SID is a platform for building personalized AI applications. It allows you to always find the necessary context to anything your users are saying, enabling you to create truly magical experiences.

Imagine if ChatGPT was not just generally knowledgeable, but also knew everything about you - references to your documents, emails, and more - just like a personal assistant.

This is what SID enables you to build.


Because one of the key benefits of large language models is the ability to extract information from unstructured data (such as text), SID does not attempt to impose a specific data model on you.

Instead, most of the API is centered around text chunks, which are simply strings of text with some metadata attached to them. These are intended to be fed into a language model, which will then produce the final output.

Chunks are created by retrieving text from the various data sources that a user has configured. Read on for more details on how this works.

Query Endpoint

The main endpoint of the API is the /query endpoint. Given a query string, it retrieves text chunks whose content is relevant to the query. These can then be used to generate the final, personalized, output.

Where does the data actually come from?

Currently, SID exposes data from the following sources:

  • Google Drive
  • Notion
  • Gmail

With SID, our goal is to reduce the hassle of dealing with data sources as much as possible. To this end, you actually never have to deal with integrating the data sources directly - SID handles all of that behind the scenes.

Core to this is the concept of a SID account. With SID, each end user has their own SID account, just like they have their own Google account or Facebook account. Within their SID account, they can configure the data sources that they want to use, and SID will take of synchronizing these sources and creating an index of the data.

Then, when a user wishes to use your app, they will be asked to log in to their SID account, and your application will be authorized. This gives you access to SID’s API endpoints, such as the query endpoint, where you can retrieve the indexed data.

You can try out the experience by going to our demo app.

Why SID accounts?

There are two key benefits for using SID accounts, as opposed to a fully white-labeled solution:

For you, it means that you don’t have to go through the hassle of being verified by each data source individually. In the case of google drive and gmail, for instance, this process takes weeks and requires a detailed security review of your application.

For your users, if they already have a SID account, they can immediately get started with the full feature set of you application, without having to go through the hassle of setting up each data source individually.

What’s next?