Python client library to quickly get started with the various [Watson APIs][wdc] services.
python 3.5 and aboveTo install, use pip or easy_install:
pip install --upgrade ibm-watson
or
easy_install --upgrade ibm-watson
Note the following: a) Versions prior to 3.0.0 can be installed using:
pip install --upgrade watson-developer-cloud
b) If you run into permission issues try:
sudo -H pip install --ignore-installed six ibm-watson
For more details see #225
c) In case you run into problems installing the SDK in DSX, try
!pip install --upgrade pip
Restarting the kernel
For more details see #405
The [examples][examples] folder has basic and advanced examples. The examples within each service assume that you already have service credentials.
If you run your app in IBM Cloud, the SDK gets credentials from the [VCAP_SERVICES][vcap_services] environment variable.
Watson services are migrating to token-based Identity and Access Management (IAM) authentication.
To find out which authentication to use, view the service credentials. You find the service credentials for authentication the same way for all Watson services:
On this page, you should be able to see your credentials for accessing your service instance.
There are three ways to supply the credentials you found above to the SDK for authentication.
With a credential file, you just need to put the file in the right place and the SDK will do the work of parsing and authenticating. You can get this file by clicking the Download button for the credentials in the Manage tab of your service instance.
The file downloaded will be called ibm-credentials.env. This is the name the SDK will search for and must be preserved unless you want to configure the file path (more on that later). The SDK will look for your ibm-credentials.env file in the following places (in order):
As long as you set that up correctly, you don't have to worry about setting any authentication options in your code. So, for example, if you created and downloaded the credential file for your Discovery instance, you just need to do the following:
discovery = DiscoveryV1(version='2019-04-30')
And that's it!
If you're using more than one service at a time in your code and get two different ibm-credentials.env files, just put the contents together in one ibm-credentials.env file and the SDK will handle assigning credentials to their appropriate services.
If you would like to configure the location/name of your credential file, you can set an environment variable called IBM_CREDENTIALS_FILE. This will take precedence over the locations specified above. Here's how you can do that:
export IBM_CREDENTIALS_FILE="<path>"
where <path> is something like /home/user/Downloads/<file_name>.env.
Simply set the environment variables using _ syntax. For example, using your favourite terminal, you can set environment variables for Assistant service instance:
export ASSISTANT_APIKEY="<your apikey>"
export ASSISTANT_AUTH_TYPE="iam"
The credentials will be loaded from the environment automatically
assistant = AssistantV1(version='2018-08-01')
If you'd prefer to set authentication values manually in your code, the SDK supports that as well. The way you'll do this depends on what type of credentials your service instance gives you.
IBM Cloud has migrated to token-based Identity and Access Management (IAM) authentication. IAM authentication uses a service API key to get an access token that is passed with the call. Access tokens are valid for approximately one hour and must be regenerated.
You supply either an IAM service API key or a bearer token:
from ibm_watson import DiscoveryV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator
# In the constructor, letting the SDK manage the token
authenticator = IAMAuthenticator('apikey',
url='<iam_url>') # optional - the default value is https://iam.cloud.ibm.com/identity/token
discovery = DiscoveryV1(version='2019-04-30',
authenticator=authenticator)
discovery.set_service_url('<url_as_per_region>')
from ibm_watson import IAMTokenManager
# In your API endpoint use this to generate new bearer tokens
iam_token_manager = IAMTokenManager(apikey='<apikey>')
token = iam_token_manager.get_token()
from ibm_watson import DiscoveryV1
from ibm_cloud_sdk_core.authenticators import BearerTokenAuthenticator
# in the constructor, assuming control of managing the token
authenticator = BearerTokenAuthenticator('your bearer token')
discovery = DiscoveryV1(version='2019-04-30',
authenticator=authenticator)
discovery.set_service_url('<url_as_per_region>')
from ibm_watson import DiscoveryV1
from ibm_cloud_sdk_core.authenticators import BasicAuthenticator
authenticator = BasicAuthenticator('username', 'password')
discovery = DiscoveryV1(version='2019-04-30', authenticator=authenticator)
discovery.set_service_url('<url_as_per_region>')
from ibm_watson import DiscoveryV1
from ibm_cloud_sdk_core.authenticators import NoAuthAuthenticator
authenticator = NoAuthAuthenticator()
discovery = DiscoveryV1(version='2019-04-30', authenticator=authenticator)
discovery.set_service_url('<url_as_per_region>')
To use the SDK through a third party cloud provider (such as AWS), use the MCSPAuthenticator. This will require the base endpoint URL for the MCSP token service (e.g. https://iam.platform.saas.ibm.com) and an apikey.
from ibm_watson import AssistantV2
from ibm_cloud_sdk_core.authenticators import MCSPAuthenticator
# In the constructor, letting the SDK manage the token
authenticator = MCSPAuthenticator('apikey', 'token_service_endpoint')
assistant = AssistantV2(version='2023-06-15',
authenticator=authenticator)
assistant.set_service_url('<url_as_per_region>')
Tested on Python 3.9, 3.10, and 3.11.
