Home

Awesome


page_type: sample languages:


Cognitive Services Python SDK Samples

These samples will show you how to get up and running using the Python SDKs for various Cognitive Services services. They'll cover a few rudimentary use cases and hopefully express best practices for interacting with the data from these APIs.

Features

This project framework provides examples for the following services:

Knowledge

Language

Search

Vision

We provide several meta-packages to help you install several packages at a time. Please note that meta-packages are only recommended for development purpose. It's recommended in production to always pin specific version of individual packages.

Getting Started

Prerequisites

  1. A cognitive services API key with which to authenticate the SDK's calls. Create a new Azure account, and try Cognitive Services for free.

Subscription keys are usually per service. For example, the subscription key for Spell Check will not be the same than Custom Search. Read the previous sign up link or the Azure portal for details on subscription keys.

Installation

  1. If you don't already have it, install Python.

    This sample (and the SDK) is compatible with Python 2.7, 3.3, 3.4, 3.5 and 3.6.

  2. General recommendation for Python development is to use a Virtual Environment. For more information, see https://docs.python.org/3/tutorial/venv.html

    Install and initialize the virtual environment with the "venv" module on Python 3 (you must install virtualenv for Python 2.7):

    python -m venv mytestenv # Might be "python3" or "py -3.6" depending on your Python installation
    cd mytestenv
    source bin/activate      # Linux shell (Bash, ZSH, etc.) only
    ./scripts/activate       # PowerShell only
    ./scripts/activate.bat   # Windows CMD only
    

Quickstart

  1. Clone the repository.

    git clone https://github.com/Azure-Samples/cognitive-services-python-sdk-samples.git
    
  2. Install the dependencies using pip.

    cd cognitive-services-python-sdk-samples
    pip install -r requirements.txt
    
  3. Set up the environment variable LUIS_SUBSCRIPTION_KEY with your key if you want to execute LUIS tests.

  4. Set up the environment variable SPELLCHECK_SUBSCRIPTION_KEY with your key if you want to execute SpellCheck tests.

  5. Set up the environment variable TEXTANALYTICS_SUBSCRIPTION_KEY with your key if you want to execute TextAnalytics tests. You might override too TEXTANALYTICS_LOCATION (westcentralus by default).

  6. Set up the environment variable AUTOSUGGEST_SUBSCRIPTION_KEY with your key if you want to execute Autosuggest tests.

  7. Set up the environment variable CUSTOMSEARCH_SUBSCRIPTION_KEY with your key if you want to execute CustomSearch tests.

  8. Set up the environment variable CUSTOMIMAGESEARCH_SUBSCRIPTION_KEY with your key if you want to execute CustomImageSearch tests.

  9. Set up the environment variable ENTITYSEARCH_SUBSCRIPTION_KEY with your key if you want to execute EntitySearch tests.

  10. Set up the environment variable IMAGESEARCH_SUBSCRIPTION_KEY with your key if you want to execute ImageSearch tests.

  11. Set up the environment variable NEWSSEARCH_SUBSCRIPTION_KEY with your key if you want to execute NewsSearch tests.

  12. Set up the environment variable VIDEOSEARCH_SUBSCRIPTION_KEY with your key if you want to execute VideoSearch tests.

  13. Set up the environment variable VISUALSEARCH_SUBSCRIPTION_KEY with your key if you want to execute VideoSearch tests.

  14. Set up the environment variable WEBSEARCH_SUBSCRIPTION_KEY with your key if you want to execute WebSearch tests.

  15. Set up the environment variable COMPUTERVISION_SUBSCRIPTION_KEY with your key if you want to execute Computer Vision tests. You might override too COMPUTERVISION_LOCATION (westcentralus by default).

  16. Set up the environment variable CONTENTMODERATOR_SUBSCRIPTION_KEY with your key if you want to execute Content Moderator tests. You might override too CONTENTMODERATOR_LOCATION (westcentralus by default).

  17. Set up the environment variable CUSTOMVISION_TRAINING_KEY with your key and CUSTOMVISION_PREDICTION_ID with a valid prediction resource id if you want to execute CustomVision Training tests.

  18. Set up the environment variable CUSTOMVISION_PREDICTION_KEY with your key and CUSTOMVISION_PREDICTION_ID with a valid prediction resource id if you want to execute CustomVision Prediction tests.

Demo

A demo app is included to show how to use the project.

To run the complete demo, execute python example.py

To run each individual demo, point directly to the file. For example (i.e. not complete list):

  1. python samples/language/spellcheck_samples.py
  2. python samples/search/entity_search_samples.py
  3. python samples/search/video_search_samples.py
  4. python samples/vision/inkrecognizer_sample.py

To see the code of each example, simply look at the examples in the Samples folder. They are written to be isolated in scope so that you can see only what you're interested in.

Resources