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

EduMIND

EduMIND is a Python application and active-learning pipeline for code-mixed Vietnamese–English academic lectures. It transcribes speech with Whisper, measures code-switching, translates text while preserving technical terms, indexes PDF slides, and retrieves lecture material for question answering. Its Streamlit interface, Qdrant-backed RAG engine and Label Studio review workflow connect lecture processing with human

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

EduMIND — 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 EduMIND when a lecture workflow needs to connect bilingual speech transcription and slide retrieval, or when human-reviewed corrections should update the RAG knowledge pool.

Who it is for

  • Educators and researchers working with Vietnamese–English lectures and slide materials.
  • Developers building or adapting bilingual lecture-processing and retrieval workflows.
  • Teams that want human annotation to feed corrected text into a lecture knowledge base.

Documented uses

  • Transcribe Vietnamese–English code-mixed lecture audio.
  • Translate lecture text while retaining technical terminology.
  • Measure code-switching in academic speech.
  • Index PDF slides and retrieve relevant material for RAG answers.
  • Review transcription or other text and feed corrections into the indexed corpus.
Before you choose

Requirements & limits

The project repository is public and identifies the software as MIT-licensed. Its README documents local Python and Docker Compose setup.

  • The project is built around Vietnamese–English code-mixed academic content and includes a code-mixing measure.
  • The RAG workflow uses layout-aware PDF chunking and Qdrant, with hybrid search, keyword boosting and cross-encoder reranking described in the README.
  • Translation supports a rule-based provider and a Hugging Face sequence-to-sequence provider, with rule-based fallback documented for the latter.
  • The Label Studio workflow sends human corrections through a Flask backend to a corpus file and Qdrant re-indexing.
  • Local setup requires uv and environment-variable configuration; the README gives separate launch paths for Streamlit and the annotation stack.

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

Set up EduMIND locally

Prepare the Python environment and configure required environment values before launching the application.

Before you start

  • Python 3.10 project environment
  • The uv package manager
  • Repository checkout
  • Values needed for environment variables, such as LLM API keys

Steps

  1. Clone the repository and change into its project directory.

  2. Run the command below to create the .venv environment and install the package in editable mode.

    Documented command
    make requirements

  3. Copy .env.example to .env and fill in the required values.

Expected outcome

A configured local environment ready for the separately documented application launch step.

Guide limitations

  • This setup guide does not cover running the application or configuring a particular model provider.
  • The repository instructions do not guarantee compatibility with a specific machine.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
khang3004/Edu_Omni_MyMind · Official homepage title · retained in its source language
How we review sourcesSuggest a correction