If you have issues with the APIs or have a question about the Watson services, see Stack Overflow.
To set client configs like timeout use the set_http_config() function and pass it a dictionary of configs. See this documentation for more information about the options. All options shown except method, url, headers, params, data, and auth are configurable via set_http_config(). For example for a Assistant service instance
from ibm_watson import AssistantV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator
authenticator = IAMAuthenticator('your apikey')
assistant = AssistantV1(
version='2021-11-27',
authenticator=authenticator)
assistant.set_service_url('https://api.us-south.assistant.watson.cloud.ibm.com')
assistant.set_http_config({'timeout': 100})
response = assistant.message(workspace_id=workspace_id, input={
'text': 'What\'s the weather like?'}).get_result()
print(json.dumps(response, indent=2))
To use the SDK with any proxies you may have they can be set as shown below. For documentation on proxies see here
See this example configuration:
from ibm_watson import AssistantV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator
authenticator = IAMAuthenticator('your apikey')
assistant = AssistantV1(
version='2021-11-27',
authenticator=authenticator)
assistant.set_service_url('https://api.us-south.assistant.watson.cloud.ibm.com')
assistant.set_http_config({'proxies': {
'http': 'http://10.10.1.10:3128',
'https': 'http://10.10.1.10:1080',
}})
To send custom certificates as a security measure in your request, use the cert property of the HTTPS Agent.
from ibm_watson import AssistantV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator
authenticator = IAMAuthenticator('your apikey')
assistant = AssistantV1(
version='2021-11-27',
authenticator=authenticator)
assistant.set_service_url('https://api.us-south.assistant.watson.cloud.ibm.com')
assistant.set_http_config({'cert': ('path_to_cert_file','path_to_key_file')})
For ICP(IBM Cloud Private), you can disable the SSL certificate verification by:
service.set_disable_ssl_verification(True)
Or can set it from extrernal sources. For example set in the environment variable.
export <service name>_DISABLE_SSL=True
To set the base service to be used when contacting the service
service.set_service_url('my_new_service_url')
Or can set it from extrernal sources. For example set in the environment variable.
export <service name>_URL="<your url>"
Custom headers can be passed in any request in the form of a dict as:
headers = {
'Custom-Header': 'custom_value'
}
For example, to send a header called Custom-Header to a call in Watson Assistant, pass
the headers parameter as:
from ibm_watson import AssistantV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator
authenticator = IAMAuthenticator('your apikey')
assistant = AssistantV1(
version='2018-07-10',
authenticator=authenticator)
assistant.set_service_url('https://gateway.watsonplatform.net/assistant/api')
response = assistant.list_workspaces(headers={'Custom-Header': 'custom_value'}).get_result()
If you would like access to some HTTP response information along with the response model, you can set the set_detailed_response() to True. Since Python SDK v2.0, it is set to True
from ibm_watson import AssistantV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator
authenticator = IAMAuthenticator('your apikey')
assistant = AssistantV1(
version='2018-07-10',
authenticator=authenticator)
assistant.set_service_url('https://gateway.watsonplatform.net/assistant/api')
assistant.set_detailed_response(True)
response = assistant.list_workspaces(headers={'Custom-Header': 'custom_value'}).get_result()
print(response)
This would give an output of DetailedResponse having the structure:
{
'result': <response returned by service>,
'headers': { <http response headers> },
'status_code': <http status code>
}
You can use the get_result(), get_headers() and get_status_code() to return the result, headers and status code respectively.
