AgentsClient

AgentsClient

Agents are best described as Natural Language Understanding (NLU) modules that transform user requests into actionable data. You can include agents in your app, product, or service to determine user intent and respond to the user in a natural way.

After you create an agent, you can add Intents, Contexts, Entity Types, Webhooks, and so on to manage the flow of a conversation and match user input to predefined intents and actions.

You can create an agent using both Dialogflow Standard Edition and Dialogflow Enterprise Edition. For details, see Dialogflow Editions.

You can save your agent for backup or versioning by exporting the agent by using the ExportAgent method. You can import a saved agent by using the ImportAgent method.

Dialogflow provides several prebuilt agents for common conversation scenarios such as determining a date and time, converting currency, and so on.

For more information about agents, see the Dialogflow documentation.

Constructor

new AgentsClient(optionsopt)

Construct an instance of AgentsClient.

Parameters:
Name Type Attributes Description
options object <optional>

The configuration object. See the subsequent parameters for more details.

Properties
Name Type Attributes Description
credentials object <optional>

Credentials object.

Properties
Name Type Attributes Description
client_email string <optional>
private_key string <optional>
email string <optional>

Account email address. Required when using a .pem or .p12 keyFilename.
keyFilename string <optional>

Full path to the a .json, .pem, or .p12 key downloaded from the Google Developers Console. If you provide a path to a JSON file, the projectId option below is not necessary. NOTE: .pem and .p12 require you to specify options.email as well.
port number <optional>

The port on which to connect to the remote host.
projectId string <optional>

The project ID from the Google Developer's Console, e.g. 'grape-spaceship-123'. We will also check the environment variable GCLOUD_PROJECT for your project ID. If your app is running in an environment which supports Application Default Credentials, your project ID will be detected automatically.
promise function <optional>

Custom promise module to use instead of native Promises.
apiEndpoint string <optional>

The domain name of the API remote host.
Source:

Members

(static) apiEndpoint

The DNS address for this API service - same as servicePath(), exists for compatibility reasons.

Source:

(static) port

The port for this API service.

Source:

(static) scopes

The scopes needed to make gRPC calls for every method defined in this service.

Source:

(static) servicePath

The DNS address for this API service.

Source:

Methods

deleteAgent(request, optionsopt, callbackopt) → {Promise}

Deletes the specified agent.

Parameters:
Name Type Attributes Description
request Object

The request object that will be sent.

Properties
Name Type Description
parent string

Required. The project that the agent to delete is associated with. Format: projects/<Project ID>.
options Object <optional>

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.
callback function <optional>

The function which will be called with the result of the API call.
Source:
Example
const dialogflow = require('dialogflow');

const client = new dialogflow.v2.AgentsClient({
  // optional auth parameters.
});

const formattedParent = client.projectPath('[PROJECT]');
client.deleteAgent({parent: formattedParent}).catch(err => {
  console.error(err);
});

exportAgent(request, optionsopt, callbackopt) → {Promise}

Exports the specified agent to a ZIP file.

Operation <response: ExportAgentResponse>

Parameters:
Name Type Attributes Description
request Object

The request object that will be sent.

Properties
Name Type Attributes Description
parent string

Required. The project that the agent to export is associated with. Format: projects/<Project ID>.
agentUri string <optional>

Required. The Google Cloud Storage URI to export the agent to. The format of this URI must be gs://<bucket-name>/<object-name>. If left unspecified, the serialized agent is returned inline.
options Object <optional>

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.
callback function <optional>

The function which will be called with the result of the API call.

The second parameter to the callback is a gax.Operation object.
Source:
Example
const dialogflow = require('dialogflow');

const client = new dialogflow.v2.AgentsClient({
  // optional auth parameters.
});

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the promise pattern.
client.exportAgent({parent: formattedParent})
  .then(responses => {
    const [operation, initialApiResponse] = responses;

    // Operation#promise starts polling for the completion of the LRO.
    return operation.promise();
  })
  .then(responses => {
    const result = responses[0];
    const metadata = responses[1];
    const finalApiResponse = responses[2];
  })
  .catch(err => {
    console.error(err);
  });

