OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Radient

Radient is a Python library for generating embeddings from text and other data, and composing vectorization and retrieval workflows for embedding-based search. Its examples cover audio, graphs, images and molecules as well as text.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Radient — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Radient when building Python-based embedding generation or vector-centric data pipelines; its documented Workflow example connects Google Drive documents through text extraction and Voyage AI vectorization to MongoDB storage.

Who it is for

  • Python developers preparing data for similarity search or retrieval-augmented generation.
  • Teams assembling vector-centric ETL pipelines from data sources, transformations, vectorizers and storage sinks.

Documented uses

  • Convert text into embeddings with a selected vectorization method and model.
  • Generate vectors from audio, graphs, images or molecules using the corresponding vectorizers.
  • Compose source-to-sink workflows that transform data, create embeddings and persist vectors.
  • Optimize supported vectorizers on the fly with the accelerate function.
Before you choose

Requirements & limits

The repository is public and identifies the project as open source under the BSD-2-Clause license. The documented installation command is `pip install radient`.

  • Radient handles embedding generation and retrieval-pipeline composition; its README explicitly excludes LLM connectors.
  • The default text vectorizer uses Sentence Transformers and prompts to install that dependency if missing.
  • Workflow components can include sources, transforms, vectorizers and sinks; the README gives Google Drive, Voyage AI and MongoDB as an example.
  • The README lists Sentence Transformers, ImageBind, TorchAudio, RDKit, scikit-learn and ONNX among the supporting ecosystem.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Create a text embedding with the default vectorizer

Install Radient and vectorize a short text string using its documented default model.

Before you start

  • Python environment with Radient installed using pip.
  • Sentence Transformers; if absent, Radient prompts to install it.

Steps

  1. Install Radient with the command below.

    Documented command
    pip install radient

  2. Import text_vectorizer from radient and create a vectorizer with vz = text_vectorizer().

  3. Call vz.vectorize("Hello, world!") to produce a vector.

Expected outcome

A vector representation of the input text, using the documented default model bge-small-en-v1.5 from Sentence Transformers.

Guide limitations

  • The guide covers text vectorization only; it does not set up a retrieval workflow or storage.
  • The default vectorizer depends on Sentence Transformers, which may need to be installed after Radient prompts.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
fzliu/radient · Official homepage title · retained in its source language
How we review sourcesSuggest a correction