Skip to main content

Leverage LLMs to generate and execute robust code dynamically through an intuitive and easy-to-use API!

Project description

PyLLM: In-Line Executable Code Generation Using LLMs

PyLLM harnesses the power of Large Language Models (LLMs) to generate and execute code during runtime. Whether you're automating routine tasks, solving complex problems, or just experimenting with AI-generated code, PyLLM provides a seamless and intuitive interface for code generation and execution.

Features

  • Dynamic Code Generation: Generate functions on-the-fly in one line.
  • Unit Testing: Specify unit tests to ensure the generated code meets your requirements.
  • Caching Mechanism: Avoid re-generating code for repeated requests with an optional caching feature.
  • Customizable: Easily tune your prompt template and sampling parameters.

Installation

pip install pyllm-code

Quick Start

Here's a simple example to get you started with PyLLM. The following code generates a function to swap two numbers:

from pyllm import CodeLLM

llm = CodeLLM()
swap_numbers = llm.def_function(
    "Swap two input numbers", unit_tests=[((1, 2), (2, 1))]
)
print(swap_numbers(20, 40))
# Output: (40, 20)

Usage

To generate a function using PyLLM, create a CodeLLM instance and use the function method with the desired description and unit tests:

from pyllm import CodeLLM

# Initialize the LLM interface
llm = CodeLLM()

# Generate a function
my_function = llm.def_function(
    "Function description here",
    unit_tests=[("input_example", "expected_output")],
    use_cached=True  # Set to False to disable caching
)

Contributing

Contributions are welcomed from the community, whether it's in the form of bug reports, feature requests, or code contributions. Please refer to our CONTRIBUTING.md for guidelines on how to contribute.

License

PyLLM is released under the MIT license. See the LICENSE file for more details.

Support

If you encounter any issues or have questions, please file an issue on our GitHub repository.

Enjoy crafting code with AI through PyLLM!

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

pyllm-code-0.0.2.tar.gz (13.3 kB view details)

Uploaded Source

File details

Details for the file pyllm-code-0.0.2.tar.gz.

File metadata

  • Download URL: pyllm-code-0.0.2.tar.gz
  • Upload date:
  • Size: 13.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.13

File hashes

Hashes for pyllm-code-0.0.2.tar.gz
Algorithm Hash digest
SHA256 079e51f42c7bdcbc79faeb9c01106df0292e3c25493195950166a4aa786180aa
MD5 1f74d87598d8d979e683d761cae75bd3
BLAKE2b-256 211667f0352c2781ea92c9ca08813af35473ce2692be67240cecd1e483ec0ddb

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page