Quickstart
==========

Python API
----------

Use :func:`evidence_fetcher.fetch_evidence` to retrieve normalized
:class:`evidence_fetcher.Evidence` results:

.. code-block:: python

   from evidence_fetcher import fetch_evidence

   results = fetch_evidence("retrieval augmented generation evaluation")

   for evidence in results:
       print(evidence.title)
       print(evidence.url)
       print(evidence.snippet)

CLI
---

Readable text output:

.. code-block:: console

   evidence-fetcher "retrieval augmented generation evaluation"

JSON output:

.. code-block:: console

   evidence-fetcher "retrieval augmented generation evaluation" --format json

Use ``--limit`` to control the maximum number of results.

Streamlit UI
------------

Launch the Streamlit review app:

.. code-block:: console

   evidence-fetcher-ui

The UI uses the same Brave-backed retrieval, local reranking, relevance
feedback, and explicit expansion workflow as the CLI.

For a step-by-step walkthrough, see :doc:`ui`.