Multimodal ingest
PDFs, Word, PowerPoint, images, audio, video, and text. All in one shared library you can chat over.
Chat with everything
you’ve ever uploaded.
Multimodal RAG over text, PDFs, Word, PowerPoint, images, audio, and video, with a live knowledge graph and grounded, cited answers.
Vision + OCR
Every image is turned into searchable text and a short description of what is shown.
Audio transcription
Meetings and voice notes become citable text you can chat with.
Knowledge graph
Entities and relationships pulled from your docs, visualized and used to ground answers.