Results for vector_embed

Text embedding and vector storage abstraction layer

Vector embedding projection engine for sphereQL

SIMD-accelerated vector operations and embedding generation

Local markdown semantic search with hybrid BM25+vector retrieval and LLM reranking

High-performance repository context generator for LLMs - Claude, GPT-4, Gemini optimized

High-performance repository context engine for LLMs - AST parsing, token counting, and secret detection

A minimal Rust library for creating sparse vector representations (embeddings) using the BM25 algorithm for information retrieval.

VecLite embedded vector database component

Knowledge graph embeddings with TransE, ComplEx, and custom models

Embedding providers (candle EmbeddingGemma, Ollama) for Lunaris

MCP server for AllSource Prime — unified agent memory engine (stdio transport)

Text embeddings with Candle. Fast and configurable. Use any model from Hugging Face. CUDA or CPU powered.