Skip to main content

Documentation Index

Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt

Use this file to discover all available pages before exploring further.

Lucidworks offers the option to execute generative AI (Gen-AI) models using an API key managed and provided by Lucidworks. Your organization can purchase the Lucidworks-managed API keys option to run Gen-AI use cases associated with the Prediction API and Async Prediction API.
You would not generate API credentials using the Authentication API.

​
Benefits

Using Lucidworks-managed API keys when running Gen-AI models provides the following benefits to your organization:
  • Faster time to market
    • Eliminates configuration time for third-party API credentials and authentication infrastructure.
    • Reduces deployment complexity and allows your teams to focus on business goals rather than managing integrations.
    • Decreases the time to test models and roll out the configuration to Production.
  • Reduced business operational costs
    • Lowers the administrative cost of managing multiple vendor relationships, billing accounts, and API key lifecycles across specific Gen-AI models such as OpenAI, Anthropic, Google, and Azure.
    • Provides a single contract relationship with Lucidworks for this feature instead of individual contracts with multiple large language model (LLM) providers.
    • Simplifies and reduces the number of integration points to maintain, update, and secure.
  • Predictable and transparent costs
    • Provides a bundled, fixed-pricing model instead of unpredictable per-token usage costs from third-party APIs.
    • Simplifies budget forecasting and minimizes vendor invoices.
  • Reduced technical risk Decreases complexity and failure points with a single integration instead of multiple API connections.
  • Resource optimization Requires less specialized knowledge of LLM APIs because they are managed by Lucidworks.

​
Configure Fusion stages

One option your organization can adopt is to use the functions available in Fusion stages. While Lucidworks sets up the majority of this feature, your organization needs to configure the following stages:
  1. Create a dedicated index pipeline, add a LWAI Prediction index stage and enter the values provided by Lucidworks in the Use Case and Model fields based on the use cases and models to which your organization is entitled. Because Lucidworks provides the API key, you will not enter information in the API Key field.
  2. Create a dedicated query pipeline, add a LWAI Prediction query stage and enter the values provided by Lucidworks in the Use Case and Model fields based on the use cases and models to which your organization is entitled. Because Lucidworks provides the API key, you will not enter information in the API Key field.
LWAI Prediction index stage

​
Lucidworks Platform capabilities feature

With the Lucidworks Platform capabilities functions, Lucidworks manages the complete lifecycle of GenAI model execution, supporting multiple providers such as OpenAI, Azure, Google Vertex, and Anthropic. Lucidworks Platform handles all infrastructure, API key management, and model routing through the Lucidworks AI Gateway, which eliminates the need for your organization to manage your GPU resources or model hosting. Lucidworks ensures your data is secure and that it is never used to train external models.