Pubmed

Search PubMed for articles with PubmedTools’ search_pubmed function, returning expanded article detail when results_expanded is set.

PubmedTools enable an Agent to search PubMed for articles.

Prerequisites

The following example requires the openai library.

uv pip install -U openai

Example

The following agent will search PubMed for articles related to “ulcerative colitis”.

cookbook/91_tools/pubmed_tools.py

from agno.agent import Agent
from agno.tools.pubmed import PubmedTools

agent = Agent(tools=[PubmedTools()])
agent.print_response("Tell me about ulcerative colitis.")

Toolkit Params

Parameter	Type	Default	Description
email	str	"[e-mail]"	Specifies the email address to use.
max_results	Optional[int]	None	Optional parameter to specify the maximum number of results to return.
results_expanded	bool	False	Return expanded article details including author, journal, DOI, URLs, keywords, and MeSH terms.
enable_search_pubmed	bool	True	Enable the search_pubmed functionality.
all	bool	False	Enable all functionality.

Toolkit Functions

Function	Description
search_pubmed	Searches PubMed for articles based on a specified query. Parameters include query for the search term and max_results for the maximum number of results to return (default is 10). Returns a JSON string containing the search results, including publication date, title, and summary.

Developer Resources

• Tools