DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to search a book by meaning with a local vector index with Modureader

Build a semantic index for one book so AI answers can pull the passages that match a question.

Authorization notice. Modureader is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA reader with a long nonfiction book who wants to find where an idea is discussed, even when the exact words differ.

The problemKeyword search misses passages that express the same idea in different words.

The outcomeThe book has a local index, and semantic search returns related original passages that can feed AI answers.

What you need first

  • A device on a supported platform: Windows, Linux, Android, macOS, iOS (ARM64 real device, iOS 16+) or HarmonyOS, with the installer from the Releases page
  • Local reading needs no AI account. AI, online translation and online voice need their own provider settings and may cost money
  • For sync: your own WebDAV server
  • For vector search: a few hundred MB of disk space is not stated in the README, so check model sizes in the settings before downloading

Steps

  1. Open 设置 → 向量模型 (Settings → vector model) and pick a local ONNX model, such as BGE Small ZH v1.5 for Chinese text, or a remote embedding API.
  2. Download the model and tokenizer, or import the matching version offline, and wait for the size and SHA-256 check to pass.
  3. Open the book's menu and build the index.
  4. Check the background queue for progress until indexing finishes.
  5. Run a semantic search and compare the results against the book text.

Prompt for your agent

Using the sobranie2406/modureader repo, configure the local BGE Small ZH v1.5 model in Modu Reader and build a vector index for <book title>. Report the indexing status, then list two results from a semantic query on <topic> and confirm each one appears in the book.

Caveat. The README says the index stays on the device and is not synced by WebDAV, and changing the vector model requires rebuilding the index.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page