Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

logo

Langfun

PyPI version codecov pytest

Installation | Getting started

What is Langfun

Langfun is a Python library that aims to make language models (LM) fun to work with. Its design enables a programming model that flows naturally, resembling the human thought process. It emphasizes the reuse and combination of language pieces to form prompts, thereby accelerating innovation. In contrast to other LM frameworks, which feed program-generated data into the LM, langfun takes a distinct approach: It starts with natural language, allowing for seamless interactions between language and program logic, and concludes with natural language and optional structured output. Consequently, langfun can aptly be described as Language as functions, capturing the core of its methodology.

Install

pip install langfun

Or install nightly build with:

pip install langfun --pre

Hello World

import langfun as lf

class NumericAnswerExtractor(lf.LangFunc):
  """Numeric answer extractor.

  Here is my question:
  {{question}}

  Here is the response:
  {{question()}}

  Can you help me extract a number from the response as the answer to my
  question? Your response should only contain a number in numeric form.
  If the answer is not a number or you cannot extract it, respond with UNKNOWN.
  """
  output_transform = lf.transforms.Match('\d+').to_int()

l = NumericAnswerExtractor()

with lf.context(lm=lf.llms.Gpt35(debug=True)):
  r = l(question=lf.LangFunc('What is result of {{x}} plus {{y}}?'),
        x='one',
        y='two')
  print('Result:', r.result)

Disclaimer: this is not an officially supported Google product.

Metadata

Release files for langfun 0.0.2.dev20240420

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

Source distribution (sdist)

Source distribution for langfun 0.0.2.dev20240420
File Size Uploaded
langfun-0.0.2.dev20240420.tar.gz 146.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for langfun 0.0.2.dev20240420
File Interpreter ABI Platform
langfun-0.0.2.dev20240420-py3-none-any.whl Python 3 none any Details

Total release size: 368.1 kB

Release files / langfun-0.0.2.dev20240420.tar.gz

Download URL langfun-0.0.2.dev20240420.tar.gz
Size 146.0 kB
Tags Source
SHA-256 checksum
How to use checksums
95c85b3ff533167fa375d88b0eeb6b4f6620d5eac2f910440a87acffa5515d69
BLAKE2b-256 checksum
How to use checksums
86b0979b9195da0797aa9240ba2ccf9ec1ad1c8d93e8fe026c311e3d418096e5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.0.0 CPython/3.12.3

Release files / langfun-0.0.2.dev20240420-py3-none-any.whl

Download URL langfun-0.0.2.dev20240420-py3-none-any.whl
Size 222.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
da5befc9212f3d045c784451fd33680a92b6057f80436289f76e0e065ecca414
BLAKE2b-256 checksum
How to use checksums
45744311c778f7369d0a844ac781ba602509c4c9b7814765eb4e11cddc5e718c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.0.0 CPython/3.12.3

Release history Release notifications | RSS feed

0.1.1

2 release files

0.1.0

2 release files

This release

0.0.1

2 release files

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