# Data Retrieval

Exa Websets is a product dedicated to delivering a flawless web search experience. It employs Exa's web-scale vector search technology, ensuring that each search result is researched and validated by AI agents to guarantee accuracy. Users can simply write their queries in plain English without the need for complex filters or confusing interfaces. Exa Websets is suitable for sales, recruiting, investing, research, and curiosity-driven exploration, serving as an AI-driven custom data retrieval tool for knowledge workers.

PromptQL is an AI-designed agent data access tool that retrieves data like a human by first gathering relevant information and then applying appropriate large language models (LLMs) for classification and follow-up processing, significantly improving the efficiency and accuracy of private data retrieval. This technology addresses the limitations of traditional search algorithms in closed domains, particularly when users submit non-standardized queries, allowing PromptQL to better understand and respond. The product background indicates that PromptQL aims to closely collaborate with users to build the first agent for free to assess and enhance the performance of existing AI agents/assistants.

DataGemma RIG is a series of fine-tuned Gemma 2 models aimed at helping large language models (LLMs) access and integrate reliable public statistical data from Data Commons. This model employs a retrieval-based generation approach, annotating statistical data in responses through natural language queries to Data Commons' existing natural language interface. Trained on TPUv5e using JAX, DataGemma RIG is currently in the early stages and is intended primarily for academic and research purposes; it is not yet ready for commercial or public use.

MemoRAG is a memory-based RAG framework that supports a variety of applications through an efficient ultra-long memory model. Unlike traditional RAG, MemoRAG utilizes its memory model to achieve a global understanding of the entire dataset, enhancing evidence retrieval by recalling specific cues from memory, thereby generating more accurate and context-rich responses. The development of MemoRAG is active, with resources and prototypes constantly being released in this repository.

Verba is an open-source application designed to provide an end-to-end, seamless, and user-friendly retrieval-augmented generation (RAG) interface. It combines cutting-edge RAG techniques with Weaviate's context-aware database, supporting both local and cloud deployments, making it easy to explore datasets and extract insights.