Semantic Search

A TypeScript walkthrough demo showing how to build semantic search over a CSV dataset using the Pinecone vector database and a sentence-transformers embedding model.

Visit website github.com

Semantic Search is a demo application that shows how to use Pinecone for semantic search over a CSV dataset of articles. It has two main components: a data loader that reads the CSV file with papaparse, converts each row into an article object, and loads it into a Pinecone index, and a search engine that queries that index and returns similar results.

Both components share an embedder module that turns natural-language strings into embeddings using the sentence-transformers/all-MiniLM-L6-v2 model. Running it requires Node.js 22.12 or later and a Pinecone API key, index name, cloud, and region supplied through a local environment file.

It is written in TypeScript and released under the MIT license.

More in Databases

See all 294

SQLBraid
clickin.github.io
A SQL-first data-access toolkit for TypeScript that keeps ordinary SQL visible in tagged template literals, binds interpolated values safely by default, supports readable conditional SQL directives, and lets a schema validate the returned rows.
- Libraries
- Databases
QQL - SQL for Qdrant and vector search
qql.veristamp.in
A SQL-style query language and toolchain for the Qdrant vector database, covering dense, sparse and hybrid search, filtering and multitenancy, with the same grammar running from a CLI, Python, Node.js, Rust, WebAssembly and an in-process edge engine.
- Databases
Fast Knowledge
github.com
A self-hosted, Java-based knowledge base for small and mid-sized organizations, turning internal documents into a searchable, question-answerable and audit-exportable knowledge asset with hybrid retrieval and Docker deployment.
- RAG
- Databases

More in Databases

SQLBraid

QQL - SQL for Qdrant and vector search

Fast Knowledge

Cookies