Obnews Digital Desk. OpenAI has announced the launch of a new feature that allows users to search their chat history on the ChatGPT web. This enables users to access past conversations quickly and easily, making it easy to reference past discussions or pick up where they left off. This feature was developed by Rocketsat.
What is rocket?
OpenAI recently acquired Rockset, a data analytics company founded in 2016 by former meta engineers Dhruba Borthakur and Venkat Venkataramani for $105 million (INR 905 crore). The acquisition aims to leverage Rockset's advanced analytics to enhance OpenAI's recovery infrastructure.
“We just introduced the ability to search all your past chat history in ChatGPT,” said former Rockset chief Borthakur. “This requires real-time indexing and hybrid searches to find the most relevant matches, and what better database than Rockset?” Rockset is working closely with OpenAI to tackle the complex database challenges that AI applications face at scale.
Also read: You can ask any question you want on Google Play Store, every answer will be given by AI
The company highlighted this
“We will help OpenAI solve the complex database challenges that AI applications face at scale,” the company said. Rockset extends the capabilities of large language models (LLM) through its Retrieval Augmented Generation (RAG) feature. This integration will be valuable to OpenAI's enterprise customers who want to use models with their proprietary data and reduce the risk of confusion. By incorporating their data, customers can enhance LLM to deliver more relevant and accurate results, thereby expanding the applications of LLM in content creation and information retrieval.
Rockset uses this approach
Rockset uses a converged indexing approach that combines row, column, and search sequences, enabling fast searches across multiple data types and formats. Currently, no other database companies, such as MongoDB, Elasticsearch or Amazon Redshift, provide this specific service. While Elasticsearch excels at keyword searching and alternatives like Weaviate and Pinecone specialize in vector searching, Rockset combines these capabilities to provide accurate keyword matching with semantically rich search results. Its hybrid vector search combines traditional keyword search with vector search, producing more relevant and context-aware results. This is particularly beneficial for OpenAI, which handles vast amounts of unstructured data, including text, images, and audio.
Also read: Looting on the last day of Flipkart sale, goods will be available at half rate
Unlike some solutions that require complex infrastructure management, Rockset offers a fully managed, serverless architecture that reduces operational overhead and simplifies scalability. This approach eliminates the need for manual infrastructure management, allowing OpenAI to scale its operations seamlessly and efficiently.
Comments are closed.