Page tree

Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

  • Open Business and Artificial Intelligence Connectivity (OBAIC) borrows the concept from Open Database Connectivity (ODBC), which is an interface that makes it possible for applications to access data from a variety of database management systems (DBMSs). The aim of OBAIC is to define an interface allowing BI tools to access machine learning models from models and to run inferencing against those models on a variety of different AI platforms from a variety of AI platforms - “AI ODBC for BI” 
  • Through OBAIC, BI vendors can connect to any AI platform freely without concerning about themselves with the underlying implementation and , or how does the AI platform train trains the model or infer the resultinfers results. It's just like what we used to have for database with use for databases via ODBC - the caller doesn't need to concern about how the database store stores the data and or execute the queryqueries.
  • The committee has decided this standard will only define the REST APIs protocol of how AI and BI communicate. The design or the actual implementation of OBAIC, such as whether this should be Server VS Servervs Server-less VS Docker, will leave it be left up to the vendor to provide, or if implementing vendors. If this protocol grows to another open-sourced project to , that team may provide such implementation guidance/example(s)
  • There are 3 key aspects when designing this standard designed into this standard: 
    • BI - what What specific call do I need this standard to provide so that I can better leverage any underlying the AI/ML platform counterpart?
    • AI - what What should be the common denominator be for an AI platform should that can provide to support for this standard?
    • Data - Shall data be moved around in the communication between AI and BI (passed by value) or keep will the data in the same remain in it's source location (passed by reference)?

All of the REST APIs call presented below use bearer tokens for authorization. The {prefix} of each API is configurable in the hosted servers. This protocol is inspired by Delta Sharing.

SwaggerHub API (Will port this document to SwaggerHub AFTER we confirm the design)

https://app.swaggerhub.com/apis-docs/cupidchan/OBAIC/1.0.0-oas3

Protocol - Training

* Blue text below, either in the diagram or in the description, means it's out of scope of OBAIC and it's up to the BI tool, AI Platform or Data source vendor to implement. OBAIC is the connecting tissue to coordinate the communications among them to extend the capability of these 3 major components


  1. An End User analyzes is analyzing data using their BI Tools Tool and found out determines that predictive analytics on those for the data set would be valuable and they wish to train a model with the data for that purpose.  This step is the traditional step when a user interacts with BI.
  2. (a) Obtain a token a token with token with permission associated to the user making the request. This token is going to pass to AI allowing the access to the training data with a SQL statement running against the datastore. (b) BI tool, on behalf of the user, requests AI platform through OBAIC, to train/prepare a model that accepts features of a certain type (numeric, categorical, text, etc.)

    Expand
    titleAPI to train model using provided dataset

    Model configuration is based on configs from the open-source Ludwig project. At a minimum, we should be able to define inputs and outputs in a fairly standard way. Other model configuration parameters are subsumed by the options field.

    The data stanza provides a bearer token allowing the ML provider to access the required data table(s) for training. The provided SQL query indicates how the training data should be extracted from the source.

    Don't be confused with the Bearer token which is used to authenticate with OBAIC, and the dbToken which is created in 2(a) and AI platform will use that to access the data source for training

    HTTP RequestValue
    Method

    POST

    Header

    Authorization: Bearer {token}

    URL

    {prefix}/models/

    Query Parameters

    {

      "dbToken": "D41C4A382C27A4B5DF824E2D4F148";
      "inputs":[
        {
          "name":"customerAge",
          "type":"numeric"
        },
        {
          "name":"activeInLastMonth",
          "type":"binary"
        }
      ],
      "outputs":[
        {
          "name":"canceledMembership",
          "type":"binary"
        }
      ],
      "modelOptions": {

          “providerSpecificOption”: “value”

       },
      "data":{
          "sourceType":"snowflake",
          "endpoint":"some/endpoint",
          "bearerToken":"...",
          "query":"SELECT foo FROM bar WHERE baz"
      }
    }



    Expand
    titleAlternatively, we may also consider to support SQL-like syntax for Model Training

    If we go beyond just REST API, SQL-like is an alternative as the syntax is also well-known

    Use BigQuery ML model creation as an example and generalizing

    CREATE MODEL (
      customerAge WITH ENCODING (
        type=numeric
      ),
      activeInLastMonth WITH ENCODING (
        type=binary
      ),
      canceledMembership WITH DECODING (
        type=binary
      )
    )
    FROM myData (
      sourceType=snowflake,
      endpoint="some/endpoint",
      bearerToken=<...>,

    AS (SELECT foo FROM BAR)
    WITH OPTIONS ();



    Expand
    title200: Training is started and the corresponding ID is return for future reference


    HTTP ResponseValue
    HeaderContent-Type: application/json; charset=utf-8
    Body

    {
      "modelID": "d677b054-2cd4-4711-959b-971af0081a73"
    }

    • modelID is generated and returned to the caller if training is started successfully. This will be used to check the status of the training, or for future Inference (see Inference section below)



  3. AI Platform provider provides the implementation to fulfill the request by connecting to the datasource with the provided token and the set of training data specified in SQL. This step is up to how the AI platform interacts with the data source to performance the training. 
  4. BI tool polls for the status or retrieve the training result. If the training is still in progress, the status will be returned. When training is completed, results and performance of the model will be returned.

