google-assistant-sdk

问题 I am trying to install Google Assistant on OSX with Python 3.6. I successfully ran this command: python3 -m pip install "google-assistant-sdk[samples]" But when I run this command with the path to the JSON file from the Google Cloud Platform: python3 -m googlesamples.assistant.auth_helpers --client-secrets /path-to/secret.json I get this error: /usr/local/opt/python3/bin/python3.6: No module named googlesamples.assistant.auth_helpers Also here's the python3.6/site-packages folder: Terminal

问题 The Google Assistant SDK example requires the user to hit enter before speaking to the Google Assistant. I was wondering is there a way to wire a button to one of the RPI GPIO pins and have it trigger G.Assistant. while True: if wait_for_user_trigger: click.pause(info='Press Enter to send a new request...') continue_conversation = assistant.converse() # wait for user trigger if there is no follow-up turn in # the conversation. wait_for_user_trigger = not continue_conversation # If we only

问题 The Google Assistant SDK example requires the user to hit enter before speaking to the Google Assistant. I was wondering is there a way to wire a button to one of the RPI GPIO pins and have it trigger G.Assistant. while True: if wait_for_user_trigger: click.pause(info='Press Enter to send a new request...') continue_conversation = assistant.converse() # wait for user trigger if there is no follow-up turn in # the conversation. wait_for_user_trigger = not continue_conversation # If we only

问题 I'm making a google assistant with my Raspberry Pi 3 and I'm just trying make an LED turn on and off like in the docs (https://developers.google.com/assistant/sdk/guides/service/python/extend/handle-device-commands) but when I run this command googlesamples-assistant-pushtotalk to test it, I get an error: (env) pi@raspberrypi:~ $ googlesamples-assistant-pushtotalk INFO:root:Connecting to embeddedassistant.googleapis.com WARNING:root:Device config not found: [Errno 2] No such file or directory

问题 i am new to google actions and dialogflow. Here i want to send notification to google assistant. But i am getting TypeError: Cannot read property 'access_token' of undefined const { google } = require('googleapis'); const key = require('./myapp.json'); let jwtClient = new google.auth.JWT( key.client_email, null, key.private_key, ['https://www.googleapis.com/auth/actions.fulfillment.conversation'], null ); jwtClient.authorize((err, tokens) => { let notif = { userNotification: { title: "message

问题 I'm developing an Action, let's call it "foo". It's a grocery list, so users should be able to explicitly invoke it like so: "ask foo to add milk" (fails) "ask foo add milk" (works, but grammatically awful) "tell foo add milk" (fails, even though it's basically identical to the above?) "talk to foo" ... "add milk" (works, but awkward) I've defined "add {item} to my foo list" and "add {item}" (as well as many others) as training phrases in Dialogflow. So it seems like everything should be

问题 I am currently working on a project that uses the Google Assistant SDK with Python. I have it working with direct audio listening, but I want to know if there is a way to use it with raw text input instead of listening to audio. 回答1: This is, apparently, a common request - but there is no way to do it yet. (Given this is still an early Developer Preview, and there have been many requests for this, we can hope they'll deliver it as part of a forthcoming update.) 来源： https://stackoverflow.com

问题 I successfully created EmbeddedAssistantStub using the below code. EmbeddedAssistantGrpc.EmbeddedAssistantStub mAssistantService = EmbeddedAssistantGrpc.newStub(channel) .withCallCredentials(MoreCallCredentials.from( Credentials.fromResource(mClientId,mRefreshToken,mAccessToken) )); After this i passed audio data to StreamObserver, At that time below exxception was occured. Line 3378: 12-07 12:59:25.099 1917 4286 E GASample: io.grpc.StatusRuntimeException: UNAUTHENTICATED: Request is missing

问题 I am trying to figure out how I can embed Google Actions responses, such as the cards carousel, in a webhook response for DialogFlow. According to the documentation, the structure looks as following: "carouselSelect": { "items": [ { "optionInfo": { "key": "MATH_AND_PRIME", "synonyms": [ "math", "math and prime", "prime numbers", "prime" ] }, "title": "Math & prime numbers", "description": "42 is an abundant number because the sum of its proper divisors 54 is greater...", "image": { "url":

问题 I am trying ever so hard to get the Google Assistant on my Windows 10 PC. I am up to the "Register Device" part. Developers.google.com Says to run the following command to register your device. googlesamples-assistant-devicetool register-model --manufacturer "Assistant SDK developer" \ --product-name "Assistant SDK light" --type LIGHT --model my-model Which i conclude for Windows (and me) is: googlesamples-assistant-devicetool register-model --manufacturer "Assistant SDK developer" --product