|
additionalParams
Additional query parameters
|
Additional query parameters to pass to return resultsfrom Fusion. Please specify in dictionary format: e.g. { "rowsFromSolrToRerank": 20,"fq": "type:answer" }"
type: string
|
|
appName
App name
required
|
Fusion app where indexed documents or QA pairs live.
type: string
|
|
batchSize
Output Batch Size
|
If writing to solr, this field defines the batch size for documents to be pushed to solr.
type: string
|
|
collectionName
Main Collection
required
|
Fusion collection where indexed documents or QA pairs live
type: string
|
|
doWeightsSelection
Perform weights selection
|
Whether to perform grid search to find the best weights combination for ranking scores for query pipeline's Compute Mathematical Expression stage"
type: boolean
default value: 'false'
|
|
fetcherType
Fetcher Type to use with query evaluation
|
type: string
default value: 'query-service'
|
|
id
Job ID
required
|
The ID for this job. Used in the API to reference this job. Allowed characters: a-z, A-Z, dash (-) and underscore (_)
type: string
maxLength: 63
pattern: [a-zA-Z][_\-a-zA-Z0-9]*[a-zA-Z0-9]?
|
|
inputEvaluationCollection
Input Evaluation Data Path
required
|
Cloud storage path or Solr collection to pull labeled data for use in evaluation
type: string
minLength: 1
|
|
kList
Metrics@k list
|
The k retrieval position that will be used to compute for each metric
type: string
default value: '[1,3,5]'
|
|
matchFieldInFile
Ground Truth Field
|
Field which contains id or text of the ground truth answer in the evaluation collection
type: string
default value: 'answer_id'
|
|
matchFieldInFusion
Answer or id Field in Fusion
|
Field name in Fusion which contains answer id or text for matching ground truth answer id or text in the evaluation collection
type: string
default value: 'doc_id'
|
|
metricsList
Metrics list
|
List of metrics that should be computed during evaluation. e.g.["recall","precision","map","mrr"]
type: string
default value: '["recall","map","mrr"]'
|
|
outputEvaluationCollection
Output Evaluation Data Path
required
|
Cloud storage path or Solr collection to store evaluation results (recommended collection is job_reports)
type: string
minLength: 1
|
|
outputFormat
Output format
required
|
The format of the output data - solr, parquet etc.
type: string
default value: 'solr'
minLength: 1
|
|
partitionFields
Partition fields
|
If writing to non-Solr sources, this field will accept a comma-delimited list of column names for partitioning the dataframe before writing to the external output
type: string
|
|
queryPipelineName
Fusion Query Pipeline
required
|
Configured query pipeline name that should be used for evaluation
type: string
|
|
rankingScoreField
Ranking score
|
Score to be used for ranking and evaluation
type: string
default value: 'ensemble_score'
|
|
readOptions
Read Options
|
Options used when reading input from Solr or other sources.
type: array of object
object attributes: {
key
(required)
: {
display name: Parameter Name
type: string
}
value
: {
display name: Parameter Value
type: string
}
}
|
|
returnFields
Return fields
required
|
Fields (comma-separated) that should be returned from the main collection (e.g. question, answer). The job will add them to the output evaluation
type: string
|
|
scoreListForWeights
List of ranking scores for ensemble
|
Ranking scores (comma-separated) used for ensemble in the query pipeline's Compute Mathematical Expression stage. The job will perform weights selection for the listed scores
type: string
default value: 'score,vectors_distance'
|
|
secretName
Cloud storage secret name
|
Name of the secret used to access cloud storage as defined in the K8s namespace
type: string
minLength: 1
|
|
seed
Sampling Seed
|
Random seed for sampling
type: integer
default value: '12345'
|
|
solrScaleFunc
Solr scale function
|
Function used in the pipeline to scale Solr scores. E.g., scale by max Solr score retrieved (max), scale by log with base 10 (log10) or take squre root of score (pow0.5)
type: string
default value: 'max'
|
|
sparkConfig
Additional parameters
|
Provide additional key/value pairs to be injected into the training JSON map at runtime. Values will be inserted as-is, so use " to surround string values
type: array of object
object attributes: {
key
(required)
: {
display name: Parameter Name
type: string
}
value
: {
display name: Parameter Value
type: string
}
}
|
|
targetRankingMetric
Target metric to use for weight selection
|
Target ranking metric to optimize during weights selection
type: string
default value: 'mrr@3'
|
|
testQuestionFieldInFile
Test Question Field
|
Defines the field in the collection containing the test question
type: string
default value: 'question'
|
|
trainingDataFilterQuery
Training Data Filter Query
|
Solr or SQL query to filter training data. Use solr query when solr collection is specified in Training Path. Use SQL query when cloud storage location is specified. The table name for SQL is `spark_input`
type: string
|
|
trainingFormat
Input data format
required
|
The format of the input data - solr, parquet etc.
type: string
default value: 'solr'
minLength: 1
|
|
trainingSampleFraction
Sampling proportion
|
The proportion of data to be sampled from the full dataset. Use a value between 0 and 1 for a proportion (e.g. 0.5 for 50%), or for a specific number of examples, use an integer larger than 1. Leave blank for no sampling
type: number
|
|
type
Spark Job Type
required
|
type: string
default value: 'argo-qna-evaluate'
enum: {
argo-qna-evaluate
}
|
|
useConcurrentQuerying
Use Concurrent Querying
|
Check this option if you want to make concurrent queries to Fusion. It will greatly speed up the job at the cost of increased load on Fusion. Use with caution.
type: boolean
default value: 'false'
|
|
useLabelingResolution
Use Labeling Resolution
|
Check this to determine similar questions and similar answers via labeling resolution and graph connected components. Does not work well with signals data.
type: boolean
default value: 'false'
|
|
writeOptions
Write Options
|
Options used when writing output to Solr or other sources
type: array of object
object attributes: {
key
(required)
: {
display name: Parameter Name
type: string
}
value
: {
display name: Parameter Value
type: string
}
}
|