> ## Documentation Index
> Fetch the complete documentation index at: https://doc.lucidworks.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Smart Answers Evaluate Pipeline

export const schema = {
  "type": "object",
  "title": "Smart Answers Evaluate Pipeline",
  "description": "Evaluates the performance of a configured Fusion query pipeline against labeled ground truth data and writes metrics to an output collection.",
  "required": ["id", "inputEvaluationCollection", "trainingFormat", "outputEvaluationCollection", "outputFormat", "appName", "queryPipelineName", "collectionName", "returnFields", "type"],
  "properties": {
    "id": {
      "type": "string",
      "title": "Job ID",
      "description": "The ID for this job. Used in the API to reference this job. Allowed characters: a-z, A-Z, dash (-) and underscore (_).",
      "maxLength": 63,
      "pattern": "[a-zA-Z][_\\-a-zA-Z0-9]*[a-zA-Z0-9]?"
    },
    "sparkConfig": {
      "type": "array",
      "title": "Additional parameters",
      "description": "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.",
      "hints": ["advanced"],
      "items": {
        "type": "object",
        "required": ["key"],
        "properties": {
          "key": {
            "type": "string",
            "title": "Parameter Name"
          },
          "value": {
            "type": "string",
            "title": "Parameter Value"
          }
        }
      }
    },
    "writeOptions": {
      "type": "array",
      "title": "Write Options",
      "description": "Sets additional key-value options passed to the Spark writer when writing output to Solr or other sinks.",
      "hints": ["advanced"],
      "items": {
        "type": "object",
        "required": ["key"],
        "properties": {
          "key": {
            "type": "string",
            "title": "Parameter Name"
          },
          "value": {
            "type": "string",
            "title": "Parameter Value"
          }
        }
      }
    },
    "readOptions": {
      "type": "array",
      "title": "Read Options",
      "description": "Sets additional key-value options passed to the Spark reader when loading input from Solr or other sources.",
      "hints": ["advanced"],
      "items": {
        "type": "object",
        "required": ["key"],
        "properties": {
          "key": {
            "type": "string",
            "title": "Parameter Name"
          },
          "value": {
            "type": "string",
            "title": "Parameter Value"
          }
        }
      }
    },
    "inputEvaluationCollection": {
      "type": "string",
      "title": "Input Evaluation Data Path",
      "description": "Specifies the cloud storage path or Solr collection containing labeled evaluation data.",
      "minLength": 1
    },
    "trainingFormat": {
      "type": "string",
      "title": "Input data format",
      "description": "Specifies the format of the input evaluation data, such as `solr` or `parquet`.",
      "default": "solr",
      "minLength": 1
    },
    "outputEvaluationCollection": {
      "type": "string",
      "title": "Output Evaluation Data Path",
      "description": "Specifies the cloud storage path or Solr collection where evaluation results are stored.",
      "minLength": 1
    },
    "partitionFields": {
      "type": "string",
      "title": "Partition fields",
      "description": "Specifies document fields used to partition the output.",
      "hints": ["advanced"]
    },
    "batchSize": {
      "type": "string",
      "title": "Output Batch Size",
      "description": "Sets the number of documents processed per batch during evaluation.",
      "hints": ["advanced"]
    },
    "outputFormat": {
      "type": "string",
      "title": "Output format",
      "description": "Specifies the format of the output evaluation results, such as `solr` or `parquet`.",
      "default": "solr",
      "minLength": 1
    },
    "secretName": {
      "type": "string",
      "title": "Cloud storage secret name",
      "description": "Specifies the name of the Kubernetes secret used to access cloud storage.",
      "hints": ["advanced"],
      "minLength": 1
    },
    "trainingDataFilterQuery": {
      "type": "string",
      "title": "Training Data Filter Query",
      "description": "Specifies a Solr query or SQL expression to filter training data. Use a Solr query when reading from a Solr collection.",
      "hints": ["code/sql", "advanced"]
    },
    "trainingSampleFraction": {
      "type": "number",
      "title": "Sampling proportion",
      "description": "Sets the proportion of data sampled from the full dataset. Use a value between `0` and `1`.",
      "hints": ["advanced"]
    },
    "seed": {
      "type": "integer",
      "title": "Sampling Seed",
      "description": "Sets the random seed for reproducible sampling.",
      "default": 12345,
      "hints": ["advanced"]
    },
    "testQuestionFieldInFile": {
      "type": "string",
      "title": "Test Question Field",
      "description": "Specifies the evaluation collection field containing the test question.",
      "default": "question"
    },
    "matchFieldInFile": {
      "type": "string",
      "title": "Ground Truth Field",
      "description": "Specifies the evaluation collection field containing the ID or text of the ground truth answer.",
      "default": "answer_id"
    },
    "matchFieldInFusion": {
      "type": "string",
      "title": "Answer or id Field in Fusion",
      "description": "Specifies the Fusion collection field used to match ground truth answer IDs or text.",
      "default": "doc_id"
    },
    "appName": {
      "type": "string",
      "title": "App name",
      "description": "Specifies the Fusion application where indexed documents or QA pairs are stored."
    },
    "queryPipelineName": {
      "type": "string",
      "title": "Fusion Query Pipeline",
      "description": "Specifies the Fusion query pipeline used for evaluation."
    },
    "collectionName": {
      "type": "string",
      "title": "Main Collection",
      "description": "Specifies the Fusion collection where indexed documents or QA pairs are stored."
    },
    "additionalParams": {
      "type": "string",
      "title": "Additional query parameters",
      "description": "Specifies additional query parameters passed to Fusion when retrieving results. Use dictionary format.",
      "hints": ["advanced"]
    },
    "returnFields": {
      "type": "string",
      "title": "Return fields",
      "description": "Specifies the fields returned from Fusion query results."
    },
    "rankingScoreField": {
      "type": "string",
      "title": "Ranking score",
      "description": "Specifies the field used as the ranking score during evaluation.",
      "default": "ensemble_score",
      "hints": ["advanced"]
    },
    "metricsList": {
      "type": "string",
      "title": "Metrics list",
      "description": "Specifies the list of metrics to compute, such as `recall`, `precision`, `map`, and `mrr`.",
      "default": "[\"recall\",\"map\",\"mrr\"]",
      "hints": ["advanced"]
    },
    "kList": {
      "type": "string",
      "title": "Metrics@k list",
      "description": "Specifies the retrieval positions K at which metrics are computed.",
      "default": "[1,3,5]",
      "hints": ["advanced"]
    },
    "doWeightsSelection": {
      "type": "boolean",
      "title": "Perform weights selection",
      "description": "When enabled, computes optimal weights for combining scores in the query pipeline.",
      "default": false,
      "hints": ["advanced"]
    },
    "solrScaleFunc": {
      "type": "string",
      "title": "Solr scale function",
      "description": "Specifies the function used to scale Solr scores during ensemble ranking, such as `max` to scale by the maximum score.",
      "default": "max"
    },
    "scoreListForWeights": {
      "type": "string",
      "title": "List of ranking scores for ensemble",
      "description": "Specifies comma-separated ranking scores used for ensemble weighting in the pipeline's Compute Mathematical Expression stage.",
      "default": "score,vectors_distance"
    },
    "targetRankingMetric": {
      "type": "string",
      "title": "Target metric to use for weight selection",
      "description": "Specifies the target ranking metric to optimize during weight selection.",
      "default": "mrr@3"
    },
    "fetcherType": {
      "type": "string",
      "title": "Fetcher Type to use with query evaluation",
      "default": "query-service",
      "hints": ["hidden"]
    },
    "useLabelingResolution": {
      "type": "boolean",
      "title": "Use Labeling Resolution",
      "description": "When enabled, identifies similar questions and answers using labeling resolution and graph connectivity. Does not work well with noisy data.",
      "default": false,
      "hints": ["advanced"]
    },
    "useConcurrentQuerying": {
      "type": "boolean",
      "title": "Use Concurrent Querying",
      "description": "When enabled, makes concurrent queries to Fusion to speed up evaluation.",
      "default": false,
      "hints": ["advanced"]
    },
    "type": {
      "type": "string",
      "title": "Spark Job Type",
      "enum": ["argo-qna-evaluate"],
      "default": "argo-qna-evaluate",
      "hints": ["readonly"]
    }
  },
  "additionalProperties": true,
  "category": "Other",
  "categoryPriority": 1,
  "propertyGroups": [{
    "label": "Input / Output Parameters",
    "properties": ["inputEvaluationCollection", "trainingFormat", "outputEvaluationCollection", "outputFormat", "trainingDataFilterQuery", "testQuestionFieldInFile", "matchFieldInFile", "trainingSampleFraction", "seed", "useLabelingResolution", "partitionFields", "batchSize", "secretName"]
  }, {
    "label": "Query Pipeline Input / Output Parameters",
    "properties": ["appName", "collectionName", "queryPipelineName", "matchFieldInFusion", "additionalParams", "returnFields", "useConcurrentQuerying"]
  }, {
    "label": "Metrics",
    "properties": ["rankingScoreField", "metricsList", "kList", "doWeightsSelection", "solrScaleFunc", "scoreListForWeights", "targetRankingMetric"]
  }]
};

