Kinetica Integrates ChatGPT for “Conversational Querying”
Kinetica, an analytical database provider for spatial, time-series, and temporal data, has integrated with OpenAI’s ChatGPT for “conversational querying." This integration enables enterprise users to use natural language prompts to query their data assets, rather than writing complex SQL queries. This move from Kinetica is aimed at making its product more intuitive and accessible for end customers.
Through the integration, enterprise users can ask questions about their data on Kinetica’s workbench UI, regardless of whether the query is simple or unknown. The ChatGPT interface powered by GPT-3.5 turbo then converts the question into SQL and runs the query to provide insights.
Kinetica’s CEO and co-founder, Nima Negahban, stated that the system maintains anonymity to ensure the user’s data is secure. “Kinetica automatically hydrates the GPT-3 context in an anonymized fashion with the necessary prompts and rules derived from the database metadata. This allows the GPT model to generate the correct SQL query, given a user’s data model and question, without exposing the underlying detailed data to GPT."
Enhancing the Feature
Kinetica plans to enhance its conversational querying feature using GPT-4 integration and make it more widely available to enterprises. The company plans to launch a programmatic SQL API to open this capability to be used by other developers in their analytics applications and is exploring other areas where it can benefit from large language models.
Other enterprise technology vendors, such as Salesforce, Microsoft, ThoughtSpot, Domo and SiSense, have started leveraging LLMs into their products, furthering competition and innovation in this area.
