NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
pub.dev
pub.dev
Flutter plugin for on-device AI inference with MediaPipe RAG.
Latest stable
0.0.1
Last release 1 years ago
31 Oct 2025
Too new to tell
only 1 dated releases
Nearly every release is documented
notes for 1 of 1 stable releases
Nothing withdrawn
no release was ever pulled
1 years old
1 releases · first in 2025
chore: update ai_edge_model_dl version in example lock files by @KyoheiG3 in https://github.com/KyoheiG3/ai_edge/pull/17
Full Changelog: https://github.com/KyoheiG3/ai_edge/compare/ai_edge_model_dl_v0.1.0...ai_edge_rag-v0.0.1
RAG Support: Complete implementation of Retrieval Augmented Generation capabilities
Embedding Models: Support for both local and cloud-based embeddings
Vector Storage: Flexible storage options for embeddings
Document Processing: Comprehensive text chunking capabilities
memorizeChunk, memorizeChunks)Streaming Responses: Real-time text generation
partialResultCustomizable Retrieval: Fine-tuned context retrieval
topK for number of retrieved chunksminSimilarityScore threshold for relevance filteringCore classes and methods:
AiEdgeRag - Main entry pointcreateEmbeddingModel() - Local embedding model setupcreateGeminiEmbedder() - Gemini API embedder setupmemorizeChunk() - Single chunk storagememorizeChunks() - Batch chunk storagememorizeChunkedText() - Automatic text chunking and storagesetSystemInstruction() - RAG behavior configurationgenerateResponseAsync() - Context-aware streaming generationEmbeddingModelConfig - Local embedding configurationGeminiEmbedderConfig - Gemini API configurationSystemInstruction - RAG system instructionVectorStore - Storage type enum (inMemory, sqlite)EmbeddingModelType - Model type enum (gemma, gecko)Your coding agent can read these notes before it upgrades. Set up the MCP server →
One column per month.