Skip to main content

precis-summary

Fast extractive summarization via RAKE keyword extraction. Zero dependencies.

Usage

from precis_summary import telegram_precis, pick_best_summary

# RAKE keyword extraction (~5ms, zero deps)
text = "Metal-organic frameworks exhibit high CO2 adsorption capacity..."
precis = telegram_precis(text)
# → "Metal-organic frameworks; high CO2 adsorption capacity; ..."

# Pick best summary from a multi-profile dict
summaries = {
    "rake": "Metal-organic frameworks; high CO2 adsorption",
    "llm:qwen3.5:9b": "MOFs show 3x CO2 uptake vs zeolites; amine-functionalized variants optimal",
}
best = pick_best_summary(summaries)
# → "MOFs show 3x CO2 uptake vs zeolites; amine-functionalized variants optimal"

Summary ranking

pick_best_summary() uses prefix-priority matching:

  1. llm:* — any LLM-generated summary (best quality)
  2. rake — extractive RAKE keyphrases (instant, always available)
  3. Fallback — first non-empty value

Ranking lives in code, not in the data. New summary methods are added by extending SUMMARY_PRIORITY in ranking.py.

Metadata

Release files for precis-summary 0.2.3

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

Source distribution (sdist)

Source distribution for precis-summary 0.2.3
File Size Uploaded Provenance
precis_summary-0.2.3.tar.gz 10.0 kB With provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for precis-summary 0.2.3
File Interpreter ABI Platform
precis_summary-0.2.3-py3-none-any.whl Python 3 none any Details

Total release size: 16.4 kB

Release files / precis_summary-0.2.3.tar.gz

Download URL precis_summary-0.2.3.tar.gz
Size 10.0 kB
Tags Source
SHA-256 checksum
How to use checksums
73009e7e930dfe6f345a5076520dd8d0b868303bd30ebce0a16b812a44b7f832
BLAKE2b-256 checksum
How to use checksums
b981d7f1acf8dc7c09d92c5c2406913550b995f9efae6eb021887f366804cd4d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 7, 2026.

Transparency log

Release files / precis_summary-0.2.3-py3-none-any.whl

Download URL precis_summary-0.2.3-py3-none-any.whl
Size 6.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
ddbfee288beac06194e2dbc1bf2c6a9cb515f7115bac76ac500c60da66ad643b
BLAKE2b-256 checksum
How to use checksums
fa26251e486357566ed45b4e418f2cce76774a29e56f7e1ce9c984ab6749ee34
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.12.9

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 7, 2026.

Transparency log

Security for precis-summary 0.2.3

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.

Full provenance

All 2 files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for precis_summary-0.2.3.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Apr 7, 2026.

Transparency log

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.

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