ibm-watson

I'm using Ratchet to connect to IBM Watson websockets, and it always seems to work fine for smaller files (I've tested up to a 66-minute 23 MB mp3 file), but it always fails for larger files (such as 2-hour 56 MB mp3). This is my log: [2019-03-17 21:43:23] local.DEBUG: \Ratchet\Client\connect bf4e38983775f6e53b392666138b5a3a50e9c9c8 [2019-03-17 21:43:24] local.DEBUG: startWatsonStream options = {"content-type":"audio\/mpeg","timestamps":true,"speaker_labels":true,"smart_formatting":true,"inactivity_timeout":-1,"interim_results":false,"max_alternatives":1,"word_confidence":false,"action":"start

When making a post cURL request as below to try and continue a created conversation watson instead returns a new conversation. curl -u "USERNAME":"PASSWORD" -X POST --form conversation_id=CONVOID --form client_id=CLIENTID --form input="What type of toppings do you have?" "https://gateway.watsonplatform.net/dialog/api/v1/dialogs/DIALOGID/conversation" If i use the below cURL it works fine. curl -u "USERNAME":"PASSWORD" --data "conversation_id=CONVOID&client_id=CLIENTID&input=What type of toppings do you have?" https://gateway.watsonplatform.net/dialog/api/v1/dialogs/DIALOGID/conversation My

I'm failing to be able to play audio when making an "AJAX" request to my server side api. I have backend Node.js code that's using IBM's Watson Text-to-Speech service to serve audio from text: var render = function(request, response) { var options = { text: request.params.text, voice: 'VoiceEnUsMichael', accept: 'audio/ogg; codecs=opus' }; synthesizeAndRender(options, request, response); }; var synthesizeAndRender = function(options, request, response) { var synthesizedSpeech = textToSpeech.synthesize(options); synthesizedSpeech.on('response', function(eventResponse) { if(request.params.text

I am using this, but this only sets it to empty, { "context": { "time": "", "place": "", "things": "", "transport": "" }, "output": {} } I also tried "time": "null" and "time": "$time.remove" For those using Watson Assistant on an older API version: The best is to use context.remove() in the output section . I usually have an extra child node for cleanup. { "output": { "text": {}, "deleted": "<? context.remove('eventName') ?> <? context.remove('queryPredicate') ?>" } } Because deleted is not part of the context section it won't be carried forward. For those on recent API versions of Watson

I have a spring mvc application and I would like to make my user call a bot and the bot based on user input should access a url and based on the response provide an answer.How could I achieve this in Java? There is no direct way to do it. However, Watson Conversation does provide a mechanism to handle such requests. You will need to tell the calling Java app that a url needs to be invoked. This is done by using two features: Context.request skip_user_input A request is a special context variable that has args, name and result. It is used to tell the calling app that it should do some action