GenAI Builder

Overview

SnapLogic’s GenAI Builder enables you to build Language Learning Models (LLM) powered custom co-pilots based on your use cases. Use this no-code solution to accelerate and automate your business workflows.

This article describes how to use GenAI Builder to build your AI application, which can be used to answer employees' HR-related queries, review legal documents, summarize companies' quarterly results, and more.

Prerequisites

  • Valid Amazon Bedrock Account, Azure OpenAI API Key Account, OpenAI API Key Account and Pinecone Account in SnapLogic.
  • GenAI Builder Snaps:
    • Amazon Bedrock LLM Snap Pack: Integrates with Amazon's foundation models (FMs) within the SnapLogic platform. It enables you to integrate Amazon Bedrock's FMs from diverse sources via a unified API for tasks such as prompt generation, chat completions, and embedding.
    • Azure OpenAI LLM Snap Pack: Integrates OpenAI's language learning models (LLM) with Azure OpenAI Service. It enables you to incorporate advanced language models for tasks like embedding, chat completions, and prompt generation.
    • HTML Utilities Snap Pack: Enables you to transform the HTML content into text and Markdown. You can also leverage this Snap Pack to convert Markdown content into text.
    • LLM Utilities Snap Pack: Includes utilities that improve working with text for LLM processing capabilities.
    • OpenAI LLM Snap Pack: Integrates with OpenAI's language learning models (LLM) within the SnapLogic Platform. It enables you to incorporate advanced language models for tasks such as embedding, chat completions, and prompt generation.
    • Pinecone Snap Pack: Integrates with Pinecone's cloud-native vector database that simplifies the integration of long-term memory into high-performance AI applications. It enables you to use it's straightforward API and eliminates infrastructure complexities.
  • Access to the SnapLogic Public Pattern Library either on the Global control plane or the EMEA control plane

Summary steps

  1. Configure your Amazon Bedrock Account, Azure OpenAI API Key Account, OpenAI API Key Account, and Pinecone Account in SnapLogic.
  2. Launch the Indexer and Retriever pattern pipelines from the Public Pattern Library.
  3. Modify the Snap Settings of the pattern pipelines' based on your requirements.
  4. Validate and test the pipelines.
  5. Launch the chat interface and prompt.