nomic-ai/nomic

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1878 stars · 196 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

The official Python client for Nomic Atlas, a platform for exploring, labeling, searching, and sharing massive unstructured datasets (text, image, audio, video) in the browser. It lets you generate, store, and retrieve embeddings and build interactive dataset maps from Python.

Use cases

• generate and store embeddings for unstructured text or image data
• visualize and explore millions of data points in an interactive map
• find duplicate or near-duplicate items in a large dataset
• build topic models over a corpus of documents
• run semantic search over my own dataset
• label and curate datasets collaboratively in the browser
• share dataset insights with teammates via a web link

When to choose

• you need to explore, cluster, or curate large unstructured datasets visually
• you want hosted embedding generation and semantic search without managing infrastructure
• you need shareable interactive dataset maps for text, image, audio, or video data

When to avoid

• you need fully offline or self-hosted embedding and dataset tooling
• you only need a local embedding model without a hosted platform
• your data cannot be uploaded to a third-party cloud service

Facets

library · maturity active

machine-learning search-engine data-visualization sdk nlp machine-learning data-science data-visualization developer-tools python embeddings topic-modeling clustering unstructured-data dataset-exploration duplicate-detection atlas natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nomic-ai/nomic")