Features¶

• Make queries
• Create Entities
• Create and update Intents

Installation¶

pip install api.ai

Quickstart¶

from api.ai import Agent

agent = Agent(
     '<subscription-key>',
     '<client-access-token>',
     '<developer-access-token>',
)
response = agent.query("Hello there")

Credits¶

• Fulfil.IO Inc

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.

Entities¶

List all entities:

agent.entities.all()

Create a new Entity:

agent.entities.create(
    'Languages', [
        {'value': 'Python', 'synonyms': ['python', 'py']},
        {'value': 'Golang', 'synonyms': ['go', 'google go language']},
    ]
)

Update an entity with new entries:

agent.entities.update(
    'entity-id-uuid',
    [
        {'value': 'Python', 'synonyms': ['python', 'py']},
        {'value': 'Golang', 'synonyms': ['go', 'google go language']},
    ],
)

Intents¶

List all intents:

agent.intents.all()

Create a new Intent:

agent.intents.create(
    'name',
    'templates': [
        "Who am I?"
    ]
)

API Reference¶

class api.ai.Agent(sub_key, client_token, dev_token, session=None, timezone=None)[source]¶

Agent interface for an API.AI agent

entities¶

Return an entities handler object

intents¶

Return an intents handler object

query(query, confidence=None, lang='en', contexts=None, resetContexts=False, entities=None, timezone=None, session=None)[source]¶

Use when you want to make a single query.

For multiple queries use multi_query (TODO)

Parameters:	query – The natural language text to be processed. confidence – The confidence of the corresponding query parameter having been correctly recognized by a speech recognition system. 0 represents no confidence and 1 represents the highest confidence.

class api.ai.Entities(client)[source]¶

An entity is a data type that contains mappings between a set of synonyms

all()¶

return all the records in the endpoint

create(name, entries)[source]¶

Create a new entity with the name

Parameters:	name – Name of the entity entries – List of dictionaries

agent.entities.create(
    'EntityName',
    [{
        "value": "Coffee Maker",
        "synonyms": ["coffee maker", "coffee machine"]
    }, {
        "value": "Thermostat",
        "synonyms": ["Thermostat", "heat", "air conditioning"]
    }, {
        "value": "Lights",
        "synonyms": ["lights", "light", "lamps"]
    }, {
        "value": "Garage door",
        "synonyms": ["garage door", "garage"]
    }]
)

update(entity_id, entries, name=None)[source]¶

Update an existing entity

class api.ai.Intents(client)[source]¶

Intents convert a number of user expressions or patterns into an action.

all()¶

return all the records in the endpoint

create(name, contexts=None, templates=None, responses=None)[source]¶

For explanation of the params read: https://docs.api.ai/docs/intents#intent-object

Types of Contributions¶

Get Started!¶

Ready to contribute? Here’s how to set up api_ai for local development.

1. Fork the api_ai repo on GitHub.

2. Clone your fork locally:

   $ git clone git@github.com:your_name_here/api_ai.git
   

3. Install your local copy into a virtualenv. Assuming you have virtualenvwrapper installed, this is how you set up your fork for local development:

   $ mkvirtualenv api_ai
   $ cd api_ai/
   $ python setup.py develop
   

4. Create a branch for local development:

   $ git checkout -b name-of-your-bugfix-or-feature
   

   Now you can make your changes locally.

5. When you’re done making changes, check that your changes pass flake8 and the tests, including testing other Python versions with tox:

   $ flake8 api_ai tests
   $ python setup.py test
   $ tox
   

   To get flake8 and tox, just pip install them into your virtualenv.

6. Commit your changes and push your branch to GitHub:

   $ git add .
   $ git commit -m "Your detailed description of your changes."
   $ git push origin name-of-your-bugfix-or-feature
   

7. Submit a pull request through the GitHub website.

Pull Request Guidelines¶

Before you submit a pull request, check that it meets these guidelines:

1. The pull request should include tests.
2. If the pull request adds functionality, the docs should be updated. Put your new functionality into a function with a docstring, and add the feature to the list in README.rst.
3. The pull request should work for Python 2.6, 2.7, 3.3, 3.4 and 3.5, and for PyPy. Check https://travis-ci.org/fulfilio/api_ai/pull_requests and make sure that the tests pass for all supported Python versions.

Tips¶

To run a subset of tests:

$ python -m unittest tests.test_api_ai

Development Lead¶

• Fulfil.IO Inc. <hello@fulfil.io>

Contributors¶

None yet. Why not be the first?

0.1.0 (2016-1-22)¶

• First release on PyPI.