Vespa python API

Vespa is the scalable open-sourced serving engine to store, compute and rank big data at user serving time. pyvespa provides a python API to Vespa - use it to create, modify, deploy and interact with running Vespa instances. The main goal of the library is to allow for faster prototyping and get familiar with Vespa features.

Warning

pyvespa is under active development and backward incompatible changes may occur.

Hybrid Search - Quickstart is a good primer on how to create an application, feed data and run queries. See Examples for use cases. The following blog post series will get you started:

• Run search engine experiments in Vespa from python

• Build sentence/paragraph level QA application from python with Vespa

• Build a basic text search application from python with Vespa: Part 1

• Build a News recommendation app from python with Vespa: Part 1

The Vespa FAQ is a great resource, also see pyvespa troubleshooting.

Requirements

Install pyvespa:

  python3 -m pip install pyvespa

Install jupyter notebook to run the notebooks in a browser:

  git clone --depth 1 https://github.com/vespa-engine/pyvespa.git
  jupyter notebook --notebook-dir pyvespa/docs/sphinx/source

Many of the pyvespa guides / notebooks use Docker - minimum memory requirement is 4 Gb unless other documented:

  docker info | grep "Total Memory"
  or
  podman info | grep "memTotal"

One can also use Vespa Cloud to run the notebooks.