    Expand
    titleAPI to get model status


    HTTP RequestValue
    Method

    GET

    Header

    Authorization: Bearer {token}

    URL

    {prefix}/modelStatus?modelID=

    Query Parameters

    modelID (type: String): The modelID returned from previous OBAIC call either from training or list of Models.



    Expand
    title200: Status of the Model returned


    HTTP ResponseValue
    HeaderContent-Type: application/json; charset=utf-8
    Body

    {
      "modelID": "d677b054-2cd4-4711-959b-971af0081a73",

      "status": "training",

      "progress": "80",
    }

    • modelID is same ID provided in the request
    • status can be training | inferencing | ready
    • progress is the estimated progress of the current status



  5. BI tool presents the result to the user in their own way, which is the "secret sauce" and unique to each other.

Protocol - Inference

1. When a BI user wants to extend its capability to AI, it reaches out to AI platform and request for requests a list of available models of which the credential of the provided token is authorized to see

Expand
titleAPI to list models accessible to the recipient


HTTP RequestValue
Method

GET

Header

Authorization: Bearer {token}

URL

{prefix}/models/{model}

Query Parameters

maxResults (type: Int32, optional): The maximum number of results per page that should be returned. If the number of available results is larger than maxResult, the response will provide a nextPageToken that can be used to get the next page of results in subsequent list requests. The server may return fewer than maxResults items even if there are more available. The client should check nextPageToken in the response to determine if there are more available. Must be non-negative. 0 will return no results but nextPageToken may be populated.

pageToken (type: String, optional): Specifies a page token to use. Set pageToken to the nextPageToken returned by a previous list request to get the next page of results. nextPageToken will not be returned in a response if there are no more results available.


...

2. After the list of models is returnreturned, the BI user can selectively retrieve the detail of the model(s). This step can also be called right after the newly trained model is completed as described in the previous section since modelID is returned as a result of the training request.

...

Code Block
languagejs
firstline1
titleGET {prefix}/models/6d4b571a-80ca-41ef-bc67-b158f4352ad8
collapsetrue
{
    "id": "6d4b571a-80ca-41ef-bc67-b158f4352ad8",
    "name": "Model 1",
    "revision": 3,
    "format": { 
      "name": "PMML",
      "version": "4.3"
    },
    "algorithm": "Neural Network", 
    "tags": [
      "Anomaly detection",         
      "Banking"                    
    ],                              
    "dependency", "",
    "creator": "John Doe",
    "description": "This is a predictive model, refer to {input} and {output} for detailed format of each field, such as value range of a field, as well as possible predictions the model will gave. You may also refer to the example data here.",
    "input": {
      "fields": [
        {
          "name": "Account ID",
          "opType": "categorical",
          "dataType": "string",
          "taxonomy": "ID",
          "example": "account abc-001",
          "allowMissing": false,
          "description": "unique value"
        },
        {
          "name": "Account Balance",
          "opType": "continuous",
          "dataType": "double",
          "taxonomy": "currency",
          "example": "1,378,560.00",
          "allowMissing": true,
          "description": "Minimum: 0, Maximum: 999,999,999.00"
        }, 
      ],
      "ref": "http://dmg.org/pmml/v4-3/pmml-4-3.xsd"                                                       
    }
    "output": {
      "fields": [
        {
          "name": "Churn",
          "opType": "continuous",
          "dataType": "string",
          "taxonomy": "ID",
          "example": "0.67",
          "allowMissing": false,
          "description": "the possibility of the account stop doing business with a company over 6 months"
        }
      ],
      "ref": "http://dmg.org/pmml/v4-3/pmml-4-3.xsd"                                                       
    }
    "performance": {            
      "metric": "accuracy",     
      "value": 0.85
    },
    "rating": 5,
    "url": "uri://link_to_the_model"  
}

3. The BI tool tools will use the information retrieved from the AI platform to display to the user, including what type of models are available and the performance. It can optionally match the data and suggest what may be the good match based on what the user has.

4. User interacts with the result BI presented and decides what can be a good model to make a prediction on certain set of data. Please note that the model can also be returned as the result of the training step described in the previous section. In the case, the user may bypass these 2 steps and go directly to see the result.

