radprompter 2.0.0

A package for simplified and reproducible LLM prompting.

RadPrompter

RadPrompter is a Python package for simplified and reproducible LLM prompting, particularly tailored for biomedical applications, including Radiology.

Installation

You can install RadPrompter using pip:

pip install radprompter

Note: RadPrompter works with Python 3.7+. However, for maximum compatilibity we recommend using Python 3.11+.

Getting Started

The core of RadPrompter is the .toml configuration file which defines your prompts. Here's a minimal example:

[METADATA]
version = 0.1
description = "A sample prompt for RadPrompter"

[CONSTRUCTOR]
system = "You are an experienced radiologist that help users extract infromation from radiology reports."
user = """Does the following report indicate a normal or abnormal finding?
{{report}}

Just reply with "normal" or "abnormal" to indicate your answer, without any additional information.
"""

And here's how you would use it in Python:

from radprompter import Prompt, RadPrompter, vLLMClient

prompt = Prompt("sample.toml")

client = vLLMClient(
    model="google/medgemma-4b-it",
    base_url="http://localhost:8000/v1",
    temperature=0.0,
    seed=42
)

engine = RadPrompter(
    client=client,
    prompt=prompt, 
    output_file="output.csv",
)

reports = [{"report": "..."}]  # Your radiology reports
engine(reports)

For more details and advanced usage, check out our tutorials.

Tutorials

Tutorial	Description	Notebook
01_Basic-Usecase	Covers the basic usage of RadPrompter	👁️ 📓
02_RDP-Templating	Introduces the [PROMPTS] section and rdp operator	👁️ 📓
03_Multiturn-Prompting	Demonstrates multi-turn prompting	👁️ 📓
04_Using-Schemas	Shows how to use schemas for structured output	👁️ 📓
05_JSON-Prefill	Covers using JSON prefills and sanitization	👁️ 📓
06_HuggingFace-Client	Covers using the new HuggingFaceClient	👁️ 📓
07_Conditional-Schemas	Demonstrates how to use conditional schemas (v2.0+)	👁️ 📓

Contributing

We welcome contributions! If you have any updates or improvements to the package, please open an issue or submit a pull request. We're happy to review and incorporate your changes.

Authors

RadPrompter is created and maintained by:

• Bardia Khosravi ([e-mail])
• Theo Dapamede ([e-mail])