Overview of AI features

The Data Productivity Cloud incorporates the power of generative AI and large language models (LLMs) in several ways.

Remember to check out our What's New blog to read about new features (including generative AI) regularly entering the Data Productivity Cloud. This blog is released once per week and rounds up our changelog.

---

Copilot

With Copilot, you can create data pipelines simply using plain language instructions, taking advantage of advanced AI technology. Copilot accompanies you throughout your data pipeline journey, offering help at every step.

Copilot is available in public preview while we gather feedback and continue to enhance your data pipeline assistant.

Note

• Currently, Copilot is only available for Snowflake projects.
• Currently, Copilot is only available for transformation pipelines.

Read these pages to get started:

• Copilot overview
• Copilot prerequisites
• Start using Copilot

---

Prompt components

Prompt components use a large language model (LLM) to provide responses to user-composed prompts. The components take inputs from a source table, combine the inputs with user prompts, and send this data to the LLM for processing.

These prompt components are currently available in the Data Productivity Cloud:

• OpenAI Prompt
• Azure OpenAI Prompt
• Amazon Bedrock Prompt

---

Vector database components

The Data Productivity Cloud can connect to your Pinecone vector database using the following components:

• Pinecone Vector Upsert converts data stored in your cloud data warehouse into embeddings, and then stores these embeddings as vectors in your Pinecone vector database.
• Pinecone Vector Query ingests text search strings and returns text data associated with similar vectors in your Pinecone vector database.

---

Automatic documentation generation with AI notes

Documenting your pipelines with on-canvas notes lets you provide other users with information on the purpose of the pipelines. The AI Note feature takes the effort out of documenting a pipeline yourself by using generative AI to analyze the pipeline's features and write appropriate notes automatically. You can regenerate notes, extend notes, and shorten notes.