> ## 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.

# Gazetteer Lookup Extraction

> Index pipeline stage configuration specifications

export const schema = {
  "type": "object",
  "title": "Gazetteer Lookup Extraction",
  "description": "Extracts named entities from document fields by matching text against preconfigured gazetteers, which are curated lists of known entity names such as locations, organizations, or products. Annotates matched entities for downstream enrichment and filtering.",
  "properties": {
    "skip": {
      "type": "boolean",
      "title": "Skip This Stage",
      "description": "Controls whether this stage executes during pipeline processing at runtime. When set to `true`, the stage is completely bypassed and documents pass through unchanged to the next stage. Useful for A/B testing, gradual rollouts, or temporarily disabling a stage without removing it from the pipeline.",
      "default": false,
      "hints": ["advanced"]
    },
    "label": {
      "type": "string",
      "title": "Label",
      "description": "Human-readable identifier displayed in the Fusion Admin UI, monitoring dashboards, and log messages. Use descriptive labels like `Parse Product PDFs` to aid debugging and team collaboration. Labels appear in performance metrics and error reports, making it easier to identify which stage failed.",
      "hints": ["advanced"],
      "maxLength": 255
    },
    "condition": {
      "type": "string",
      "title": "Condition",
      "description": "JavaScript expression evaluated at runtime on each document to conditionally execute this stage. The expression must return `true` to execute or `false` to skip. Access document fields using `doc.getFieldValue('fieldName')` and request parameters via `request.getFirstParam('paramName')`. For example, `doc.getFieldValue('type') === 'premium'` executes this stage only for premium content.",
      "hints": ["code", "code/javascript", "advanced"]
    },
    "rules": {
      "type": "array",
      "title": "Extraction Rules",
      "items": {
        "type": "object",
        "required": ["source", "target", "entityTypes"],
        "properties": {
          "source": {
            "type": "array",
            "title": "Source Fields",
            "minItems": 1,
            "items": {
              "type": "string",
              "format": "regex"
            }
          },
          "target": {
            "type": "string",
            "title": "Target Field"
          },
          "writeMode": {
            "type": "string",
            "title": "Write Mode",
            "description": "What to do if document has target field already.",
            "enum": ["overwrite", "append"],
            "default": "append",
            "hints": ["advanced"]
          },
          "entityTypes": {
            "type": "array",
            "title": "Entity Types",
            "minItems": 1,
            "items": {
              "type": "object",
              "required": ["name", "entityDefinitions"],
              "properties": {
                "name": {
                  "type": "string",
                  "title": "Entity Name"
                },
                "entityDefinitions": {
                  "type": "array",
                  "title": "Entity Definitions (Model files)",
                  "minItems": 1,
                  "items": {
                    "type": "string",
                    "reference": "blob",
                    "blobType": "model:open-nlp"
                  }
                }
              }
            }
          },
          "additionalEntities": {
            "type": "array",
            "title": "Additional Entities",
            "items": {
              "type": "object",
              "required": ["name", "entityDefinitions"],
              "properties": {
                "name": {
                  "type": "string",
                  "title": "Entity Name"
                },
                "entityDefinitions": {
                  "type": "array",
                  "title": "Entity Definitions (List of entities)",
                  "minItems": 1,
                  "items": {
                    "type": "string"
                  }
                }
              }
            }
          },
          "caseSensitive": {
            "type": "boolean",
            "title": "Case Sensitive",
            "default": false
          }
        }
      }
    }
  },
  "category": "Natural Language Processing",
  "categoryPriority": 6,
  "unsafe": false
};

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/lucidworks-search/09-developer-documentation/config-specs/index-pipeline-stages/gazetteer-lookup-extraction

[mintlify link]: https://doc.lucidworks.com/docs/lucidworks-search/09-developer-documentation/config-specs/index-pipeline-stages/gazetteer-lookup-extraction

[old doc.lw link]: https://doc.lucidworks.com/managed-fusion/5.9/8eiqpf

The Gazetteer Lookup Extraction index stage (called the Gazetteer Lookup Extractor stage in versions earlier than 3.0) uses predefined lists of words and phrases to process specified text fields in a document.
A gazetteer is a set of lookup lists over names of people, places, or things.
These lookup lists are used to find occurrences of these names in text.
The matched items are saved into separate fields on the document for downstream processing.

<LwTemplate />

## Gazetteers and OpenNLP Tools

The following video shows how to configure a Gazetteer Lookup Extraction stage in combination with OpenNLP:

<iframe width="640" height="480" src="https://www.youtube.com/embed/bbbLAMnfHjY" title="Fusion Learners - OpenNLP and Gazetteer" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen />

## Uploading Lookup Lists to Lucidworks Search Blob Store

Lucidworks Search includes a number of lookup lists in the directory at `https://EXAMPLE_COMPANY.lucidworks.cloud/data/nlp/gazetteer`.
To use the supplied lists or a list of your own data, each must list be uploaded to Lucidworks Search
using the [Blob Store API](/api-reference/blobs/get-blob-store-service-status)
in order to make the list contents available to the Gazetteer Lookup Extraction stage.

For example, to identify color names, you would first compile a list of color terms, one entry per line in a text file with suffix `.lst` and then
upload that file using the Lucidworks Search REST API endpoint `api/blobs/<listfilename>`, as per the following example which
uses the `curl` command-line utility, where 'admin' is the name of a user with admin privileges, and 'pass' is that user’s password:

```bash wrap  theme={"dark"}
curl -u USERNAME:PASSWORD -X PUT --data-binary @data/nlp/gazetteer/colors.lst -H 'Content-type: text/plain' http://EXAMPLE_COMPANY.lucidworks.cloud/api/blobs/colors.lst
```

<Note>
  Replace `EXAMPLE_COMPANY` with the name provided by your Lucidworks representative.
</Note>

## Name Lookup Example

*Define a lookup-extractor to identify mentions of certain celebrities in text field `description_t`:*

```json wrap  theme={"dark"}
{
  "type" : "lookup-extractor",
  "id" : "peopleLookup",
  "rules" : [ {
    "source" : [ "description_t" ],
    "target" : "celebrities_ss",
    "entityTypes" : [ {
      "name" : "person_female",
      "definitions" : [ "person_female.lst" ]
    } ],
    "additionalEntities" : [ {
      "name" : "players",
      "definitions" : [ "sharapova", "murray" ]
    }, {
      "name" : "actors",
      "definitions" : [ "pitt", "jolie" ]
    } ],
    "caseSensitive" : false
  } ],
  "skip" : false
}
```

## Configuration

<Tip>
  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.
</Tip>

<SchemaParamFields schema={schema} />