Perplexity has launched an Internal Knowledge Search feature that allows Pro and Enterprise Pro users to search both their internal files and the web from a single platform. Users can upload important files, limited to 500 for Enterprise Pro, in various formats like Excel, Word, and PDFs, VentureBeat reports. The aim is to streamline the research process by focusing on valuable data rather than sifting through less relevant files. Early access clients, including Nvidia and Dell, have utilized this feature for tasks such as due diligence and proposal preparation.
Additionally, Perplexity introduced “Spaces,” enabling teams to share and organize research while maintaining control over data access. This feature excludes files from AI training by default, ensuring privacy. Future plans include integrating third-party data from services like Crunchbase and FactSet, enhancing the search capabilities further. Perplexity’s approach to retrieval augmented generation (RAG) allows users to leverage their internal data, competing with established platforms like Glean and Elastic.