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the event emitter pattern.
client.exportAgent({parent: formattedParent})
  .then(responses => {
    const [operation, initialApiResponse] = responses;

    // Adding a listener for the "complete" event starts polling for the
    // completion of the operation.
    operation.on('complete', (result, metadata, finalApiResponse) => {
      // doSomethingWith(result);
    });

    // Adding a listener for the "progress" event causes the callback to be
    // called on any change in metadata when the operation is polled.
    operation.on('progress', (metadata, apiResponse) => {
      // doSomethingWith(metadata)
    });

    // Adding a listener for the "error" event handles any errors found during polling.
    operation.on('error', err => {
      // throw(err);
    });
  })
  .catch(err => {
    console.error(err);
  });

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the await pattern.
const [operation] = await client.exportAgent({parent: formattedParent});

const [response] = await operation.promise();

getAgent(request, optionsopt, callbackopt) → {Promise}

Retrieves the specified agent.

Parameters:
Name Type Attributes Description
request Object

The request object that will be sent.

Properties
Name Type Description
parent string

Required. The project that the agent to fetch is associated with. Format: projects/<Project ID>.
options Object <optional>

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.
callback function <optional>

The function which will be called with the result of the API call.

The second parameter to the callback is an object representing Agent.
Source:
Example
const dialogflow = require('dialogflow');

const client = new dialogflow.v2.AgentsClient({
  // optional auth parameters.
});

const formattedParent = client.projectPath('[PROJECT]');
client.getAgent({parent: formattedParent})
  .then(responses => {
    const response = responses[0];
    // doThingsWith(response)
  })
  .catch(err => {
    console.error(err);
  });

getProjectId(callback)

Return the project ID used by this class.

Parameters:
Name Type Description
callback function

the callback to be called with the current project Id.
Source:

importAgent(request, optionsopt, callbackopt) → {Promise}

Imports the specified agent from a ZIP file.

Uploads new intents and entity types without deleting the existing ones. Intents and entity types with the same name are replaced with the new versions from ImportAgentRequest.

Operation <response: google.protobuf.Empty>

Parameters:
Name Type Attributes Description
request Object

The request object that will be sent.

Properties
Name Type Attributes Description
parent string

Required. The project that the agent to import is associated with. Format: projects/<Project ID>.
agentUri string <optional>

The URI to a Google Cloud Storage file containing the agent to import. Note: The URI must start with "gs://".
agentContent Buffer <optional>

Zip compressed raw byte content for agent.
options Object <optional>

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.
callback function <optional>

The function which will be called with the result of the API call.

The second parameter to the callback is a gax.Operation object.
Source:
Example
const dialogflow = require('dialogflow');

const client = new dialogflow.v2.AgentsClient({
  // optional auth parameters.
});

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the promise pattern.
client.importAgent({parent: formattedParent})
  .then(responses => {
    const [operation, initialApiResponse] = responses;

    // Operation#promise starts polling for the completion of the LRO.
    return operation.promise();
  })
  .then(responses => {
    const result = responses[0];
    const metadata = responses[1];
    const finalApiResponse = responses[2];
  })
  .catch(err => {
    console.error(err);
  });

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the event emitter pattern.
client.importAgent({parent: formattedParent})
  .then(responses => {
    const [operation, initialApiResponse] = responses;

    // Adding a listener for the "complete" event starts polling for the
    // completion of the operation.
    operation.on('complete', (result, metadata, finalApiResponse) => {
      // doSomethingWith(result);
    });

    // Adding a listener for the "progress" event causes the callback to be
    // called on any change in metadata when the operation is polled.
    operation.on('progress', (metadata, apiResponse) => {
      // doSomethingWith(metadata)
    });

    // Adding a listener for the "error" event handles any errors found during polling.
    operation.on('error', err => {
      // throw(err);
    });
  })
  .catch(err => {
    console.error(err);
  });

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the await pattern.
const [operation] = await client.importAgent({parent: formattedParent});

const [response] = await operation.promise();

matchProjectFromProjectName(projectName) → {String}

Parse the projectName from a project resource.

Parameters:
Name Type Description
projectName String

A fully-qualified path representing a project resources.
Source:

projectPath(project) → {String}

Return a fully-qualified project resource name string.

