Skip to main content
from compressor.semantic import compress_text, find_needle_in_haystack

text = """
Akin to France's heartier, spicier, richer boeuf bourguignon, "alcatra" is synonymous with a single island in the remote Azores archipelago.  The Azores, an archipelago of nine islands belonging to Portugal and located roughly between Europe and the US, are cow country. They're said to be home to more cattle than people, and despite being home to less than 3% of Portugal's population, the islands produce 30% of Portugal's dairy products and 13% of its beef.   Beef is part of everyday life in the Azores, and come spring on one particular island, the ingredient even crosses paths with religion.   In the days following Easter, Azorean people kick off a series of religious celebrations called Festas do Espírito Santo (Festivals of the Holy Spirit). During the 13th Century, a Catholic sect called the Cult of the Holy Spirit predicted a utopian era on Earth. This fringe faith was discouraged in mainland Europe but lived on in these remote islands in the middle of the Atlantic Ocean. The sect was also promoted by Portuguese queen Elizabeth of Aragon (also known as Elizabeth of Portugal), who was known for her charity.  Over the subsequent centuries, a series of festivals emerged on the Azores that blended these utopian aspirations with the queen's alleged generosity. Between Easter and the week following Whitsunday, a total of eight weeks, the islands host a series of parades and other cultural and religious festivals that revolve around brightly coloured community houses called impérios. During this time, the community houses also collect donations from locals, which is then redistributed to people in the form of bread, beef and wine.  These three elements generally come together in the form of a soup, called sopa do Espírito Santo, that's served at the impérios during the festivals. But on the island of Terceira, locals combine these ingredients in a different and delicious way, one that's become synonymous with the island's culinary identity.  Austin Bush The Festas do Espírito Santo revolve around community houses called impérios (Credit: Austin Bush)Austin Bush The Festas do Espírito Santo revolve around community houses called impérios (Credit: Austin Bush) "People eat alcatra year round, but especially during the celebrations in spring and summer," explains Duarte Fournier. He is the Grand Master of the Brotherhood of Alcatra, a culinary fraternity on Terceira, and is telling me about the island's signature dish: cuts of beef braised in local wine, smoked pork fat and dried spices, resulting in something of a heartier, spicier, richer version of France's famed boeuf bourguignon.  We're sitting at a cafe in Angra do Heroísmo, Terceira's largest city, and as we chat, children race to and from a nearby império delivering massive trays of raw beef to neighbours. Fournier tells me that alcatra likely has its origins in northern Portugal, where there's a tradition of baking goat in wine.  "We don't know why it's called alcatra," he says. "We suppose it's from Arabic. Al catar means 'small pieces of meat'."  According to Fournier, alcatra differs from mainland Portugal's baked meat dishes in that it includes dried spices, generally allspice and black peppercorns, but also sometimes clove or cinnamon.
""".strip()

compressed_text_90_percent = compress_text(text, compression_rate=0.9)
print(compressed_text_90_percent)
# "He is the Grand Master of the Brotherhood of Alcatra, a culinary fraternity on Terceira, and is telling me about the island's signature dish: cuts of beef braised in local wine, smoked pork fat and dried spices, resulting in something of a heartier, spicier, richer version of France's famed boeuf bourguignon."

compressed_text_to_100_tokens = compress_text(text, target_token_count=100)
print(compressed_text_to_100_tokens)
# 'Akin to France\'s heartier, spicier, richer boeuf bourguignon, "alcatra" is synonymous with a single island in the remote Azores archipelago.'

text_reference = "Archipelago Islands"
compressed_text_with_steering = compress_text(text, compression_rate=0.7, reference_text_steering=text_reference)
# 'Akin to france\'s heartier, spicier, richer boeuf bourguignon, "alcatra" is synonymous with a single island in the remote azores archipelago. The azores, an archipelago of nine islands belonging to portugal and located roughly between europe and the us, are cow country. Beef is part of everyday life in the azores, and come spring on one particular island, the ingredient even crosses paths with religion. But on the island of terceira, locals combine these ingredients in a different and delicious way, one that\'s become synonymous with the island\'s culinary identity. He is the grand master of the brotherhood of alcatra, a culinary fraternity on terceira, and is telling me about the island\'s signature dish: cuts of beef braised in local wine, smoked pork fat and dried spices, resulting in something of a heartier, spicier, richer version of france\'s famed boeuf bourguignon.'

needle_in_haystack = find_needle_in_haystack(
    haystack = text,
    needle = "Archipelago Islands",
    block_size = 200
)
# 'Akin to France\'s heartier, spicier, richer boeuf bourguignon, "alcatra" is synonymous with a single island in the remote Azores archipelago.  The Azores, an archipelago of nine islands belonging to Portugal and located roughly between Europe and the US, are cow country. They\'re said to be home to more cattle than people, and despite being home to less than 3% of Portugal\'s population, the islands'

Metadata

Release files for semantic-compressor 2.43

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

Source distribution (sdist)

Source distribution for semantic-compressor 2.43
File Size Uploaded Provenance
semantic_compressor-2.43.tar.gz 50.4 MB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for semantic-compressor 2.43
File Interpreter ABI Platform
semantic_compressor-2.43-py3-none-any.whl Python 3 none any Details

Total release size: 101.0 MB

Release files / semantic_compressor-2.43.tar.gz

Download URL semantic_compressor-2.43.tar.gz
Size 50.4 MB
Tags Source
SHA-256 checksum
How to use checksums
23327120d4e6ae408f9a2dfebcd7d82dbf3b77990c4f08e499e85e158a540254
BLAKE2b-256 checksum
How to use checksums
20d232f539eb4d4e6e1471b433fa53bf49504314c03711a595963519313b088d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.11

Release files / semantic_compressor-2.43-py3-none-any.whl

Download URL semantic_compressor-2.43-py3-none-any.whl
Size 50.6 MB
Tags Python 3
SHA-256 checksum
How to use checksums
3eed4583bd3209f877bdb6606c20a3c3b0bca4c1f4afa44b3350373f78c1be74
BLAKE2b-256 checksum
How to use checksums
b6c1028f49d97a15de570626121c5012c8e24439d8fddfcf702f1852ccbc9902
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.11

Security for semantic-compressor 2.43

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.

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