> ## 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.

# Detect Sentences Index Stage

export const schema = {
  "type": "object",
  "title": "Tag Part-of-Speech",
  "description": "Tag sentences with part-of-speech information. Requires Sentence Detection on the same fields earlier in the pipeline",
  "required": ["tokenizerModel", "posModel", "source"],
  "properties": {
    "skip": {
      "type": "boolean",
      "title": "Skip This Stage",
      "description": "Set to true to skip this stage.",
      "default": false,
      "hints": ["advanced"]
    },
    "label": {
      "type": "string",
      "title": "Label",
      "description": "A unique label for this stage.",
      "hints": ["advanced"],
      "maxLength": 255
    },
    "condition": {
      "type": "string",
      "title": "Condition",
      "description": "Define a conditional script that must result in true or false. This can be used to determine if the stage should process or not.",
      "hints": ["code", "code/javascript", "advanced"]
    },
    "tokenizerModel": {
      "type": "string",
      "title": "Tokenizer Model",
      "reference": "blob",
      "blobType": "model:open-nlp"
    },
    "posModel": {
      "type": "string",
      "title": "Part of Speech Model",
      "reference": "blob",
      "blobType": "model:open-nlp"
    },
    "source": {
      "type": "array",
      "title": "Source Fields",
      "minItems": 1,
      "items": {
        "type": "string"
      }
    }
  },
  "category": "Natural Language Processing",
  "categoryPriority": 5,
  "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 formatDescription = str => {
    const s = sanitize(str);
    return (/[.!?]\)*$/).test(s) ? s : `${s}.`;
  };
  const {description, properties = {}, required: requiredProps = []} = schema;
  const visibleProps = useMemo(() => Object.entries(properties).filter(([, prop]) => !prop.hints?.includes("hidden")), [properties]);
  return <div>
      {description && <p>{formatDescription(description)}</p>}

      {visibleProps.map(([name, prop]) => {
    const isRequired = requiredProps.includes(name);
    const hasDefault = prop.default !== undefined;
    const rawDefault = prop.default;
    const isComplexDefault = hasDefault && (typeof rawDefault === "object" || typeof rawDefault === "string" && (rawDefault.length > 20 || rawDefault.includes('"')));
    const fieldProps = {
      key: name,
      body: prop.title || name,
      type: prop.type,
      ...prop.title && ({
        post: [<><span className="text-stone-400 dark:text-stone-500">API property: </span>{name}</>]
      }),
      ...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>{formatDescription(prop.description)}</p>}

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

            {isArrayOfObjects && <div className="flex">
              <p>
                <strong>Object attributes:</strong>
              </p>
              <pre className="!my-0">
                <code>
                  {'{\n'}
                  {Object.entries(prop.items.properties).map(([iname, iprop]) => <>
                      {`  ${iname}`}
                      {prop.items?.required?.includes(iname) && <span style={{
      color: 'red'
    }}> required</span>}
                      {`: {\n    display name: ${sanitize(iprop.title || '')}\n    type: ${iprop.type}\n  }\n`}
                    </>)}
                  {'}'}
                </code>
              </pre>
              </div>}

            {isObject && <Expandable title="properties">
                <SchemaParamFields schema={{
      properties: prop.properties,
      required: prop.required
    }} />
              </Expandable>}
          </ParamField>;
  })}
    </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/4/fusion-server/reference/pipeline-stages/indexing/sentence-detection-index-stage

[mintlify link]: https://doc.lucidworks.com/docs/4/fusion-server/reference/pipeline-stages/indexing/sentence-detection-index-stage

[old doc.lw link]: https://doc.lucidworks.com/fusion-server/4.2/230

The Detect Sentences index stage (called the Sentence Detection stage in versions earlier than 3.0) operates over one of more fields in the Pipeline Document and annotates each field with sentence boundary information. These annotations can be used by downstream indexing stages. A Detect Sentences stage can be used in tandem with a Tag Part-of-Speech Index Stage to provide part-of-speech annotations for the individual tokens in the field.

This stage uses [Apache OpenNLP](http://opennlp.apache.org/) project’s [Sentence Detection](http://opennlp.apache.org/docs/#tools.sentdetect) tool. The OpenNLP documentation states:

***

The OpenNLP Sentence Detector can detect that a punctuation character marks the end of a sentence or not. In this sense a sentence is defined as the longest white space trimmed character sequence between two punctuation marks. The first and last sentence make an exception to this rule. The first non whitespace character is assumed to be the begin of a sentence, and the last non whitespace character is assumed to be a sentence end.
*\_*

Models are available from the OpenNLP [models SourceForge repository](http://opennlp.sourceforge.net/models-1.5/).

Model files must be uploaded to Fusion using the [Fusion Blob Store service](/docs/4/fusion-server/reference/api/blob-store-api) via the REST API (see examples below).

<LwTemplate />

## Sentence Detection in a NLP Pipeline

The following video shows how to use a Sentence Detection index stage as part of an NLP pipeline:

<Frame>
  <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 />
</Frame>

## Stage Setup

This is an example of how to upload a sentence model file to the Fusion blob:

**INPUT**

```bash wrap  theme={"dark"}
curl -u USERNAME:PASSWORD -X PUT --data-binary @en-pos-maxent.bin -H 'Content-type: text/plain' http://localhost:8764/api/blobs/en-pos-maxent.bin
```

**OUTPUT**

```json wrap  theme={"dark"}
{
  "name" : "en-sent.bin",
  "contentType" : "text/plain",
  "size" : 5696197,
  "modifiedTime" : "2015-07-15T06:57:48.636Z",
  "version" : 0,
  "md5" : "db2cd70395b9e2e4c6b9957015a10607"
}
```

This is an example setup of this stage using the previously loaded .bin file:

**INPUT**

```bash wrap  theme={"dark"}
curl -u USERNAME:PASSWORD -X POST -H 'Content-type: application/json' -d '{"id":"DetectSentences1", "type": "detect-sentences","sentenceModel":"en-sent.bin","source": ["A test sentence"]}' http://localhost:8764/api/index-stages/instances
```

**OUTPUT**

```json wrap  theme={"dark"}
{
  "type" : "detect-sentences",
  "id" : "DetectSentences1",
  "sentenceModel" : "en-sent.bin",
  "source" : [ "A test sentence" ],
  "skip" : false,
  "label" : "detect-sentences",
  "type" : "detect-sentences"
}
```

## 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} />