Utilora

Local Vector Embeddings Tester (ONNX)

Compute cosine similarity locally using an ONNX embedding pipeline. Zero delays.

How to use

  1. 1

    Wait for Model

    Locally downloads the 23MB all-MiniLM-L6-v2 model on first test.

  2. 2

    Type Documents

    Enter two sentences or words in the containers.

  3. 3

    Compute Similarity

    See how vector-identical their contextual definitions are.

Why use this tool?

  • Runs huggingface pipeline entirely via Web Workers
  • No backend server required

Frequently asked questions

Is it really running locally?
Yes! Using WebAssembly and Xenova's transformers port, the inference operates purely on device CPU/GPU.

Related tools

RAG Document Chunking Preview

Simulate and test text chunking algorithms and overlap characters instantly.

LLM Agent Trace Visualizer

Paste agent trace logs in standard formats - LangChain LCEL, AutoGen messages, or any JSON array with role/type/content fields

Popular right now

JSON Formatter & Validator

Format, validate, and minify JSON instantly in your browser. Your data never leaves your device.

JWT Decoder

Decode JWT tokens and inspect header and payload instantly in your browser. Your tokens never leave your device.

Word Counter

Count words, characters, sentences, and estimate reading time instantly in your browser. No sign-up required.