5. Once the BI user/developer decides which model to run for prediction. BI will compile all required predictions, they will take the appropriate actions in the BI tool to prepare the data and call OBAIC and request it run that model with the data.

Query should be in the body


Expand
titleAPI to infer from a model using provided dataset by reference


HTTP RequestValue
Method

POST

Header

Authorization: Bearer {token}

URL

{prefix}/models/{modelID}

Query Parameters

{

  "dbToken": "string";
  "modelIDaction": "string",
  "data":{
      "sourceType":"string",
      "endpoint":"string",
      "bearerToken":"string",
      "query":"string"
  }
}

Example

{

  "dbToken": "D41C4A382C27A4B5DF824E2D4F148";
  "modelIDaction": "6d4b571a-80ca-41ef-bc67-b158f4352ad8"infer",
  "data":{
      "sourceType":"snowflake",
      "endpoint":"some/endpoint",
      "bearerToken":"7CA4D3C152646DDEFB527A958C45B",
      "query":"SELECT foo FROM bar WHERE baz"
  }
}


Explanation 

Pass by value is recommended only for small data set 

{

  "dbToken": "string";
  "modelID":"string"

  "data":{
     
Expand
titleAPI to infer from a model using provided dataset by value
HTTP RequestValue
Method

POST

Header

Authorization: Bearer {token}

URL

{prefix}/models/

Query Parameters
200: Prediction returned successfully by reference


string   string   string  stringExample
HTTP ResponseValue
HeaderContent-Type: application/json
Body{
  "resultStatus": "ready",

  "result":{
    "sourceType":"
snowflake",
   
"endpoint":"some/endpoint",
   
"bearerToken":"7CA4D3C152646DDEFB527A958C45B",
    "query":"SELECT * FROM resultTable"
  }

}



{

  "dbToken": "D41C4A382C27A4B5DF824E2D4F148";
  "modelID":"6d4b571a-80ca-41ef-bc67-b158f4352ad8"
Expand
titleAPI to infer from a model using provided dataset by value

Pass by value is recommended only for small data sets 

HTTP RequestValue
Method

GET

Header

Authorization: Bearer {token}

URL

{prefix}/models/model/{modelID}

Query Parameters

{
  "action": "string",
  "data":{
      "sourceType":"snowflakestring",
      "endpoint":"some/endpointstring",
      "bearerToken":"7CA4D3C152646DDEFB527A958C45Bstring",
      "query":"SELECT foo FROM bar WHERE bazstring"
  }
}

Error - Apply to all API calls above

Expand
title400: The request is malformed
HTTP ResponseValue
HeaderContent-Type: application/json
Body{
"errorCode": "string",
"message": "string"
}
Expand
title401: The request is unauthenticated. The bearer token is missing or incorrect
{
"errorCode": "string",
"message": "string"
HTTP ResponseValue
HeaderContent-Type: application/json
BodyExample


{
  "action": "infer",
  "data":[
    { 
      "AccountBalance": 100,
      "YearOpened": 1990
    },
    { 
      "AccountBalance": 200,
      "YearOpened": 1995
    },
  ]

}





Expand
title403: The request is forbidden from being fulfilled200: Prediction returned successfully by value


HTTP ResponseValue
HeaderContent-Type: application/json
Body{
  "errorCoderesultStatus": "stringready",
  "
messageresult": "string"

}
Expand
title500: The request is not handled correctly due to a server error
HTTP ResponseValue
HeaderContent-Type: application/json
Body{
"errorCode": "string",
"message": "string"
}

Next Step

  • Finalize Logo
  • Determine what other AI framework can be supported by OBAIC besides ONNX and PMML

Future Enhancement

  • Define potential value for each parameter in the API call
  • Formally define JSON in http://json-schema.org/ so that future development can validate the JSON structure
  • Define data pipeline to transform data before running
  • Define containerized model so that prediction can run in BI instead of in AI
  • Define format of nextPageToken
  • Define different types of errorCode and message for each API call

FAQ

  1. Why should AI share model to BI?
    • The setting of OBAIC assumes an organization owns both the BI Tool(s) and AI platform(s). However, they are 2 (or more) discrete entities and may not have a good way to integrate. Hence OBAIC comes in to connect the dots.
  2. Who owns the model and data?
    • The AI platform owns the model but share with BI tools through OBAIC. The data is owned by the business but BI has been authorized to use it and re-share this to AI for training and inference.
  3. How do you deal with Security?
    • Call will be handled by HTTPS protocol and authorized by bearer token standard 

References

Authors

...

Name

...

Affiliation

...

Get Model Metrics

Get core evaluation metrics for a trained model.

