Skip to main content

LLM plugin for comprehensive research using Jina AI's Search Foundation APIs

Project description

llm-jina-research

PyPI Changelog License

LLM plugin for comprehensive research using Jina AI's Search Foundation APIs

Installation

Install this plugin in the same environment as LLM:

llm install llm-jina-research

Set your Jina AI API key:

export JINA_API_KEY="your_api_key_here"

Get your Jina AI API key for free: https://jina.ai/?sui=apikey

Usage

Perform comprehensive research using Jina AI's APIs:

llm research "What are the latest advancements in AI safety?"

Options:

  • query: The research question to investigate
  • --output: Path to save results as JSON file

Features

  • 🔍 Web search with relevance filtering
  • 📥 Advanced content extraction with reader API
  • 🧬 Query embedding generation
  • 🔬 Document reranking based on relevance
  • 📊 Interactive terminal report generation
  • 📄 JSON output for programmatic use
  • 📝 Automatic research session logging

Example

llm research "What are the latest advancements in AI safety?" --output results.json

This will:

  1. Search the web for relevant information
  2. Extract and process content from top results
  3. Analyze and rank the content
  4. Generate an interactive report
  5. Save the results to a JSON file

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd llm-jina-research
python -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

pip install -e '.[test]'

To run the tests:

pytest

Contributing

Contributions to llm-jina-research are welcome! Please refer to the GitHub repository for more information on how to contribute.

License

This project is licensed under the Apache License 2.0. See the LICENSE file for details.

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

llm_researcher-0.1.0.tar.gz (5.7 kB view details)

Uploaded Source

Built Distribution

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

llm_researcher-0.1.0-py3-none-any.whl (6.1 kB view details)

Uploaded Python 3

File details

Details for the file llm_researcher-0.1.0.tar.gz.

File metadata

  • Download URL: llm_researcher-0.1.0.tar.gz
  • Upload date:
  • Size: 5.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.7

File hashes

Hashes for llm_researcher-0.1.0.tar.gz
Algorithm Hash digest
SHA256 080fcfa5ba5b16f3aa55f98a3a69c6092a2c89fdc0f26da67436398fa3ba9d9f
MD5 ceb62b78fb6c4b51876cdc9589372454
BLAKE2b-256 c39eb3d7240efe1ee158679fcf237a2c92675cb6dbd6f5a31dbeb95c09ac020f

See more details on using hashes here.

File details

Details for the file llm_researcher-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: llm_researcher-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 6.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.7

File hashes

Hashes for llm_researcher-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c07b9321eeb7baaee8bac6bad56481bb0bc7dbb315c195e5946b7ec585be060e
MD5 107b3e4627150bc03816d7987ffc5e65
BLAKE2b-256 bda1c6e0d6a9d756ec60235a7935eafec0bc6ea3167957553b031119e3e0633e

See more details on using hashes here.

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