Every SDK call returns a response with a transaction ID in the X-Global-Transaction-Id header. Together the service instance region, this ID helps support teams troubleshoot issues from relevant logs.
from ibm_watson import AssistantV1
service = AssistantV1(authenticator={my_authenticator})
response_headers = service.my_service_call().get_headers()
print(response_headers.get('X-Global-Transaction-Id'))
from ibm_watson import AssistantV1, ApiException
try:
service = AssistantV1(authenticator={my_authenticator})
service.my_service_call()
except ApiException as e:
print(e.global_transaction_id)
# OR
print(e.http_response.headers.get('X-Global-Transaction-Id'))
However, the transaction ID isn't available when the API doesn't return a response for some reason. In that case, you can set your own transaction ID in the request. For example, replace <my-unique-transaction-id> in the following example with a unique transaction ID.
from ibm_watson import AssistantV1
service = AssistantV1(authenticator={my_authenticator})
service.my_service_call(headers={'X-Global-Transaction-Id': '<my-unique-transaction-id>'})
The Text to Speech service supports synthesizing text to spoken audio using web sockets with the synthesize_using_websocket. The Speech to Text service supports recognizing speech to text using web sockets with the recognize_using_websocket. These methods need a custom callback class to listen to events. Below is an example of synthesize_using_websocket. Note: The service accepts one request per connection.
from ibm_watson.websocket import SynthesizeCallback
class MySynthesizeCallback(SynthesizeCallback):
def __init__(self):
SynthesizeCallback.__init__(self)
def on_audio_stream(self, audio_stream):
return audio_stream
def on_data(self, data):
return data
my_callback = MySynthesizeCallback()
service.synthesize_using_websocket('I like to pet dogs',
my_callback,
accept='audio/wav',
voice='en-US_AllisonVoice'
)
If your service instance is of CP4D, below are two ways of initializing the assistant service.
The SDK will manage the token for the user
from ibm_watson import AssistantV1
from ibm_cloud_sdk_core.authenticators import CloudPakForDataAuthenticator
authenticator = CloudPakForDataAuthenticator(
'<your username>',
'<your password>',
'<authentication url>', # should be of the form https://{icp_cluster_host}{instance-id}/api
disable_ssl_verification=True) # Disable ssl verification for authenticator
assistant = AssistantV1(
version='<version>',
authenticator=authenticator)
assistant.set_service_url('<service url>') # should be of the form https://{icp_cluster_host}/{deployment}/assistant/{instance-id}/api
assistant.set_disable_ssl_verification(True) # MAKE SURE SSL VERIFICATION IS DISABLED
from ibm_watson import AssistantV1
from ibm_cloud_sdk_core.authenticators import BearerTokenAuthenticator
authenticator = BearerTokenAuthenticator('your managed access token')
assistant = AssistantV1(version='<version>',
authenticator=authenticator)
assistant.set_service_url('<service url>') # should be of the form https://{icp_cluster_host}/{deployment}/assistant/{instance-id}/api
assistant.set_disable_ssl_verification(True) # MAKE SURE SSL VERIFICATION IS DISABLED
import logging
logging.basicConfig(level=logging.DEBUG)
This would show output of the form:
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): iam.cloud.ibm.com:443
DEBUG:urllib3.connectionpool:https://iam.cloud.ibm.com:443 "POST /identity/token HTTP/1.1" 200 1809
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): gateway.watsonplatform.net:443
DEBUG:urllib3.connectionpool:https://gateway.watsonplatform.net:443 "POST /assistant/api/v1/workspaces?version=2018-07-10 HTTP/1.1" 201 None
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): gateway.watsonplatform.net:443
DEBUG:urllib3.connectionpool:https://gateway.watsonplatform.net:443 "GET /assistant/api/v1/workspaces/883a2a44-eb5f-4b1a-96b0-32a90b475ea8?version=2018-07-10&export=true HTTP/1.1" 200 None
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): gateway.watsonplatform.net:443
DEBUG:urllib3.connectionpool:https://gateway.watsonplatform.net:443 "DELETE /assistant/api/v1/workspaces/883a2a44-eb5f-4b1a-96b0-32a90b475ea8?version=2018-07-10 HTTP/1.1" 200 28
To get low level information of the requests/ responses:
from http.client import HTTPConnection
HTTPConnection.debuglevel = 1
python_dateutil >= 2.5.3websocket-client 1.1.0ibm_cloud_sdk_core >= 3.16.2See [CONTRIBUTING.md][contributing].
This library is licensed under the [Apache 2.0 license][license].
FAQs
Client library to use the IBM Watson Services
We found that ibm-watson demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 3 open source maintainers collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
In this segment of the Risky Business podcast, Feross Aboukhadijeh and Patrick Gray discuss the challenges of tracking malware discovered in open source softare.
Research
Security News
A threat actor's playbook for exploiting the npm ecosystem was exposed on the dark web, detailing how to build a blockchain-powered botnet.
Security News
NVD’s backlog surpasses 20,000 CVEs as analysis slows and NIST announces new system updates to address ongoing delays.