With artificial intelligence taking the world by storm, unconventional approaches are expected to push AI adoption beyond the evaluation phase.

While large language models seem to work magic with consumer-ready summary blogs, data authenticity has much higher stakes when it comes to generative application development. To this end Snowflake Inc. devised a technique called Retrieval Augmented Generation for believable outcomes, according to Sridhar Ramaswamy (pictured), senior vice president at Snowflake and co-founder of Neeva Inc., which was acquired by Snowflake in May.

“We pioneered a technique called RAG, Retrieval Augmented Generation, or you can just think of that as smart search, that you need to use in conjunction with the language model in order to produce believable output,” Ramaswamy explained. “We want to have that index that can set the context for a language model to always produce believable, authentic information.”

Ramaswamy spoke with theCUBE industry analyst Dave Vellante at Supercloud 4, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. They discussed how Snowflake is jumping on the AI bandwagon by making outputs believable through RAG and the importance of data and language models.

Language models are changing the stakes in the enterprise world

Based on language models’ proficiency and efficiency, Snowflake is boosting its adoption rate through structured query language, according to Ramaswamy. This comes in handy in making data practitioners’ lives easier because language models are revolutionizing the business landscape.

“A really important part of language models is literally what the two words say, which is their proficiency with language … in terms of efficiency, they’re pretty amazing,” he said. “What we are going to do as part of the Snowflake platform is, not just host a set of models, but we are going to make it easily accessible in SQL, which means that the thousands of data analysts … have access to language models in the SQL that they write, without needing to deal with GPUs, deal with APIs.”

Open-source language models are changing the dynamics in the AI field. This is a notable transformation because it has provided a lot of impetus to the ecosystem, which looked like it would only have a handful of players, such as OpenAI and Anthropic, according to Ramaswamy.

“The rise of open-source language models and the role that Meta is increasingly playing in the language model space,” he pointed out. “We have a great partnership with Meta, but of course, we are also pre-training our own models. I think this sort of rise in open source and the democratization of AI models is an important development.”

With AI being a cutting-edge technology in the modern era, Snowflake is moving a notch higher by integrating a set of AI capabilities into its platform. This includes vector indexing and running language models, Ramaswamy pointed out.

“The core technology of AI is that it’s a natural language, you can speak to it, you can write things and it can extract the structured information that is underneath and surface it to you,” he said. “We are also integrating the Neeva Search technology, which is a combination of old-school information retrieval plus vector indexing natively into Snowflake so that you’re able to just, with a single command, index a table.”

Combining SQL and Streamlit for better data access

To democratize access to the structured data sitting in Snowflake, innovations, such as merging SQL and the Streamlit app are of the essence, according to Ramaswamy. This creates fluid access to data needed for better decision-making.

“Our take is that combining SQL and Streamlit to write interesting applications, people are going to come up with some crazy stuff that will be incredibly valuable … I think the first wave is going to come early next year,” he said. We are also creating a Copilot experience that builds on top of the inferencing platform and the vector indexing so that when you can talk to it in English, it writes the SQL queries and then you can click a button and have that run.”

When it comes to data, creating value and making the outcomes believable are of the essence. As a result, Snowflake is geared toward this objective by incorporating the necessary parameters, Ramaswamy pointed out.

“How exactly is access control going to work?” he asked. “This is why, with the things that we are implementing, we make sure that governance and security are right in there from the very beginning. We actually have applications where people can feel like, ‘OK, only the people that are supposed to look at some data are actually allowed to look at that data.’”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of Supercloud 4:

Photo: SiliconANGLE