llmreference
Salesforce Einstein Generative AI

Using GPT-3.5 Turbo 16k on Salesforce Einstein Generative AI

Implementation guide · GPT-3.5 · OpenAI

Serverless

Quick Start

  1. 1
    Create an account at Salesforce Einstein Generative AI and generate an API key.
  2. 2
    Use the Salesforce Einstein Generative AI SDK or REST API to call gpt-3.5-turbo-16k — see the documentation for request format.

Code Examples

About Salesforce Einstein Generative AI

Salesforce Einstein Generative AI is a comprehensive artificial intelligence platform designed to enhance customer interactions and streamline business processes. At its core, the platform leverages advanced Large Language Models (LLMs) to generate personalized content, such as sales emails and customer service replies. This capability allows users to save time while maintaining high-quality engagement with clients. The platform also includes innovative tools like the Prompt Builder and Skills Builder, which enable users to create custom prompts and workflows tailored to their specific business needs, thereby improving operational efficiency. Beyond content generation, the platform harnesses real-time customer data to deliver actionable insights, enhancing decision-making across various departments. It automates case classifications, generates knowledge articles, and provides next-best-action recommendations based on historical data. This not only improves response times but also personalizes customer experiences. The Einstein Trust Layer ensures data security and compliance, allowing organizations to confidently utilize AI while protecting sensitive information. Through intelligent automation and personalized engagement, the platform empowers businesses to optimize their operations and significantly enhance customer satisfaction.

Salesforce offers a comprehensive AI platform integrated into its customer relationship management (CRM) ecosystem. Their AI capabilities are primarily focused on enhancing customer interactions, automating business processes, and providing intelligent insights. The platform leverages data from various sources to power personalized recommendations, real-time decision-making, and journey automation. Salesforce's AI solutions are designed to help businesses exceed customer expectations by delivering highly personalized experiences across all touchpoints. The company emphasizes the use of AI in conjunction with their Data Cloud to enable seamless activation of customer data for improved engagement and business outcomes.

Pricing on Salesforce Einstein Generative AI

Capabilities

Structured Outputs

About GPT-3.5 Turbo 16k

GPT-3.5 Turbo 16k, developed by OpenAI, is an advanced language model featuring a significantly enhanced context window of 16,384 tokens—four times larger than its predecessor's 4,096 tokens 245. This extension allows it to process and comprehend extended texts, up to approximately 20 pages, in a single interaction, while maintaining the speed and efficiency of earlier versions 10. Although it is a chat-centric model not compatible with the completions endpoint 8, it remains highly effective for tasks requiring prolonged relevance and coherence through OpenAI's API 46. With a knowledge cutoff in September 2021, it surpasses its predecessors in capability, yet it is less advanced than GPT-4 in visual and multilingual contexts 35.

Model Specs

Released2023-06-13
Parameters20B
Context16K
ArchitectureDecoder Only
Knowledge cutoff2021-09

Provider

Salesforce Einstein Generative AI
Salesforce Einstein Generative AI

Salesforce

San Francisco, California, United States