Operand API Documentation

Operand is the missing knowledge layer for large language models. Index anything and get semantic search, question answering and more, all built in <20 lines of code using our battle-tested infrastructure.

Getting Started

The best resource to get started with the Operand API. Learn how to create your first index, upsert your first documents, and perform search operations. This can be done via REST, or using one of our official SDKs.

Augmenting Language Models with Knowledge

Use Operand search results to augment GPT-3 style prompts with additional, context-relevant knowledge. Help your pre-trained language models learn and get better over time, without having to do any additional training.

Object Types

All of the "things" you can index with Operand. For example, an HTML webpage, PDF, EPUB, or even a podcast.

Index Best Practices

A guide on managing your indexes, and keeping them up to date with your database. This article also includes tips on keeping indexes organized and optimized for the best possible performance.


Learn how to use Operand to build multi-tenant applications, i.e. a per-user index of knowledge. Keep data logically seperated, to ensure users are only seeing knowledge belonging to them.


Learn how to use filters to search over a subset of an index, based on specific properties of the indexed objects.