Skip to main content

AI support for fusion experiments - feature extraction, embeddings, and natural language data analysis

Project description

nucleai

AI Support for Fusion Experiments

nucleai is a codegen-first library designed to empower fusion research with advanced AI capabilities. It provides a comprehensive workflow for extracting features from fusion data, generating rich descriptions, and creating vector embeddings for both feature images and text.

Key Features

  • Natural Language Interface: Ask questions about data and test hypotheses using natural language.
  • Data Search & Retrieval: Advanced search capabilities using text and feature shapes.
  • Analysis & Display: Automated analysis and visualization of experimental data.
  • Feature Extraction: Automated extraction of significant features from experimental fusion data.
  • Vector Embeddings: Generation of embeddings for feature images and text descriptions to enable semantic understanding.
  • Codegen-First Design: Built to be driven by AI agents and code generation tools, allowing users to request complex, novel plots and processing pipelines on demand.

Getting Started

(Instructions for installation and usage will be added here)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nucleai-0.0.1.tar.gz (5.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

nucleai-0.0.1-py3-none-any.whl (2.3 kB view details)

Uploaded Python 3

File details

Details for the file nucleai-0.0.1.tar.gz.

File metadata

  • Download URL: nucleai-0.0.1.tar.gz
  • Upload date:
  • Size: 5.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for nucleai-0.0.1.tar.gz
Algorithm Hash digest
SHA256 50a4b7814e2a8165db1bf3b6e2f7f1386b9213c40fa57d97093f9aecd02f92c4
MD5 70313e565f03becdc51e5ededfbe519d
BLAKE2b-256 9105dd79314d8d9db308b12f79b85b6e5566c65fcd7f7a3ef119356462164326

See more details on using hashes here.

Provenance

The following attestation bundles were made for nucleai-0.0.1.tar.gz:

Publisher: publish.yml on iterorganization/nucleai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file nucleai-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: nucleai-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 2.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for nucleai-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 31f323b8e8792bd7a7824494468dd737dae519af66e31ce86bf761cf8bb5cf65
MD5 5cb00b1e1b1b19f5aec2ab9db5c68534
BLAKE2b-256 8426502300a607ca1bfdc05316d95823496caf12311eafb3db2340eb53a88cff

See more details on using hashes here.

Provenance

The following attestation bundles were made for nucleai-0.0.1-py3-none-any.whl:

Publisher: publish.yml on iterorganization/nucleai

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page