PubMed Paper Reader (pubmed/base.py)

llama-hub · scraping, Scraping / Crawling, pubmed, literature, search, api, retrieval

Fetches top scientific papers from PubMed based on a query and returns them as Document objects.

# Source: https://github.com/mperkins0155/llama-hub | License: MIT | Copyright Jerry Liu
# Provided via justclaw.it.com; keep this notice with the code.
"""Read Pubmed Papers."""
from typing import List, Optional

from llama_index.readers.base import BaseReader
from llama_index.readers.schema.base import Document


class PubmedReader(BaseReader):
    """Pubmed Reader.

    Gets a search query, return a list of Documents of the top corresponding scientific papers on Pubmed.
    """

    def load_data_bioc(
        self,
        search_query: str,
        max_results: Optional[int] = 10,
    ) -> List[Document]:
        """Search for a topic on Pubmed, fetch the text of the most relevant full-length papers.
        Uses the BoiC API, which has been down a lot.

        Args:
            sear

... (truncated -- full source via MCP)

See the full source, get the GitHub permalink, and search 40K more like it.

Get a free API key