pywit is the Python SDK for Wit.ai.

Using pip:

pip install wit

From source:

git clone https://github.com/wit-ai/pywit
pip install .

See the examples folder for examples.

The default API version is 20160516. You can target a specific version by setting the env variable WIT_API_VERSION.

pywit provides a Wit class with the following methods:

• message - the Wit message API
• speech - the Wit speech API
• interactive - starts an interactive conversation with your bot

The Wit constructor takes the following parameters:

• access_token - the access token of your Wit instance

A minimal example looks like this:

from wit import Wit

client = Wit(access_token)
client.message('set an alarm tomorrow at 7am')

The Wit message API.

Takes the following parameters:

• msg - the text you want Wit.ai to extract the information from
• verbose - (optional) if set, calls the API with verbose=true

Example:

resp = client.message('what is the weather in London?')
print('Yay, got Wit.ai response: ' + str(resp))

The Wit speech API.

Takes the following parameters:

• audio_file - a file handler opened in binary mode
• verbose - (optional) if set, calls the API with verbose=true
• headers - (optional) the dict of headers (e.g. "Content-Type")

Example:

resp = None
with open('test.wav', 'rb') as f:
  resp = client.speech(f, None, {'Content-Type': 'audio/wav'})
print('Yay, got Wit.ai response: ' + str(resp))

Starts an interactive conversation with your bot.

Example:

client.interactive()

See the docs for more information.

Default logging is to STDOUT with INFO level.

You can set your logging level as follows:

from wit import Wit
import logging
client = Wit(token)
client.logger.setLevel(logging.WARNING)

You can also specify a custom logger object in the Wit constructor:

from wit import Wit
client = Wit(access_token=access_token, logger=custom_logger)

See the logging module and logging.config docs for more information.

The license for pywit can be found in LICENSE file in the root directory of this source tree.