{"slug": "show-hn-instant-local-ai-search-with-a-95-hit-rate-uses-perplexity-models", "title": "Show HN: Instant – Local AI search with a 95% hit rate (uses Perplexity models)", "summary": "A developer released Instant Search, a free local AI file search tool that uses Perplexity's latest embedding models and claims a 95% hit rate in finding the exact file and page matching a query. Instant Search relies on a bidirectional late-interaction embedding model rather than traditional RAG's single vector per body of text, and the developer says an average content library needs less than 1GB of disk space for indexing. The tool is positioned against Spotlight, which the developer describes as keyword-only search that does not understand file content.", "body_md": "Hi HN!\n\nInstant Search is the first accurate local AI file search that uses the latest embedding models from Perplexity to find the exact file (and page) with the content you’re looking for with a 95% hit rate.\n\nSearch never worked properly, especially with local files. Now, you can find the right image, document, or Obsidian file in seconds. Looking for your driver’s license? Just type “driver’s license”. Looking for a particular note? Just explain the context.\n\nWhy not Finder/Spotlight?\n\nSpotlight is just a keyword search. It doesn’t understand file content. Instant finds the exact file you’re describing in under a second.\n\nWhy not RAG?\n\nTraditional RAG models give you a single embedding vector per entire body of text. That means either you have a vector that’s not detailed enough to give you an accurate semantic representation, or it’s too precise and doesn’t contain enough surrounding context. Instant circumvents these problems by relying on a bidirectional late-interaction embedding model that works flawlessly.\n\nHow much space does indexing need? An average library of content needs less than 1GB of disk space.\n\nCheck it out, share with friends, and let me know your feedback! It's free.\n\nComments URL: [https://news.ycombinator.com/item?id=50213691](https://news.ycombinator.com/item?id=50213691)\n\nPoints: 2\n\n# Comments: 0", "url": "https://wpnews.pro/news/show-hn-instant-local-ai-search-with-a-95-hit-rate-uses-perplexity-models", "canonical_source": "https://useinstantsearch.com/", "published_at": "2026-10-23 18:52:34+00:00", "updated_at": "2026-10-23 19:13:22.162657+00:00", "lang": "en", "topics": ["ai-search", "ai-tools", "ai-products", "large-language-models", "artificial-intelligence"], "entities": ["Instant Search", "Perplexity", "Spotlight", "Obsidian", "Hacker News"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-instant-local-ai-search-with-a-95-hit-rate-uses-perplexity-models", "markdown": "https://wpnews.pro/news/show-hn-instant-local-ai-search-with-a-95-hit-rate-uses-perplexity-models.md", "text": "https://wpnews.pro/news/show-hn-instant-local-ai-search-with-a-95-hit-rate-uses-perplexity-models.txt", "jsonld": "https://wpnews.pro/news/show-hn-instant-local-ai-search-with-a-95-hit-rate-uses-perplexity-models.jsonld"}}