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

Wikipedia Semantic Search

Wikipedia Semantic Search is an open-source TypeScript application and example of semantic search and retrieval-augmented chat over Wikipedia articles. It uses multilingual embeddings and Upstash Vector for search, Upstash Redis for chat sessions, and QStash LLM APIs for language generation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Wikipedia Semantic Search — 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 the live demo to explore the documented Wikipedia search and chat experience; use the repository when you need an implementation example for multilingual vector search or RAG over an indexed knowledge base.

Who it is for

  • People exploring semantic search and question answering over Wikipedia.
  • Developers studying or adapting a multilingual vector-search and RAG application.
  • Teams considering a document-ingestion pipeline that embeds and indexes content by language.

Documented uses

  • Find relevant Wikipedia articles through semantic rather than exact-word matching.
  • Search across languages using multilingual embeddings.
  • Ask questions through a chatbot grounded in indexed Wikipedia content.
  • Study how article preparation, embedding, vector indexing, chat-session storage, and LLM requests fit together.
Before you choose

Requirements & limits

The repository is public and reports an MIT license. The README links to a live demo and documents local development through Upstash Vector, Redis, and QStash credentials.

  • The documented example uses BGE-M3 for multilingual embeddings and language-specific Vector namespaces.
  • Vector search, chat-session storage, embedding generation, and LLM requests use separate components: Upstash Vector, Upstash Redis, SentenceTransformers, and QStash LLM APIs.
  • The README describes an index of more than 144 million Wikipedia vectors across 11 languages.
  • Adapting the Wikipedia pipeline to another corpus may require changes to data preparation and ingestion code.

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

Prepare the documented local development setup

Configure the required Upstash services and start the project's development server.

Before you start

  • An Upstash Vector database with embedding-model support.
  • An Upstash Redis database for chat sessions.
  • QStash credentials for hosted LLM requests.
  • pnpm and the project's code.

Steps

  1. Create the Vector and Redis databases in the Upstash Console and copy their credentials, along with QStash credentials.

  2. Add the Vector, Redis, and QStash values to a root-level .env file using the variable names shown in the README.

  3. Populate the Vector index, placing vectors in the namespace for their language; the README gives en for English.

  4. Run pnpm install, then pnpm dev.

Expected outcome

The documented service configuration, populated index, installed dependencies, and development-server start sequence are in place.

Guide limitations

  • The guide documents setup stages but does not establish a successful run or deployment.
  • The README does not give the article-ingestion procedure in this setup section.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Wikipedia Semantic SearchFind relevant Wikipedia articles through semantic rather than exact-word matching.Cloud, WebThe repository is public and reports an MIT license. The README links to a live demo and documents local development through Upstash Vector, Redis, and QStash credentials.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

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