export const SchemaParamFields = ({schema}) => {
  const sanitize = str => {
    if (typeof str !== "string") return str;
    return str.replace(/^"(.*)"$/s, "$1").replace(/\\/g, "").replace(/"/g, "'");
  };
  const renderMd = str => {
    const s = sanitize(str);
    const text = (/[.!?]\)*$/).test(s) ? s : `${s}.`;
    return text.split(/(\*\*[^*]+\*\*|_[^_]+_|`[^`]+`)/g).map((part, i) => {
      if (part.startsWith("**")) return <strong key={i}>{part.slice(2, -2)}</strong>;
      if (part.startsWith("_")) return <em key={i}>{part.slice(1, -1)}</em>;
      if (part.startsWith("`")) return <code key={i}>{part.slice(1, -1)}</code>;
      return part;
    });
  };
  const {description, properties = {}, required: requiredProps = []} = schema;
  const visibleProps = useMemo(() => Object.entries(properties).filter(([, prop]) => !prop.hints?.includes("hidden")), [properties]);
  const renderProp = ([name, prop]) => {
    const isRequired = requiredProps.includes(name);
    const hasDefault = prop.default !== undefined;
    const rawDefault = prop.default;
    const hints = prop.hints || [];
    const isComplexDefault = hasDefault && (typeof rawDefault === "object" || typeof rawDefault === "string" && (rawDefault.length > 20 || rawDefault.includes('"')));
    const postBadges = [];
    if (prop.title) {
      postBadges.push(<><span className="text-stone-400 dark:text-stone-500">API property: </span>{name}</>);
    }
    const constraints = [];
    if (prop.minimum !== undefined && prop.maximum !== undefined) {
      constraints.push(`Range: ${prop.minimum} – ${prop.maximum}`);
    } else if (prop.minimum !== undefined) {
      constraints.push(`Min: ${prop.minimum}`);
    } else if (prop.maximum !== undefined) {
      constraints.push(`Max: ${prop.maximum}`);
    }
    if (prop.minLength !== undefined && prop.maxLength !== undefined) {
      constraints.push(`Length: ${prop.minLength} – ${prop.maxLength}`);
    } else if (prop.minLength !== undefined) {
      constraints.push(`Min length: ${prop.minLength}`);
    } else if (prop.maxLength !== undefined) {
      constraints.push(`Max length: ${prop.maxLength}`);
    }
    const fieldProps = {
      key: name,
      body: prop.title || name,
      type: prop.type,
      ...postBadges.length > 0 && ({
        post: postBadges
      }),
      ...isRequired && ({
        required: true
      }),
      ...!isComplexDefault && hasDefault ? {
        default: sanitize(String(rawDefault))
      } : {}
    };
    const isObject = prop.type === "object" && prop.properties;
    const isArrayOfObjects = prop.type === "array" && prop.items?.type === "object" && prop.items.properties;
    return <ParamField {...fieldProps}>
        {prop.description && <p>{renderMd(prop.description)}</p>}

