LWAI Prediction
Index pipeline stage configuration specifications
The LWAI Prediction index stage is an integration between Fusion and Lucidworks AI to enrich your index with Generative AI predictions.
More detailed information to configure this stage is in Configure the LWAI Prediction index Stage.
By default, the Fusion
General purpose integration between Fusion and Lucidworks AI. By default, this stage is asynchronous, meaning that it will not block the pipeline while waiting for a response from Lucidworks AI. This default asynchronous configuration may benefit from the use of other stages, e.g. ‘Solr Asynchronous Query’ to incrementally handle the response from Lucidworks AI.
Configure the LWAI Prediction index Stage
Configure the LWAI Prediction index Stage
The LWAI Prediction index stage is a Fusion index pipeline stage that enriches your index with Generative AI predictions.
It defaults to asynchronous processing, which does not block the pipeline while waiting for a response from Lucidworks AI.For reference information, see LWAI Prediction index stage.To use this stage, non-admin Fusion users must be granted the
PUT,POST,GET:/LWAI-ACCOUNT-NAME/** permission in Fusion, which is the Lucidworks AI API Account Name defined in Lucidworks AI Gateway when this stage is configured.To configure this stage:- Sign in to Fusion and click Indexing > Index Pipelines.
- Click Add+ to add a new pipeline.
- Enter the name in Pipeline ID.
- Click Add a new pipeline stage.
- In the AI section, click LWAI Prediction.
- In the Label field, enter a unique identifier for this stage.
- In the Condition field, enter a script that results in true or false, which determines if the stage should process.
- In the Account Name field, select the Lucidworks AI API account name defined in Lucidworks AI Gateway.
- In the Use Case field, select the Lucidworks AI use case to associate with this stage.
- To generate a list of the use cases for your organization, see Use Case API.
- If the Call Asynchronously? check box is selected, see available use cases described in Async Prediction API.
- If the Call Asynchronously? check box is not selected, see available use cases described in Prediction API.
- In the Model field, select the Lucidworks AI model to associate with this stage.
PUT,POST,GET:/LWAI-ACCOUNT-NAME/**Your Fusion account name must match the name of the account that you selected in the Account Name dropdown.For more information about models, see:- In the Input context variable variable field, enter the name of the variable in context to be used as input. Template expressions are supported.
- In the Destination field name and context output field, enter the name that will be used as both the field name in the document where the prediction is written and the context variable that contains the prediction.
-
If the Call Asynchronously? check box is selected and a value is entered in this field:
-
{destination name}_tis the full response. -
In the document:
-
_lw_ai_properties_sscontains the Lucidworks account, boolean setting for async, use case, input for the call, and the collection. -
_lw_ai_request_countis the number of GET requests bypredictionIdand_lw_ai_success_countis the number of responses without errors. These two fields are used for debugging only. Based on the deployment, the most useful measure is the ratio of_lw_ai_success_countdivided by `_lw_ai_request_count and then adjusting as much as possible to achieve 1.0. -
enriched_sscontains the use case. This can be used as a boolean value to verify if the use case indexed successfully.
-
-
-
If the Call Asynchronously? check box is not selected and a value is entered in this field:
{destination name}_tis the full response.
-
If no value is entered in this field (regardless of the Call Asynchronously? check box setting):
-
_lw_ai_{use case}_tis theresponse.responseobject, which is the raw model output. -
_lw_ai_{use case}_response_sis the full response.
-
- In the Use Case Configuration section, click the + sign to enter the parameter name and value to send to Lucidworks AI. The
useCaseConfigparameter is only applicable to certain use cases.
- If the Call Asynchronously? check box is selected,
useCaseConfiginformation for each applicable use case is described in Async Prediction API. - If the Call Asynchronously? check box is not selected,
useCaseConfiginformation for each applicable use case is described in Prediction API.
- In the Model Configuration section, click the + sign to enter the parameter name and value to send to Lucidworks AI. Several
modelConfigparameters are common to generative AI use cases.
- If the Call Asynchronously? check box is selected,
modelConfiginformation is described in Async Prediction API. - If the Call Asynchronously? check box is not selected,
modelConfiginformation is described in Prediction API.
- In the API Key field, enter the secret value specified in the external model. For:
-
OpenAI models,
"apiKey"is the value in the model’s"[OPENAI_API_KEY]"field. For more information, see Authentication API keys. -
Azure OpenAI models,
"apiKey"is the value generated by Azure in either the model’s"[KEY1 or KEY2]"field. For requirements to use Azure models, see Generative AI models. -
Google VertexAI models,
"apiKey"is the value in the model’s"[BASE64_ENCODED_GOOGLE_SERVICE_ACCOUNT_KEY]"field. For more information, see Create and delete Google service account keys.
- To run the API call asynchronously, select the Call Asynchronously? check box to specify the stage is to use the Lucidworks AI Async Prediction API endpoints. If this is selected, the API call does not block the pipeline while waiting for a response from Lucidworks AI.
- In the Maximum Asynchronous Call Tries field, enter the maximum number of times to send an asynchronous API call before the system generates a failure error.
- Select the Fail on Error checkbox to generate an exception if an error occurs while generating a prediction for a document.
- Click Save.
Additional requirements
Additional requirements to use async calls include:- Use a V2 connector. Only V2 connectors work for this task and not other options, such as PBL or V1 connectors.
- Remove the
Apache Tikastage from your parser because it can cause datasource failures with the following error: “The following components failed: [class com.lucidworks.connectors.service.components.job.processor.DefaultDataProcessor : Only Tika Container parser can support Async Parsing.]” - Replace the
Solr Indexerstage with theSolr Partial Update Indexerstage with the following settings:Enable Concurrency Controlset to offReject Update if Solr Document is not Presentset to offProcess All Pipeline Doc Fieldsset to onAllow reserved fieldsset to on- A parameter with
Update Type,Field Name&ValueinUpdates
Call Asynchronously? field is selected, which specifies this stage uses the Lucidworks AI Async Prediction API endpoints.
If the Fusion Call Asynchronously? field is not selected, this stage uses the LWAI Prediction API endpoints.
To use this stage, non-admin Fusion users must be granted the PUT,POST,GET:/LWAI-ACCOUNT-NAME/** permission in Fusion, which is the Lucidworks AI API Account Name defined in Lucidworks AI Gateway when this stage is configured.
Configuration
When entering configuration values in the UI, use unescaped characters, such as
\t for the tab character. When entering configuration values in the API, use escaped characters, such as \\t for the tab character.