ibm-watson

问题 While we have had good success with Bluemix Java SDK in the general case, we've bumped into problems while trying to recognize occasional non-English words (e.g., foreign last names). Our hope was that one could specify the keyword list using SPR phonetic notation (which works great for text2speech), but that does not seem to be supported for speech2text. Any suggestions/workarounds? SpeechToText service = new SpeechToText(); service.setUsernameAndPassword("USERNAME", "PASSWORD"); File audio

问题 AlchemyLanguage used to return the number of API transactions that took place during any call, this was particularly useful when making a combined call. I do not see the equivalent way to get those results per REST call. Is there any way to track or calculate this? I am concerned about things like some of the sub-requests like when you ask for sentiment on entities does that count as two, or one plus an additional call per recognized entity? 回答1: There's currently no way to track the

问题 In reviewing the API documentation, I didn't see a way to jump into a specific area of a Watson Dialog template. This might be useful if you determine a user's intent (e.g. using Watson Natural Language Classifier) and want to go directly to the relevant section of a comprehensive Watson Dialog template. Is there a way to do this or is it better to have a separate dialog for each possible entry point or is there some other way to think about this? 回答1: You would simply pass that input node in

问题 I've already gotten a token on the server side and stored it in a cookie, but I can't seem to figure out why I'm getting an error when I query the api with that token. Here's the jQuery ajax request I'm sending: $.ajax({ url:'https://gateway.watsonplatform.net/tone-analyzer/api/v3/tone', data:{ 'X-Watson-Authorization-Token':readCookie('token'), 'text':input, 'version':'v3', 'version_date':'2016-05-19' }, dataType:'jsonp', contentType:'application/json', method:'GET', success:function(tone){

问题 I am not getting the answer from Retrieve and Rank which is a perfect match to the question( I get the perfectly matched answer in the Retrieve and Rank WebUI. The data is trained with 80 questions, creating a ranker will help in getting the perfectly matched answer ? And can I create a ranker with only 80 questions instead of 150 questions, as stated in the documentation? I would like to use the curl command to create a ranker using the curl command : curl -X POST -u "{username}":"{password}

问题 Having trouble adding a class to one of my custom classifiers using Visual Recognition, when executing the task I get the below error: status: 500, error: If you are seeing this message, you are likely making an excessive number of concurrent HTTP connections to this service. Please check the concurrency limits for your assigned service tier. Does anyone know what this means or where I can manage my "concurrency limits"? Edit: This is the code I'm using to make the call of adding a new class.

问题 I'm using Watson Conversation. I get an exception when trying to execute a ServiceCall, at line 90 of ResponseUtils (in getObject): final T model = GsonSingleton.getGsonWithoutPrettyPrinting().fromJson(reader, type); com.google.gson.JsonSyntaxException: java.lang.IllegalStateException: Expected a string but was BEGIN_ARRAY at line 1 column 647 path $.output.text I explore the response and I see this: Response{protocol=http/1.1, code=200, message=OK, url= https://gateway.watsonplatform.net

问题 I have an application built on .NET Framework using MVC 5 and SQL Server 2008 R2 Enterprise Edition which I want to deploy on Bluemix. Does Bluemix Support .NET. If I deploy my .NET application on Bluemix, would it work? I have Virtual Servers hosting the application and data for my Application on a separate hosting provider. If I deploy some components of my application (built on Bluemix supported technologies such as Java/ php/ node.js/ DB2) on Bluemix, will I still be able to communicate

问题 I am trying to use the IBM personality insights service inside a for loop. def generateToken(username, password): r = requests.get("https://gateway.watsonplatform.net/authorization/api/v1/token?url=https://gateway.watsonplatform.net/personality-insights/api", auth=(username, password)) if r.status_code == requests.codes.ok: return r.text def personalityRequest(text, token): base_url='https://gateway.watsonplatform.net/personality-insights/api/v3/profile?version=2017-08-17&consumption

问题 I am doing PCA on CIFAR 10 image on IBM WATSON Studio Free version so I uploaded the python file for downloading the CIFAR10 on the studio pic below. But when I trying to import cache the following error is showing. pic below- After spending some time on google I find a solution but I can't understand it. link https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/add-script-to-notebook.html the solution is as follows:- Click the Add Data icon (Shows the Add Data icon), and then