Multimodal in three ways:
Sync and search for both text and images.
Attach text documents and images, and use them to search.
Use AI language models with vision.
Semantic search:
Search based on deep semantic meaning (uses embedding models).
Lexical search:
Find a needle in a haystack using keywords (uses a BM25 algorithm).
Minimum Hardware Requirements:
OS: Windows 10 (Version 19041.0 or higher) or Windows 11
Memory (RAM): 8 GBÂ (16GB recommended)
Processor: Intel Core i5 (8th Gen) or AMD Ryzen 5 (2000 Series)
Storage: 2 GB available space
Features:
Supported files: .txt, .pdf, .docx, .png, .jpg, .jpeg, .gif, .webp
Works offline with downloaded models.
Optional AI Mode:
LLM Integration: Supports local models via LM Studio and cloud models, like GPT-5, via OpenAI.
Retrieval-Augmented Generation (RAG): Uses search results to provide high-quality AI responses rooted in the knowledge-base.
The AI Mode is entirely optional; a search can be run without AI.
Security and privacy: local search ensures no data is sent to the internet.