        {prop.enum && <p>
            Allowed values: 
            {prop.enum.map((v, i) => <>{i > 0 && ", "}<code key={i}>{String(v)}</code></>)}
          </p>}

        {constraints.length > 0 && <p className="text-stone-500 dark:text-stone-400 text-sm">
            {constraints.join(" · ")}
          </p>}

        {isComplexDefault && <div className="flex">
            <p>
              <strong>Default:</strong>
            </p>
            <pre className="!my-0">
              <code>
                {JSON.stringify(rawDefault, null, 2)}
              </code>
            </pre>
          </div>}

        {isArrayOfObjects && <Expandable title="item properties">
            <SchemaParamFields schema={{
      properties: prop.items.properties,
      required: prop.items.required
    }} />
          </Expandable>}

        {isObject && <Expandable title="properties">
            <SchemaParamFields schema={{
      properties: prop.properties,
      required: prop.required
    }} />
          </Expandable>}
      </ParamField>;
  };
  return <div>
      {description && <p>{renderMd(description)}</p>}

      {visibleProps.map(renderProp)}
    </div>;
};

export const LwTemplate = ({title = "Key questions to get you started", icon = "sparkles", cta = "Powered by Agent Studio", linkHref = "https://lucidworks.com/demo/?utm_source=docs&utm_medium=referral&utm_campaign=docs_cta_ai"}) => {
  const [isLoaded, setIsLoaded] = useState(false);
  useEffect(() => {
    const timer = setTimeout(() => {
      setIsLoaded(true);
    }, 500);
    return () => clearTimeout(timer);
  }, []);
  return <div className="lw-template-container">
      <Card title={title} icon={icon}>
        {isLoaded && <span dangerouslySetInnerHTML={{
    __html: `<lw-template id="a029c1a9-28be-427e-b0e1-5d918920246a"></lw-template
            >`
  }} />}
        <Link href={linkHref} className="agent-studio-link text-left text-gray-600 gap-2 dark:text-gray-400 text-sm font-medium flex flex-row items-center hover:text-primary dark:hover:text-primary-light group-hover:text-primary group-hover:dark:text-primary-light">Powered by Lucidworks Agent Studio</Link>
      </Card>
    </div>;
};

[localhost link]: http://localhost:3000/docs/5/fusion/reference/config-ref/jobs/smart-answers-evaluate-pipeline

[mintlify link]: https://doc.lucidworks.com/docs/5/fusion/reference/config-ref/jobs/smart-answers-evaluate-pipeline

[old doc.lw link]: https://doc.lucidworks.com/fusion/5.9/8846

Evaluate the performance of a [Smart Answers](/docs/5/fusion/getting-data-out/advanced-query-enhancement/smart-answers/overview) pipeline.

See [Evaluate a Smart Answers Query Pipeline](/docs/5/fusion/getting-data-out/advanced-query-enhancement/smart-answers/overview#evaluate-the-query-pipeline) for configuration instructions.

<LwTemplate />

## Configuration properties

<SchemaParamFields schema={schema} />