A Smarter Way to Unlock Unstructured Data: SAS RAM in Action
16m + Hands-On Practice
Available in:
A Smarter Way to Unlock Unstructured Data: SAS RAM in Action
AIRAM : AIRAM1
Learn How To
- Build and automate end-to-end RAG pipelines, including data ingestion, organization, vectorization, evaluation, and automation.
- Load unstructured data (PDF, JSON, images, text, Word), organizing it into collections, and configuring embedding models and extraction tools.
- Evaluate pipeline configurations using manual and automated tests, interpret results, and select the best-performing setup.
- Interact with collections through a chat interface and create agents to automate querying and post-processing.
- Create agents for advanced data processing, automation, and integration.
- Set up workflow automation so that updates to sources trigger downstream processing and agent reinitialization, reducing manual effort.
Who Should Attend
- Technical Roles:
- AI/ML Engineers: Focused on configuring embedding models, integrating large language models (LLMs), optimizing vector databases, and automating workflows for efficient RAG pipeline operations.
- Application Developers: Those who build, extend, or integrate SAS RAM with other enterprise systems through APIs and automation tools.
- Business Roles:
- Business Analysts & Research Analysts: Although not strictly technical, these users interact with the system to streamline discovery of relevant enterprise information and validate outputs using built-in evaluation frameworks.
Prerequisites
Before attending this course, you should shoud have:
- Familiarity with Large Language Models (LLMs).
- Experience with Python.
- Basic Knowledge of Embedding Models and Vector Databases.
- Basic Data Processing and Workflow Automation skills.
SAS Products Covered
SAS Machine Learning;SAS Viya
Course Outline
Concepts and Introduction
- What Is Retrieval Augmented Generation?
- Introduction to SASRaportowanie w SAS Enterprise Guide i SAS Add-In for Microsoft Office; Retrieval Agent Manager
Configuration
- Configure LLMs and Vector Databases
Retrieve Source Data
- Use a custom script to query and download PDF files from arXiv, an open-access repository widely used for preprints in physics, computer science, and AI.
Configure a collection and vectorize the collection
- Vectorize the source documents.
- Store the embeddings in a vector database for efficient retrieval.
Evaluation Phase
- Create both user-driven and automated evaluations to validate the setup.
- Once the configuration meets quality standards, designate it as the Champion for production use.
Chat
- Start interacting with the Retrieval-Augmented Generation (RAG) system for contextual responses.
Agents
- Build an agent that leverages the curated collection. Chat with the agent.
Automation
- Implement automation for a change in the source.
Optional Practice: Code Generation