Parameters:
Name Type Description
project String
Source:

restoreAgent(request, optionsopt, callbackopt) → {Promise}

Restores the specified agent from a ZIP file.

Replaces the current agent version with a new one. All the intents and entity types in the older version are deleted.

Operation <response: google.protobuf.Empty>

Parameters:
Name Type Attributes Description
request Object

The request object that will be sent.

Properties
Name Type Attributes Description
parent string

Required. The project that the agent to restore is associated with. Format: projects/<Project ID>.
agentUri string <optional>

The URI to a Google Cloud Storage file containing the agent to restore. Note: The URI must start with "gs://".
agentContent Buffer <optional>

Zip compressed raw byte content for agent.
options Object <optional>

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.
callback function <optional>

The function which will be called with the result of the API call.

The second parameter to the callback is a gax.Operation object.
Source:
Example
const dialogflow = require('dialogflow');

const client = new dialogflow.v2.AgentsClient({
  // optional auth parameters.
});

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the promise pattern.
client.restoreAgent({parent: formattedParent})
  .then(responses => {
    const [operation, initialApiResponse] = responses;

    // Operation#promise starts polling for the completion of the LRO.
    return operation.promise();
  })
  .then(responses => {
    const result = responses[0];
    const metadata = responses[1];
    const finalApiResponse = responses[2];
  })
  .catch(err => {
    console.error(err);
  });

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the event emitter pattern.
client.restoreAgent({parent: formattedParent})
  .then(responses => {
    const [operation, initialApiResponse] = responses;

    // Adding a listener for the "complete" event starts polling for the
    // completion of the operation.
    operation.on('complete', (result, metadata, finalApiResponse) => {
      // doSomethingWith(result);
    });

    // Adding a listener for the "progress" event causes the callback to be
    // called on any change in metadata when the operation is polled.
    operation.on('progress', (metadata, apiResponse) => {
      // doSomethingWith(metadata)
    });

    // Adding a listener for the "error" event handles any errors found during polling.
    operation.on('error', err => {
      // throw(err);
    });
  })
  .catch(err => {
    console.error(err);
  });

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the await pattern.
const [operation] = await client.restoreAgent({parent: formattedParent});

const [response] = await operation.promise();

searchAgents(request, optionsopt, callbackopt) → {Promise}

Returns the list of agents.

Since there is at most one conversational agent per project, this method is useful primarily for listing all agents across projects the caller has access to. One can achieve that with a wildcard project collection id "-". Refer to List Sub-Collections.

Parameters:
Name Type Attributes Description
request Object

The request object that will be sent.

Properties
Name Type Attributes Description
parent string

Required. The project to list agents from. Format: projects/<Project ID or '-'>.
pageSize number <optional>

The maximum number of resources contained in the underlying API response. If page streaming is performed per-resource, this parameter does not affect the return value. If page streaming is performed per-page, this determines the maximum number of resources in a page.
options Object <optional>

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.
callback function <optional>

The function which will be called with the result of the API call.

The second parameter to the callback is Array of Agent.

When autoPaginate: false is specified through options, it contains the result in a single response. If the response indicates the next page exists, the third parameter is set to be used for the next request object. The fourth parameter keeps the raw response object of an object representing SearchAgentsResponse.
Source:
Example
const dialogflow = require('dialogflow');

const client = new dialogflow.v2.AgentsClient({
  // optional auth parameters.
});

// Iterate over all elements.
const formattedParent = client.projectPath('[PROJECT]');

client.searchAgents({parent: formattedParent})
  .then(responses => {
    const resources = responses[0];
    for (const resource of resources) {
      // doThingsWith(resource)
    }
  })
  .catch(err => {
    console.error(err);
  });

// Or obtain the paged response.
const formattedParent = client.projectPath('[PROJECT]');


const options = {autoPaginate: false};
const callback = responses => {
  // The actual resources in a response.
  const resources = responses[0];
  // The next request if the response shows that there are more responses.
  const nextRequest = responses[1];
  // The actual response object, if necessary.
  // const rawResponse = responses[2];
  for (const resource of resources) {
    // doThingsWith(resource);
  }
  if (nextRequest) {
    // Fetch the next page.
    return client.searchAgents(nextRequest, options).then(callback);
  }
}
client.searchAgents({parent: formattedParent}, options)
  .then(callback)
  .catch(err => {
    console.error(err);
  });

searchAgentsStream(request, optionsopt) → {Stream}

Equivalent to searchAgents, but returns a NodeJS Stream object.

