Skip to main content

LLM Summarizer

LLummarizer is a Python library that provides an interface to the OpenAI GPT-4 model for generating summaries from structured data. This library allows developers to easily integrate summarization capabilities into their applications.

Installation

You can install the LLM Summarizer library using pip:

pip install llummarizer

Usage

Here is a simple example of how to use the LLMSummarizer class:

from llummarizer import LLMSummarizer

# Create an instance of the summarizer
summarizer = LLMSummarizer()

# Define the data to summarize
data = {
    "first_name": "Lewis",
    "last_name": "Hamilton",
    "occupation": "Driver",
    "wins": 100,
    "points": 1000
}

# Optionally, define context and excluded keys
context = {
    "first_name": "Named after Olympic sprinter Carl Lewis",
    "occupation": "Formula 1 racing driver"
}
excluded_keys = ["email"]

# Generate the summary in English (default)
summary_en = summarizer.create_summary(data, context=context, excluded_keys=excluded_keys)

# Generate the summary in Spanish
summary_es = summarizer.create_summary(data, context=context, excluded_keys=excluded_keys, language="spanish")

print("English summary:", summary_en)
print("Spanish summary:", summary_es)

Features

  • Generate summaries from structured data
  • Customize summaries with additional context
  • Exclude specific keys from summarization
  • Support for multiple output languages
  • Powered by OpenAI's GPT-4 model

Requirements

  • Python 3.12 or higher
  • OpenAI API key (set as an environment variable OPENAI_API_KEY)

License

This project is licensed under the MIT License. See the LICENSE file for more details.

Metadata

Release files for llmarizer 0.0.1

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

Source distribution (sdist)

Source distribution for llmarizer 0.0.1
File Size Uploaded Provenance Actions
llmarizer-0.0.1.tar.gz 3.4 kB Without provenance Details for llmarizer-0.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for llmarizer 0.0.1
File Interpreter ABI Platform Actions
llmarizer-0.0.1-py3-none-any.whl Python 3 none any Details for llmarizer-0.0.1-py3-none-any.whl

Total release size: 6.7 kB

Release files / llmarizer-0.0.1.tar.gz

Download URL llmarizer-0.0.1.tar.gz
Size 3.4 kB
Tags Source
SHA-256 checksum
How to use checksums
3c22eda2498d3ebd78d8c8c95ba88108b074fef38daf2fdea2a74b6356f6cecc
BLAKE2b-256 checksum
How to use checksums
45ee1a1cc3e03aba1b3c1f6267b7c41ca115514b8718a963af73ad02113cf903
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.12.2

Release files / llmarizer-0.0.1-py3-none-any.whl

Download URL llmarizer-0.0.1-py3-none-any.whl
Size 3.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
154219adc154432a1d9d347956e0728768fbc0c712c6a0c59030c2b75fac79ba
BLAKE2b-256 checksum
How to use checksums
03a0d977c5e4c6bcccf42437eea7cd90d6bd46071df3078b2109ee8ea3321a1b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.12.2

Security for llmarizer 0.0.1

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.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.0.1 This release

2 release files No provenance

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