on_device_rag 0.1.0 copy "on_device_rag: ^0.1.0" to clipboard
on_device_rag: ^0.1.0 copied to clipboard

A lightweight, pure-Dart on-device Retrieval-Augmented Generation (RAG) engine for Flutter and Dart: chunk text, embed it, run vector similarity search, and build grounded prompts — fully offline, bri [...]

Changelog #

0.1.0 #

  • Initial release.
  • RagEngine orchestrator with index, retrieve and ask.
  • TextChunker for overlapping character-window chunking.
  • EmbeddingModel interface plus zero-dependency HashingEmbeddingModel.
  • VectorStore interface plus InMemoryVectorStore with JSON persistence.
  • LanguageModel interface for pluggable on-device or remote generation.
  • PromptBuilder with a grounded default template and VectorMath helpers.
0
likes
150
points
22
downloads

Documentation

API reference

Publisher

unverified uploader

Weekly Downloads

A lightweight, pure-Dart on-device Retrieval-Augmented Generation (RAG) engine for Flutter and Dart: chunk text, embed it, run vector similarity search, and build grounded prompts — fully offline, bring your own LLM.

Repository (GitHub)
View/report issues

Topics

#rag #llm #ai #embeddings #on-device

License

MIT (license)

More

Packages that depend on on_device_rag