EINSTEIN LANGUAGE IS BETA!
We're excited to announce Einstein Language, a powerful set of new APIs that allow developers of all skill levels to integrate natural language processing into their applications. Developers can now leverage two new APIs, Einstein Sentiment and Einstein Intent, to unlock powerful insights within text.
 
EINSTEIN LANGUAGE
Build smarter apps with natural language processing.
• Einstein Sentiment (Beta) allows developers to classify the sentiment of text into positive, negative, and neutral classes.
• Einstein Intent (Beta) is a customizable natural language processing service that allows developers to categorize unstructured text into user defined labels to better understand and prioritize customers’ needs across channels. 
 
• Einstein Language Technical Docs: https://metamind.readme.io/docs/intro-to-einstein-language

Please use this forum to provide feedback, success stories, and service questions.

-Einstein.ai Team

Having trouble with the sign-up process for the new Predictive Vision Service?  Please let us know here and we will work to help you through the process.  

Thanks!
 

Having trouble with the sign-up process for the new Predictive Vision Service?  Please let us know here and we will work to help you through the process.  

Thanks!
 

I'm attempting to retrain an evisting vision model using additional feedback. I've also tried creating a new model for the dataset.

In both cases I was using a trainParams of:

'{"withFeedback": true}'

The existing model has a SUCCEEDED status but shows no sign that the feedback was incoperated.

The new model ends up with the failureMsg:

"java.lang.IllegalArgumentException: The dataset example referenced examples/1010273-4e2abc4183fd732aae779a1a3a3cb088de02898ec2fce61aee921df31675a676 does not exist"

Has something got corrupted within my dataset? Should I just start again with a new dataset?
 

Hello All, 

Trying to get hang on Vision API . I am following this link : https://metamind.readme.io/docs/apex-qs-create-vf-page

I have generated my oauth token through here : https://api.einstein.ai/token

I am trying to create dataset, all I get is 400 bad request. I am using postman and trying this with a einstein enabled developer edition. 

What am i doing wrong here?




 

I am trying to start with salesforce einsten Can anyone please help me with this. In few posts i could see that i need to have einsten license to start. is there any way to start without paying? Need to try few things that could get me started.

This may simply just not be available yet, didn't see it in any of the doc surrounding training a model.  

You can specify what percentage of the dataset gets used for training with the remainder being used for testing.  Is there any mechanism to explicitly define a dataset to use for training and another dataset to be used for testing?  

It would seem like this would be valuable for tuning the model, having a static test data set to always test against while being able to modify the training dataset to increase the accuracy.

Hi, I tried the CURL commands for Einstein Language Intent following the examples in https://metamind.readme.io/ for uploading datasets, training them and predicting and they worked just fine in bash Terminal. However, I'm unable to find the method in HttpRequest class in Apex to replace -F in curl commands like in the example
curl -X POST -H "Authorization: Bearer <TOKEN>" -H "Cache-Control: no-cache" -H "Content-Type: multipart/form-data" -F "path=http://einstein.ai/text/case_routing_intent.csv" -F "type=text-intent" https://api.einstein.ai/v2/language/datasets/upload

Please help me implement Language Intent.

I have been trying to use the Intent Web Service and I am able to get a 200 and Response when I POST from cURL and SOAPUI. However, when I construct the request body in APEX and POST am getting a Error - 400 which is a generic BAD request response. I have inspected the requests from cURL and my Apex anonymous code and both are identical. Not sure why I am getting this error. With limited error message details (since Language is still in Beta) am unable to proceed. Below are screenshots from requestbin -

POST from Salesforce -



POST from cURL -

EINSTEIN LANGUAGE IS BETA!
We're excited to announce Einstein Language, a powerful set of new APIs that allow developers of all skill levels to integrate natural language processing into their applications. Developers can now leverage two new APIs, Einstein Sentiment and Einstein Intent, to unlock powerful insights within text.
 
EINSTEIN LANGUAGE
Build smarter apps with natural language processing.
• Einstein Sentiment (Beta) allows developers to classify the sentiment of text into positive, negative, and neutral classes.
• Einstein Intent (Beta) is a customizable natural language processing service that allows developers to categorize unstructured text into user defined labels to better understand and prioritize customers’ needs across channels. 
 
• Einstein Language Technical Docs: https://metamind.readme.io/docs/intro-to-einstein-language

Please use this forum to provide feedback, success stories, and service questions.

-Einstein.ai Team

I get response as System.HttpResponse[Status=Forbidden, StatusCode=403] when i Quick start with eienstien vision trail

Hi,
I am trying to find the quickest way to convert Salesforce Solutions attached to Cases into Knowledge base. I have around 10k cases in my Salesforce org. The manual way is to go through each case and solution and identify similar solutions. Export them and import as Articles into Knowledge Base.
However, going through 10k cases manually is time consming. Can anyone suggest me better option of doing this?
Currently, I am trying to find a way using Salesforce Eintstein to seggregate solutions. Once this is done then it is easy to import them as articles in Knowledge Base. Am I going in right direction?
 

Hi,


I am getting above error while training the dataset. The dataset which I have used is from Einstein vision (mountainvsbeach). Also I have checked, the images are no longer than 2000 pixel.

 

Hello Everyone

I was going through the Einstein Vision API's and the process its working on. Its a really cool application of AI. I was going through a particular use case where I was trying to count the number of objects in a particular image, but the result that the API's returns is in some probability number, I could not figure out how to count the no. of objects using the output given by the Vision API's. Could anyone of you help me with this particular problem. Thanks in advance.

Thanks And Regards
Sumit Sharma
Mirketa Inc
 

Is it possible to update trained dataset in einstein API?

Having trouble with the sign-up process for the new Predictive Vision Service?  Please let us know here and we will work to help you through the process.  

Thanks!