Text summarization guide for Python

The MediaPipe Text Summarizer task lets you identify the most important information in a text and generate a shorter version while maintaining the original context meaning. These instructions show you how to use the Text Summarizer with Python.

For more information about the capabilities, models, and configuration options of this task, see the Overview.

Code example

The example code for Text Summarizer provides a complete implementation of this task in Python for your reference. This code helps you test this task and get started on building your own text summarizer. You can view the source code for this example on GitHub.

Setup

This section describes key steps for setting up your development environment and code projects specifically to use Text Summarizer. For general information on setting up your development environment for using MediaPipe tasks, including platform version requirements, see the Setup guide for Python.

Packages

Text Summarizer uses the mediapipe pip package. You can install the dependency with the following command:

$ python -m pip install mediapipe

Imports

Import the following classes to access the Text Summarizer task functions:

import mediapipe as mp
from mediapipe.tasks import python
from mediapipe.tasks.python import text

Model

The MediaPipe Text Summarizer task requires a trained model that is compatible with this task. For more information on available trained models for Text Summarizer, see the task overview Models section.

Select and download a model, and then store it in a local directory.

model_path = '/absolute/path/to/summarizer.litertlm'

Specify the path of the model using the model_asset_path parameter, as follows:

base_options = python.BaseOptions(model_asset_path=model_path)

Create the task

The MediaPipe Text Summarizer task uses the create_from_options function to set up the task. The create_from_options function accepts values for configuration options to set the summarizer options. You can also initialize the task using the create_from_model_path factory function. The create_from_model_path function accepts a relative or absolute path to the trained model file.

For more information on configuration options, see Configuration options.

The following code demonstrates how to build and configure this task.

import mediapipe as mp

BaseOptions = mp.tasks.BaseOptions
TextSummarizer = mp.tasks.text.TextSummarizer
TextSummarizerOptions = mp.tasks.text.TextSummarizerOptions
TextSummarizerMode = mp.tasks.text.TextSummarizerMode

# Build the configuration options
options = TextSummarizerOptions(
    base_options=BaseOptions(model_asset_path=model_path),
    mode=TextSummarizerMode.TLDR
)

text_summarizer = TextSummarizer.create_from_options(options)

Configuration options

This task has the following configuration options for Python applications:

Option Name Description Value Range Default Value
mode The summarization mode of the text summarizer task. Can be a short summary paragraph or bulleted list of key points. TextSummarizerMode.TLDR, TextSummarizerMode.KEYPOINTS TextSummarizerMode.KEYPOINTS
max_num_tokens The maximum number of tokens for summarization tasks. If set, the summarization will be truncated if the input and output exceed this value. If not set, then the default limit is decided by the model capacity. Integer None (model capacity 8k)

Prepare data

Text Summarizer accepts text (str) data and doesn't require any preparations.

input_text = "The extremely long input text to be summarized goes here..."

Run the task

The Text Summarizer uses the summarize function for synchronous execution, and summarize_async for asynchronous streaming execution to generate summaries token by token.

Synchronous Execution

The following code demonstrates how to execute the processing synchronously.

# Perform text summarization on the provided input text.
summarization_result = text_summarizer.summarize(input_text)

Asynchronous Streaming Execution

To execute asynchronous streaming where parts of the text are generated chunk by chunk, use summarize_async. The streaming engine leverages the callback to relay incremental updates, mapping the stream .summary and .done fields into the output result.

You must provide a callback function to handle these incoming results.

from typing import Optional

def result_callback(result: Optional[mp.tasks.text.TextSummarizerResult], error: Optional[str]):
    if error:
        print(f"Error: {error}")
        return

    if result and result.summary:
        # Result contains the partial chunk string
        print(result.summary, end="")

    if result and result.done:
        print("\nFinished stream!")

# Perform streaming text summarization on the provided input text.
text_summarizer.summarize_async(input_text, result_callback)

Handle and display results

The Text Summarizer outputs a TextSummarizerResult that contains the completed or partial summary and a boolean flag indicating completion status.

For streaming tasks, the Python TextSummarizerResult maps the package updates with the newly appended token chunk populated into the summary property, and the done property indicating completion.

The following shows an example of the output data from this task:

# TextSummarizerResult:
#   summary: "This is a short summary of the text."
#   done: True

# Print the output summary text
print("Summary:", summarization_result.summary)