Output Parser

gllm-inference | Tutorial: Output Parser| Use Case: Produce Consistent Output from LM| API Reference

What's an Output Parser?

The output parser is a module designed to parse text output of a language model into a certain format such as JSON. In this tutorial, you'll learn how to utilize the JSONOutputParser in just a few lines of code. You can explore the available types of output parsers here.

Prerequisites

This example specifically requires completion of all setup steps listed on the Prerequisites page.

Installation

Linux, macOS, or Windows WSL

# you can use a Conda environment
pip install --extra-index-url https://oauth2accesstoken:$(gcloud auth print-access-token)@glsdk.gdplabs.id/gen-ai-internal/simple/ gllm-inference

Windows Powershell

Windows Command Prompt

Quickstart

Let’s jump into a basic example using JSONOutputParser, which can be used to extract JSON string contained in a text output of a language model.

from gllm_inference.output_parser import JSONOutputParser

text = """
Here's the extracted JSON:
{
    "name": "John Doe",
    "age": 30,
    "city": "New York"
}
Please let me know if you need any more information!
"""

output_parser = JSONOutputParser()
result = output_parser.parse(text)
print(result)

Expected Output

{'name': 'John Doe', 'age': 30, 'city': 'New York'}

And that's it! Using an output parser is as straightforward as it can get!