Direct Access LLMs

Overview

Datasaur offers Direct Access LLMs, a new feature that allows users to instantly access and call the most popular Large Language Models (LLMs) within the platform. This feature eliminates the need for complex API key setup and multi-cloud configurations. Additionally, users can cut wait lines and immediately access the latest state of the art models.

Supported Providers

Datasaur's Direct Access LLM feature currently supports Azure, OpenAI, Amazon Bedrock and Google Vertex, each offering a unique set of LLM models. Below, we'll delve into the details of each provider and the models they offer.

Azure OpenAI

With Azure OpenAI, users can utilize the following models:

  • gpt-35-turbo: A fast and efficient model ideal for applications requiring rapid response times.

  • gpt-35-turbo-16k: A variant of the gpt-35-turbo model, with greater capacity to handle longer inputs.

  • gpt-4: A powerful model offering advanced language understanding and generation capabilities.

  • gpt-4-32k: A variant of the gpt-4 model, with greater capacity to handle longer inputs.

  • gpt-4 turbo: A high-performance model optimized for speed and efficiency.

OpenAI

With OpenAI, users can utilize the following model:

  • GPT-4o: A highly advanced model offering exceptional language understanding and generation capabilities.

Amazon Bedrock

With Amazon Bedrock, Datasaur is able to provide several Open Source Models, such as:

  • Meta Llama 3 8b Instruct: A newer model optimized for instruction-following tasks, offering high accuracy and reliability.

  • Meta Llama 3 70b Instruct: A variant of the Meta Llama 3 8b Instruct model, with increased capacity and performance.

  • Meta Llama 2 Chat 13B: A highly advanced model designed for conversational AI applications.

  • Meta Llama 2 Chat 70B: A variant of the Meta Llama 2 Chat 13B model, with increased capacity and performance.

There will be additional models that will be provided from Amazon Bedrock in the coming months, including Mixtral and Claude 3.

Vertex AI

With Vertex AI, users can utilize the following models:

  • Gemini 1.0 Pro: A highly advanced model offering exceptional language understanding and generation capabilities.

  • Gemini 1.5 Flash: A variant of the Gemini 1.0 Pro model, optimized for speed and efficiency.

  • Gemini 1.5 Pro: A high-performance model offering advanced language understanding and generation capabilities.

Getting Started with Direct Access LLM

To get started with Direct Access LLM, simply navigate to the Datasaur LLM Labs platform and create a new LLM Playground.

Once the LLM Playground is created, you just have to choose your desired provider by clicking the models button.

Last updated