Text embedding guide for Python

The MediaPipe Text Embedder task lets you create a numeric representation of text data to capture its semantic meaning. These instructions show you how to use the Text Embedder 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 Embedder 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 embedder. You can view, run, and edit the Text Embedder example code using just your web browser with Google Colab. 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 Embedder. 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 Embedder uses the mediapipe pip package. You can install the dependency with the following:

$ python -m pip install mediapipe

Imports

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

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

Model

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

Select and download a model, and then store it in a local directory. You can use the recommended UniversalSentenceEncoder model.

model_path = '/absolute/path/to/universal_sentence_encoder.tflite'

Specify the path of the model within the model_asset_path parameter, as shown below:

base_options = BaseOptions(model_asset_path=model_path)

Create the task

The MediaPipe Text Embedder 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 embedder 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
TextEmbedder = mp.tasks.text.TextEmbedder
TextEmbedderOptions = mp.tasks.text.TextEmbedderOptions

# For creating a text embedder instance:
options = TextEmbedderOptions(
    base_options=BaseOptions(model_asset_path=model_path),
    quantize=True)
text_embedder = TextEmbedder.create_from_options(options)

Configuration options

This task has the following configuration options for Python applications:

Prepare data

Text Embedder works with text (str) data. The task handles the data input preprocessing, including tokenization and tensor preprocessing.

All preprocessing is handled within the embed function. There is no need for additional preprocessing of the input text beforehand.

input_text = "The input text to be embedded."

Run the task

The Text Embedder uses the embed function to trigger inferences. For text embedding, this means returning the embedding vectors for the input text.

The following code demonstrates how execute the processing with the task model.

# Perform text embedding on the provided input text.
embedding_result = text_embedder.embed(input_text)

Handle and display results

The Text Embedder outputs a TextEmbedderResult that contains a list of embeddings (either floating-point or scalar-quantized) for the input text.

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

TextEmbedderResult:
  Embedding #0 (sole embedding head):
    float_embedding: {0.2345f, 0.1234f, ..., 0.6789f}
    head_index: 0

You can compare the semantic similarity of two embeddings using the TextEmbedder.cosine_similarity function. See the following code for an example.

# Compute cosine similarity.
similarity = TextEmbedder.cosine_similarity(
  embedding_result.embeddings[0],
  other_embedding_result.embeddings[0])