...

function GetModelMetrics(UUID) -> Metrics

Example response:

{
  "accuracy":0.781,
  "lossType":"cross-entropy",
  "loss":0.0238
}

Predict Using Trained Model

function PredictWithModel(UUID, dataConfig) -> Predictions

Example params

...

{
  "uuid": "abcdef12345",
  "data":{
      "sourceType":"snowflake",
      "endpoint":"some/endpoint",
      "bearerToken":"...",
      "query":"SELECT foo FROM bar WHERE baz"
  }
}

    

A very similar data stanza to the train request, designating the feature data on which to predict.

Example response (as JSON here for convenience, not necessarily for large responses):

...

{
  "data":[
      {
        "customerAge":2,
        "activeInLastMonth":"false",
        "predicted__canceledSubscription":"true"
      },
      {
        "customerAge":9,
        "activeInLastMonth":"true",
        "predicted__canceledSubscription":"false"
      }
  ]
}

...

[
    { 
      "AccountBalance": 100,
      "YearOpened": 1990,
      "Churn": 80
    },
    { 
      "AccountBalance": 200,
      "YearOpened": 1995,
      "Churn": 40
    },
  ]

}



Expand
title200: Prediction is running and not ready yet


HTTP ResponseValue
HeaderContent-Type: application/json
Body{
  "resultStatus": "notReady",
  "resultProgress": 50,
  "resultID": "925D2129FC57FAC5"
}


6. AI will connect to the underlying data source and run the prediction using the information provided by BI

7. In case the result cannot be returned immediately because of the prediction volume, BI can poll for the result.

In case of pass by reference

Code Block
languagejs
firstline1
titleGET {prefix}/results/925D2129FC57FAC5
collapsetrue
{
  "resultStatus": "ready",
  "result":{
    "sourceType":"snowflake",
    "endpoint":"some/endpoint",
    "bearerToken":"7CA4D3C152646DDEFB527A958C45B",
    "query":"SELECT * FROM resultTable"
  }
}

In case of pass by value:

Code Block
languagejs
firstline1
titleGET {prefix}/results/925D2129FC57FAC5
collapsetrue
{
  "resultStatus": "ready",
  "result":[
    { 
      "AccountBalance": 100,
      "YearOpened": 1990,
      "Churn": 80
    },
    { 
      "AccountBalance": 200,
      "YearOpened": 1995,
      "Churn": 40
    },
  ]
}

Error - Apply to all API calls above

Expand
title400: The request is malformed


HTTP ResponseValue
HeaderContent-Type: application/json
Body{
"errorCode": "string",
"message": "string"
}



Expand
title401: The request is unauthenticated. The bearer token is missing or incorrect


HTTP ResponseValue
HeaderContent-Type: application/json
Body{
"errorCode": "string",
"message": "string"
}



Expand
title403: The request is forbidden from being fulfilled


HTTP ResponseValue
HeaderContent-Type: application/json
Body{
"errorCode": "string",
"message": "string"
}



Expand
title500: The request is not handled correctly due to a server error


HTTP ResponseValue
HeaderContent-Type: application/json
Body{
"errorCode": "string",
"message": "string"
}


Next Step

Future Enhancement

  • Define potential value for each parameter in the API call
  • Formally define JSON in http://json-schema.org/ so that future development can validate the JSON structure
  • Define data pipeline to transform data before running
  • Define containerized model so that prediction can run in BI instead of in AI
  • Define format of nextPageToken
  • Define different types of errorCode and message for each API call

FAQ

  1. Why should AI vendors care to participate in the OBAIC standard?
    • Most AI model training and execution is done by a very small set of data scientists. The OBAIC protocol extends the influence and ability for the AI vendors. They will no longer need to work with BI partners to create one off implementations and continually maintain those. 
  2. Why should BI vendors care to participate in the OBAIC standard?
    • Providing end users access to predictions/prescriptions is the desired goal. Writing one off drivers to support every AI flavor of the week isn't the goal. The OBAIC standard provides BI vendors the opportunity to build and support 1 driver, while then enabling all customers/prospects to bring their own AI implementation(s) to the table and not lose deals as the result of not having a customer driver in place for that customer to expand, or prospect to purchase.  
  3. Who owns the model and data?
    • The AI platform owns the models but share those with BI tools through OBAIC. The data is owned by the business but BI has been authorized to use it and re-share this to AI for training and inference.
  4. How do you deal with Security?
    • Call will be handled by HTTPS protocol and authorized by bearer token standard 

References

Authors

Name

Affiliation

Cupid ChanPistevo Decision
Xiangxiang MengUpstart
Deepak KaruppiahMicroStrategy
Dalton RuerQlik
Sachin SinhaMicrosoft
Yi ShaoIBM
Stu SztukowskiSAS
Jeffrey TangPredibaes
Lingyan YinSalesforce