Snowflake Introduces Snowflake Cortex To Empower Developers And Analysts With Generative AI Tools


Snowflake, the leading cloud-based data storage platform, has unveiled Snowflake Cortex, a fully managed service aimed at simplifying the use of generative AI applications on the Snowflake platform. The launch of Snowflake Cortex aims to cater to both business users and developers by providing them with tools to work seamlessly with AI technology.

Key Takeaway

Snowflake Cortex, the newly introduced fully managed service, empowers both business analysts and developers to work with AI applications more efficiently on the Snowflake platform. With features like Document AI, universal search, and Snowflake Copilot, Snowflake Cortex streamlines data interaction, query building, and application development, providing users with greater productivity and control over their data.

Enhancing Data Interaction with Snowflake Cortex

For business analysts, Snowflake Cortex offers access to a range of AI tools, specifically designed on Snowflake’s custom large language models (LLMs), to facilitate faster and more efficient interaction with the data stored in Snowflake. This empowers analysts to work with advanced features, such as advanced search capabilities and large language models, directly within the Snowflake platform, enabling them to enhance their productivity significantly.

Developers, on the other hand, can leverage Snowflake Cortex to build generative AI applications on top of the data stored in Snowflake. This capability is built on the foundation of the Streamlit acquisition, which Snowflake made in the previous year.

The Key Components of Snowflake Cortex

One of the integral components of Snowflake Cortex is Document AI. This tool facilitates the extraction and querying of data from unstructured documents, such as PDFs and analyst reports. With Document AI, analysts without programming or specialized knowledge can easily derive structured information from these unstructured documents and organize them into tables. This allows analysts to ask meaningful questions and derive insights from the unstructured data stored within these documents.

Another significant feature introduced with Snowflake Cortex is universal search, powered by the acquisition of Neeva. This search functionality enables users to search across all data stored in Snowflake, including the Snowflake marketplace, making it easier to locate specific data or applications built within the platform.

Snowflake Copilot, the third key feature offered by Cortex, streamlines data querying for analysts. By converting plain language questions about the data stored in Snowflake into SQL queries, Snowflake Copilot eliminates the need for analysts to spend time familiarizing themselves with the data and column structure to build meaningful queries.

Development Capabilities and Future Roadmap

Developers using Snowflake Cortex can capitalize on Snowflake models to quickly build applications. Additionally, for those seeking more control over the development process, Snowflake Cortex allows for the integration of external LLMs, including open-source offerings and those provided by cloud partners like Amazon Bedrock and Azure OpenAI. Snowflake Container Services, introduced in June, further facilitate the efficient deployment of these applications as containerized workloads.

Snowflake Cortex is part of a broader initiative by Snowflake to unlock the full potential of the data stored within its platform. Whether through search, querying, or application development, Snowflake aims to enable users to leverage their data in various ways. Although Snowflake Cortex and its core features are currently in private preview, the company has not disclosed a timeline for wider availability.

Leave a Reply

Your email address will not be published. Required fields are marked *