NLMatics developed a question answering, semantic search, and data extraction pipeline that utilizes layout-aware chunking, vector and BM25 indexing, and language models. This technology, which bears similarities to RAG (Retrieval-Augmented Generation), was created between 2020 and 2023. The company's open-source codebase is available on GitHub, with packages released under Apache 2.0 and MIT licenses. NLMatics' technology found early adoption in sectors such as financial services, legal services, and life sciences, indicating its versatility and practical applications across various industries.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.