IBM Watson Discovery

pip install pineflow-retrievers-watson-discovery
class WatsonDiscoveryRetriever

Provides functionality to interact with IBM Watson Discovery for querying documents.

For more information, see IBM Watson Discovery Getting Started.

Parameters:

  • url (str) – Watson Discovery instance URL.

  • api_key (str) – Watson Discovery API key.

  • project_id (str) – Watson Discovery project ID.

  • version (str, optional) – Watson Discovery API version. Defaults to 2023-03-31.

  • disable_passages (bool, optional) – Return the full document instead of passages. Only enable this if all documents are short. Defaults to False.

Example

from pineflow.retrievers.watson_discovery import WatsonDiscoveryRetriever

doc_retriever = WatsonDiscoveryRetriever(
    url="your_url", api_key="your_api_key", project_id="your_project_id"
)
search_documents(query, filter=None, top_k=4)

Search your data in the Discovery API and return a list of documents.

Parameters:

  • query (str) – Query text.

  • filter (str, optional) – Searches for documents that match the filter. Use Discovery Query Language syntax. Defaults to None.

  • top_k (int, optional) – Number of top results to return. Defaults to 4.

Example

docs = doc_retriever.query("What's Pineflow?")