เริ่มต้นใช้งานเริ่มต้นใช้งานได้ฟรี

หน้าแรก
คอร์ส
Generative AI Essentials with Snowflake

Introduction to AI Functions and AI_COMPLETE

Create Your Free Account

or

Email Address

Password

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.

แบบฝึกหัดนี้เป็นส่วนหนึ่งของหลักสูตร

Generative AI Essentials with Snowflake

SkillTag.level.intermediateSkillTag.label

4.7+

เริ่มคอร์สฟรี

Get started with generative AI on Snowflake. You'll set up your environment, work in Snowflake Notebooks, and build a simple AI app that summarizes customer call transcripts as JSON and displays the results in Streamlit.

Exercise 1: Navigating the Generative AI Revolution with Snowflake Exercise 2: What we'll cover in this course Exercise 3: How to successfully complete this course Exercise 4: Preparing your development environment Exercise 5: Download the Snowflake Notebook for the simple AI app Exercise 6: Build a simple AI app in Snowflake Exercise 7: Chapter 1 review - Question 1 Exercise 8: Chapter 1 review - Question 2

Explore Snowflake Cortex AI functions for common AI tasks. You'll prompt models with AI_COMPLETE, use task-specific and helper functions, try newer functions for filtering, aggregating, redacting, embeddings, and image inputs, and bring it together in a Streamlit app.

Exercise 1: Course Introduction Exercise 2: Setting up your environment Exercise 3: Note: Update to LLM Functions Exercise 4: Introduction to AI Functions and AI_COMPLETE

แบบฝึกหัดปัจจุบัน

Exercise 5: Snowflake Services Consumption Table Exercise 6: Task-specific LLM functions & Helper functions Exercise 7: Using the AI_COMPLETE function Exercise 8: Using task-specific Cortex LLM functions Exercise 9: Using Helper Functions Exercise 10: Additional Cortex AI Functions: Overview Exercise 11: Additional Cortex AI Functions: Hands-on Demo Exercise 12: Reading: AI_PARSE_DOCUMENT and AI_SUMMARIZE_AGG Exercise 13: Multimodal AI: Images as Inputs Exercise 14: Vector Embeddings with AI_EMBED and AI_SIMILARITY Exercise 15: Download source code for the Streamlit app Exercise 16: Getting ready to put it all together: Build a Streamlit app Exercise 17: Module recap Exercise 18: Chapter 2 review - Question 1 Exercise 19: Chapter 2 review - Question 2 Exercise 20: Chapter 2 review - Question 3 Exercise 21: Chapter 2 review - Question 4 Exercise 22: Chapter 2 review - Question 5 Exercise 23: Chapter 2 review - Question 6

Customize LLM responses with Cortex Fine-Tuning. You'll learn how parameter- efficient fine-tuning keeps costs low, prepare training data, fine-tune Mistral-7b to respond in a specific style, test your model, and build a Streamlit app that drafts custom emails and text messages.

Exercise 1: What is Cortex Fine-tuning?Exercise 2: Setting up your environment Exercise 3: Cross-Region Inference for Standard Models Exercise 4: Setting up your environment Exercise 5: Analyzing Customer Support Tickets Exercise 6: Preparing your Training Data Exercise 7: Starting the fine-tuning job Exercise 8: Inference using fine-tuned model Exercise 9: Download source code for the Streamlit app Exercise 10: Streamlit application to auto-generate custom emails and text messages Exercise 11: Module recap Exercise 12: Continue your Generative AI education Exercise 13: Chapter 3 review - Question 1 Exercise 14: Chapter 3 review - Question 2 Exercise 15: Chapter 3 review - Question 3 Exercise 16: Chapter 3 review - Question 4 Exercise 17: Chapter 3 review - Question 5 Exercise 18: Chapter 3 review - Question 6 Exercise 19: Chapter 3 review - Question 7 Exercise 20: Chapter 3 review - Question 8 Exercise 21: Chapter 3 review - Question 9