OpenAI has recently announced the launch of a new feature on ChatGPT web that allows users to search through their chat history. This feature, developed by Rockset, enables users to easily access previous conversations and reference past discussions or continue where they left off. The company has also acquired Rockset, a data analytics company, for $105 million, with the aim of leveraging their advanced analytics to enhance OpenAI’s retrieval infrastructure.
According to former Rockset chief Dhruba Borthakur, the ability to search through chat history requires real-time indexing and hybrid searches, making Rockset the perfect database to power this feature. The company is also collaborating with OpenAI to tackle the complex database challenges faced by AI applications at scale.
Rockset’s retrieval augmented generation (RAG) feature enhances the capabilities of large language models (LLMs), making it valuable for OpenAI’s enterprise customers who want to utilize models with their proprietary data and reduce hallucination risks. By incorporating their data, customers can improve LLMs to deliver more contextual and accurate results, expanding the applications of LLMs in content generation and information retrieval.
Rockset employs a converged indexing approach that combines row, columnar, and search indexes, enabling fast searches across multiple data types and formats. This is a unique service that is not offered by other database companies such as MongoDB, Elasticsearch, or Amazon Redshift. Additionally, Rockset’s hybrid vector search combines traditional keyword search with vector search, providing more relevant and context-aware results. This is particularly beneficial for OpenAI, which manages vast volumes of unstructured data.
Rockset’s fully managed, serverless architecture eliminates the need for manual infrastructure management, allowing OpenAI to scale its operations seamlessly and efficiently. This approach reduces operational overhead and simplifies scalability, making it easier for OpenAI to manage its vast amounts of data.
In conclusion, OpenAI’s new chat history search feature, powered by Rockset’s advanced analytics, will greatly enhance the user experience on ChatGPT web. This collaboration between the two companies will also help OpenAI tackle the complex database challenges faced by AI applications at scale, making it a valuable addition to their portfolio.
