Skip to main content

llm-jina Plugin

LLM Plugin for Jina AI: Powerful AI-powered interactions across multiple domains.

Overview

The llm-jina plugin integrates Jina AI services with Simon Willison's llm CLI tool, providing a comprehensive set of AI-powered capabilities directly accessible from the command line.

Features

  • Web Search - Search the web with options for domain filtering
  • URL Content Reading - Extract and process content from URLs
  • Fact Checking - Verify the factual accuracy of statements
  • Text Embeddings - Generate vector embeddings for text analysis
  • Document Reranking - Reorder documents based on relevance to a query
  • Text Segmentation - Split text into manageable chunks
  • Classification - Categorize text or images into specified labels
  • Metaprompt Access - Access Jina's metaprompt system

Installation

pip install llm-jina
# or
llm install llm-jina

Configuration

Set your Jina AI API key:

export JINA_API_KEY=your_api_key_here

You can get a Jina AI API key from jina.ai.

Usage Examples

Search

llm jina search "AI technology trends"
llm jina search "machine learning papers" --site arxiv.org
llm jina search "news today" --links --images

Read URL

llm jina read https://example.com/article
llm jina read https://blog.jina.ai --links
llm jina read https://docs.python.org/3/ --format markdown

Embed Text

llm jina embed "Your text here"
llm jina embed "Compare similarity using embeddings" --model jina-embeddings-v3

Rerank Documents

llm jina rerank "machine learning" "Document about NLP" "Paper on computer vision" "Article about ML"

Segment Text

llm jina segment "Long text to be split into chunks" --return-chunks

Classify

llm jina classify "I love this product!" --labels positive,negative,neutral
llm jina classify --image cat.jpg dog.jpg --labels cat,dog

Ground (Fact Checking)

llm jina ground "The Earth orbits the Sun" --sites nasa.gov,space.com

Metaprompt

llm jina metaprompt

Contributing

Contributions welcome! Please read the contributing guidelines.

Testing

Run the test suite:

pip install -e ".[dev]"
pytest

License

Apache 2.0

Metadata

Release files for llm-jina 0.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llm-jina 0.3.0
File Size Uploaded Provenance
llm_jina-0.3.0.tar.gz 16.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for llm-jina 0.3.0
File Interpreter ABI Platform
llm_jina-0.3.0-py3-none-any.whl Python 3 none any Details

Total release size: 37.8 kB

Release files / llm_jina-0.3.0.tar.gz

Download URL llm_jina-0.3.0.tar.gz
Size 16.6 kB
Tags Source
SHA-256 checksum
How to use checksums
2436ea069d63dae9d122e02ad411fef7f47483d3cf46fdf75f77574707d1eb12
BLAKE2b-256 checksum
How to use checksums
a4855cf5cb7c445fde6e8e5ca4b0f3e60679da78c6e5148606d8b818902019b3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.2

Release files / llm_jina-0.3.0-py3-none-any.whl

Download URL llm_jina-0.3.0-py3-none-any.whl
Size 21.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5d9f266ede04f83e177418cfeed7b3c43251a7fd17c026fcf49ba0a0758c50c9
BLAKE2b-256 checksum
How to use checksums
82fe47eaa3050c3670ad09db11b6992d1a1db27f8cd7a7647eebfc2c251cb98f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.2

Security for llm-jina 0.3.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page