I have created a new node for Node-RED to get access to Watson Alchemy News functionality.
This nodes allows to define 'free queries' and simpler 'assisted ones' to look for the news content. Alchemy News API provides many different fields which can be queried or used as an output.
Could you help me deciding which are the most used/interesting fields to have them included in the assistant?
Thanks.
Related
How can I use the Watson Assistant "listLogs" API Function to list the user conversations from a specific assistant ? We have one skill linked to three assistants for our environments (DEV/TEST/PROD), and I want to retrieve the conversations from PROD assistant only. What filters do I have to use ?
What I already tried:
When using the listLogs function with just the "workspace_id" as parameter, it is returning just an empty list.
When using the listAllLogs function with a filter parameter (language::de,workspace_id::my-workspace-id), the resulting list is empty as well
When using the listAllLogs function with another filter parameter (language::de,meta.conversation.assistant_and_skill_reference::"my-assistant-id:main+skill"), again an empty list is returned
As the skill is used in live chatbot, there are thousands of logged conversations, all visible in the Analytics tab of the Watson Assistant console, so the data is definitely there.
UPDATE: This is the out from the Watson Conversation Tool, it's empty
I finally got the information from IBM Support that this is currently not possible.
Okay so I’m need guidance on where to start.
What I want to do is upon clicking a button in my web app which will be labelled “search” the web app will connect to my realism database and search the data base for the “search criteria” and the once found all matching cases it will create div blocks with the information inside it, in a list view and assign the ID of the div to the UID it gets back from the database.
database:
Users
--> Country
---->State
----->City
------>Post/ZipCode
------->UID
--------> Users informantion
Welcome to StackOverflow!
A great place to get started is the Firebase Realtime Database doocumentation or searching for Firecasts on YouTube (linked below).
As requested, here are some questions to ask yourself to get started and help scope out and define your new Firebase project.
What language are you going to use?
Are you planning on using any frameworks/libraries? e.g. For Javascript, these would include things like jQuery, Polymer, and React
What information are you storing in your database? e.g. user profiles, private user data/settings, public indexes, username lists, etc.
How is your database structured?
What data is being searched? The entire database? Values in a certain location?
What data needs to be displayed in your view?
Is the data accessible for just the current user or is it a public database that anyone can use?
What search criteria will be used? Is it just one filter at a time or many?
The answers to these questions aren't set in stone, but are to help you start thinking about the future of your project. They can be changed at any time as this isn't SQL where everything has to have its own schema.
If you intend on using "advanced searches" where you'll filter by multiple parameters at the same time, consider using Cloud Firestore instead.
I recommend looking at some Firecasts to help guide you through these questions. Here are some links to them:
Firebase YouTube Channel
Video: Getting Started with the Firebase Realtime Database on the Web
Playlist: Firebase on the Web
Is it possible to build one Google data studio report (i.e., template) and use a URL that links it to a specific data-set or defines a hidden filter that creates a sample of a larger data set?
I understand Data Control allows this for users operating under the same Google domain.
However, I want to provide multiple university student teams with their personal information but not allow the other teams to see or filter for information that they should not see. Ideally I could simply share a customised URL with each team that takes care of this filtering/sampling.
Any guidance appreciated - many thanks!
You can do this with custom bookmarks and URL parameters.
I would like to code something up where my employees can call in and Watson will ask them the important questions, and they can just tell Watson the information and Watson then output that information into a CSV, XLS or etc. format possibly even a database.
It seems that I should be able to do this because of the way it can converse with people through messenger etc.
I know it is probably a 3 pronged approach.
Ideas?
#Florentino DeLaguna, in this case, you can use Conversation Service and Text to Speech and Speech to text API's from IBM Watson. See options you can use for that:
In theory, you would have to built an application that integrates with one URA (using Asterisk for example), convert the Speech to Text, send that text for Conversation Service, and the response of the Conversation you would have to transform into voice and send to the URA . In practice, there are some conversational problems, especially from Speech to Text. But the return voice you can use some effects using the IBM Watson Text to Speech (faster and slower voices, control of pauses, put emotions ...).
Obs.: The URA audios are in narrowband, 8khz, and most Speech to Text services only accept broadband, 16khz.
Obs II.: You app (like Asterisk) need to be able to consume a REST API and / or make use of Web Sockets then it will be able to invoke the Watson Speech to Text service.
Another option is to route a call out of Asterisk to the new IBM Voice Gateway which is a SIP endpoint that fronts a Watson self-service agent by orchestrating Speech To Text, Text To Speech and the Watson Conversation service. You can think of IBM Voice Gateway as a stand alone, Cognitive IVR system. Go here for more details.
Another potential option is to use MRCP. IBM has a services solution that will allow you to reach the Watson STT and TTS engines using MRCP. Not sure if Asterisk supports MRCP but that is typically how traditional IVRs integrate with ASRs.
Important: The options 2 and 3 are answered for another person, see the official answer.
See more about these API's:
Speech to Text
Text to Speech
Conversation
Have a look to the Voximal solution, it integrates all the SpeechToText Cloud API (and TextToSpeech) as an Asterisk application throw a VoiceXML standard browser.
All is integrated in the VoiceXML interpreter, you got the full text result of the transcription, and you can push it to a chatbot to detect the intent of the users and pick dynamic parameters like date, number, city, and more... for example by using api.ai.
Voximal supports the STT from Google, Microsoft, IBM/watson (and soon Amazon).
The 3 API listed by Sayuri are embedded in the solution.
In an ecommerce website, users can bookmark products and bookmark other users.
I'd like to display a custom feed of products for logged-in users.
Questions:
1) How to get products user would like most, based on the similarity of products they bookmarked.
2) What services should best fit this use case?
I though in 'retrieve-and-rank' as starting point, but maybe 'Personality Insights' also should be used in conjunction with retrieve-and-rank.
Can you provide a simple code or query as example?
There is one example available in Watson Starter kit "Answer Retrieval app" to customize R&R.Below is the link
https://github.com/watson-developer-cloud/answer-retrieval