Generative AI¶
How to build, validate, and deploy generative AI applications using LLMs, vector databases, and moderation tools. This section covers creating LLM blueprints, managing chats and prompts, setting up vector databases for RAG (Retrieval-Augmented Generation), and implementing safety measures through moderation.
| Topic | Description |
|---|---|
| LLM blueprints | Create and manage LLM blueprints that define how large language models are configured and used in your applications. |
| Validate custom model LLMs | Validate deployments as custom model LLMs before using them in LLM blueprints. |
| Vector databases | Set up and manage vector databases for RAG (Retrieval-Augmented Generation) workflows. |
| Chats and prompting | Manage chat sessions and interact with LLMs through prompts, maintaining conversation history. |
| End-to-end RAG application workflow | A complete example of building a RAG application from scratch. |