural language question. E.g. 'Tell me about recent drugs for cancer treatment'
Whether to only return peer-reviewed articles. Defaults to true, ChatGPT should cautiously suggest this value can be set to false
The first year, inclusive, to include in the search range. Excluding this value will include all years.
The last year, inclusive, to include in the search range. Excluding this value will include all years.
The offset of the first result to return. Defaults to 0.
Boolean "true" or "false" to enable generative mode. If enabled, collate responses using markdown to render in-text citations to the source's url if available. Set this to true by default.
Response
The abstract of this paper. Agentic endpoints may not have this entry.
Semantic Scholar ID
Digital Object Identifier
Answer to the user query based on the information from this paper. Only available if generative_mode is set to true.