Percolate
  • Percolate - AI in the data tier
  • Getting started
    • Quick start
    • Docker
      • Services
    • Kubernetes
    • Managed Cloud
    • Basic concepts
      • Database components
      • Core functions
        • Entities
      • Admin Api
  • Configure
    • Add language models
    • Add tools via APIs
    • Add agents
  • Going multimodal
    • Introduction
    • Querying
      • Graph
      • Vector
      • Key-value
      • Relational
    • Indexing
  • Recipes
    • Percolating Python-first
    • Percolating SQL-first
    • Percolate for SREs
    • No-code Percolate
    • Founder's DataRoom P8
    • Document Drafter P8
  • Concepts
    • Why put AI in the data tier?
Powered by GitBook
On this page
  • The Transaction
  • The Extended Dialogue
  1. Recipes

Percolating SQL-first

The real power of Percolate is its native SQL interface and rich integration with data and data governance. In this section we dive into the SQL functions that can be used to build agentic AI.

The basic unit in Percolate is a transaction where we ask a question and get a response that could include a tool call and tool evaluation. We will look at this transaction first.

After getting a feel for the atomic transactions, we can look into more complex sessions which can evolved a multitude of hops, queries and use of different tools and agents.

The Transaction

The Extended Dialogue

PreviousPercolating Python-firstNextPercolate for SREs

Last updated 2 months ago