Generate local dense text embeddings with ONNX Runtime for semantic search.
npx skills add https://github.com/antonyfmunoz/OS --skill fastembed
Please help me install this Agent Skill. Skill: fastembed Source: https://github.com/antonyfmunoz/OS/tree/main/skills/tools/fastembed Command: npx skills add https://github.com/antonyfmunoz/OS --skill fastembed
This Skill solves slow, dependency-heavy embedding generation by providing a lightweight way to convert text into vectors locally for semantic search and matching.
Real-world example: You maintain a catalog of skills and notes inside your system, and you want an AI to automatically select the most relevant skill or retrieve the most similar past interactions based on a user’s task description.
Use the fastembed tool to embed your task description and compare it against pre-embedded skill vectors for semantic retrieval.
High-intent search queries and answers about installing and using this skill.
You can generate local text embeddings without a GPU by using CPU-optimized ONNX Runtime to convert input text into dense vectors. This approach supports batch processing and configurable parallelism for semantic search and knowledge retrieval workflows.
The best way to embed thousands of documents locally is using batch processing with configurable batch size and parallelism. This method efficiently converts large text volumes into fixed-size vectors for similarity comparison without heavy dependencies.
Yes, you can use CPU-optimized vectorization for pgvector skill matching by generating dense vector embeddings locally. You must ensure consistent model dimensions when storing and comparing vectors in your database for accurate retrieval.
Query vs document embedding for asymmetric retrieval works by converting both query text and document text into fixed-size vectors. These vectors are then compared using similarity metrics to retrieve the most relevant documents for a given query.
No, you do not need cloud APIs to run vectorization for knowledge retrieval pipelines. You can generate dense vectors entirely locally using ONNX Runtime, with optional cloud and keyword fallbacks to maintain retrieval continuity if embedding generation fails.
AG064Convert input text to speech offline using sherpa-onnx runtime.
eddieluengProvides scalable cloud-based vector search and storage for AI applications.
ccfCombine vector similarity with keyword matching for hybrid retrieval.
SriRamkunamsettyPerform fast similarity search over large-scale dense vectors with FAISS index types.
