@jerryjliu0: Real question: what is the actual latest state-of-the-art for file search and retrieval? - Actual grep over filesystem …
Summary
Jerry Liu asks about the current state-of-the-art for file search and retrieval, listing options from grep to hybrid search over a database.
View Cached Full Text
Cached at: 05/19/26, 12:39 AM
Real question: what is the actual latest state-of-the-art for file search and retrieval?
- Actual grep over filesystem
- Virtualized grep / BM25 over a db (what @mintlify did)
- Vector search over a db
- Hybrid search over a db
- SQL
- none of the above
- some of the above?
Similar Articles
@jerryjliu0: There’s an open question on whether grep is all you need for agentic search. This recent paper by @PwCUS (Sen et al.) s…
Recent paper investigates whether grep outperforms vector search for agentic retrieval, finding grep yields higher accuracy in conversational memory tests, but limitations around enterprise document corpora are noted.
@omarsar0: // Is Grep All You Need? // Pay attention to this on, AI devs. (bookmark it) They find that grep-style text search, whe…
A research paper from PwC finds that grep-style text search, when properly integrated into agent harnesses, can match or beat embedding-based retrieval for coding-agent tasks, suggesting vector databases may not be essential for many use cases.
@garrytan: Lots of retrieval systems seem to give you keyword matching and graph retrieval in a raw format This plus graph travers…
Garry Tan highlights a retrieval system that uniquely combines keyword matching, graph traversal, and gap analysis, an approach not seen elsewhere.
@FinanceYF5: Ten years ago, search relied on keywords; five years ago, semantics; today, Google directly stuffs its strongest AI into the search box. Driven by Gemini 3.5, it supports cross-modal queries with images, videos, and files, merging AI Overviews and AI Mode into one. Search has truly changed this time!
Google integrates Gemini 3.5 AI into the search box, supporting multi-modal queries with images, videos, and files, and merges AI Overviews and AI Mode, bringing a major transformation to the search experience.
dmtrKovalenko/fff
fff is a fast, typo-resistant file search toolkit with frecency ranking and an MCP server for AI agents, providing efficient file and content search with git awareness.