This fetches the paged responses for searchAgents continuously and invokes the callback registered for 'data' event for each element in the responses.

The returned object has 'end' method when no more elements are required.

autoPaginate option will be ignored.

Parameters:
Name Type Attributes Description
request Object

The request object that will be sent.

Properties
Name Type Attributes Description
parent string

Required. The project to list agents from. Format: projects/<Project ID or '-'>.
pageSize number <optional>

The maximum number of resources contained in the underlying API response. If page streaming is performed per-resource, this parameter does not affect the return value. If page streaming is performed per-page, this determines the maximum number of resources in a page.
options Object <optional>

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.
Source:
See:
Example
const dialogflow = require('dialogflow');

const client = new dialogflow.v2.AgentsClient({
  // optional auth parameters.
});

const formattedParent = client.projectPath('[PROJECT]');
client.searchAgentsStream({parent: formattedParent})
  .on('data', element => {
    // doThingsWith(element)
  }).on('error', err => {
    console.log(err);
  });

setAgent(request, optionsopt, callbackopt) → {Promise}

Creates/updates the specified agent.

Parameters:
Name Type Attributes Description
request Object

The request object that will be sent.

Properties
Name Type Attributes Description
agent Object

Required. The agent to update.

This object should have the same structure as Agent
updateMask Object <optional>

Optional. The mask to control which fields get updated.

This object should have the same structure as FieldMask
options Object <optional>

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.
callback function <optional>

The function which will be called with the result of the API call.

The second parameter to the callback is an object representing Agent.
Source:
Example
const dialogflow = require('dialogflow');

const client = new dialogflow.v2.AgentsClient({
  // optional auth parameters.
});

const agent = {};
client.setAgent({agent: agent})
  .then(responses => {
    const response = responses[0];
    // doThingsWith(response)
  })
  .catch(err => {
    console.error(err);
  });

trainAgent(request, optionsopt, callbackopt) → {Promise}

Trains the specified agent.

Operation <response: google.protobuf.Empty>

Parameters:
Name Type Attributes Description
request Object

The request object that will be sent.

Properties
Name Type Description
parent string

Required. The project that the agent to train is associated with. Format: projects/<Project ID>.
options Object <optional>

Optional parameters. You can override the default settings for this call, e.g, timeout, retries, paginations, etc. See gax.CallOptions for the details.
callback function <optional>

The function which will be called with the result of the API call.

The second parameter to the callback is a gax.Operation object.
Source:
Example
const dialogflow = require('dialogflow');

const client = new dialogflow.v2.AgentsClient({
  // optional auth parameters.
});

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the promise pattern.
client.trainAgent({parent: formattedParent})
  .then(responses => {
    const [operation, initialApiResponse] = responses;

    // Operation#promise starts polling for the completion of the LRO.
    return operation.promise();
  })
  .then(responses => {
    const result = responses[0];
    const metadata = responses[1];
    const finalApiResponse = responses[2];
  })
  .catch(err => {
    console.error(err);
  });

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the event emitter pattern.
client.trainAgent({parent: formattedParent})
  .then(responses => {
    const [operation, initialApiResponse] = responses;

    // Adding a listener for the "complete" event starts polling for the
    // completion of the operation.
    operation.on('complete', (result, metadata, finalApiResponse) => {
      // doSomethingWith(result);
    });

    // Adding a listener for the "progress" event causes the callback to be
    // called on any change in metadata when the operation is polled.
    operation.on('progress', (metadata, apiResponse) => {
      // doSomethingWith(metadata)
    });

    // Adding a listener for the "error" event handles any errors found during polling.
    operation.on('error', err => {
      // throw(err);
    });
  })
  .catch(err => {
    console.error(err);
  });

const formattedParent = client.projectPath('[PROJECT]');

// Handle the operation using the await pattern.
const [operation] = await client.trainAgent({parent: formattedParent});

const [response] = await operation.promise();