Azure OpenAI LLM Snap Pack

Overview

The Azure OpenAI LLM integrates OpenAI's Large Language Models (LLM) with Azure OpenAI Service. It allows you to incorporate advanced language models, including GPT-4, GPT-4 Turbo with Vision, GPT-3.5-Turbo, and Embeddings, for tasks like embedding, chat completions, and prompt generation in SnapLogic workflows. This Snap Pack has the following Snaps:
  • Add Message: Adds a user message to an existing thread, enabling the continuous build-up of context or questions for AI assistance.
  • Azure OpenAI Chat Completions: Generates chat completions using the specified model and model parameters.
  • Azure OpenAI Embedder: Generates an embedding vector based on the provided input data.
  • Azure OpenAI Prompt Generator: Generates the augmented user prompt as per the specified prompt template using mustache template format.
  • Azure OpenAI Prompt Generator: Generates the augmented user prompt as per the specified prompt template using mustache template format.
  • Azure OpenAI Function Generator: Generates a function definition that can be used for tool calling in the chat completions endpoint.
  • Azure OpenAI Function Result Generator: Formats and structures the function results that are utilized by the Azure OpenAI.
  • Azure OpenAI Tool Calling: Formats the function result generated by the OpenAI Tool Calling Snap.
  • Create Thread: Creates a new thread based on the provided input data, allowing users to append prompts and build context for AI processing.
  • Run Thread: Executes the specified thread and retrieves the AI-generated response based on the accumulated context and prompts.
This Snap Pack includes the following key features:
  • Supports integration with Azure OpenAI Service. It provides REST API access to GPT-4, GPT-4 Turbo with Vision, GPT-3.5-Turbo, and Embeddings models.
  • Supports tasks like embedding, chat completions, and prompt generation for enhanced language processing.
  • Supports advanced response configurations that enable you to customize response behavior through detailed settings, allowing for precise tuning of outputs based on your specific needs and scenarios.