> ## 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.

# Word2Vec Model Training Jobs

export const schema = {
  "type": "object",
  "title": "Word2Vec Model Training (deprecated)",
  "description": "Trains a Word2Vec shallow neural model and projects each document into the resulting vector embedding space. Deprecated. Use the Classification job instead.",
  "required": ["id", "trainingCollection", "fieldToVectorize", "dataFormat", "outputCollection", "type"],
  "properties": {
    "id": {
      "type": "string",
      "title": "Spark Job ID",
      "description": "The ID for this Spark 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": "Spark Settings",
      "description": "Spark configuration settings.",
      "hints": ["advanced"],
      "items": {
        "type": "object",
        "required": ["key"],
        "properties": {
          "key": {
            "type": "string",
            "title": "Parameter Name"
          },
          "value": {
            "type": "string",
            "title": "Parameter Value"
          }
        }
      }
    },
    "trainingCollection": {
      "type": "string",
      "title": "Training Collection",
      "description": "Specifies the Solr collection or cloud storage path containing training data.",
      "minLength": 1
    },
    "fieldToVectorize": {
      "type": "string",
      "title": "Field to Vectorize",
      "description": "Specifies the Solr field containing text to vectorize. Combine multiple fields with weights using the format `field1:weight1,field2:weight2`.",
      "minLength": 1
    },
    "dataFormat": {
      "type": "string",
      "title": "Data format",
      "description": "Specifies the Spark-compatible input data format, such as `solr`, `parquet`, or `orc`.",
      "default": "solr",
      "minLength": 1
    },
    "trainingDataFrameConfigOptions": {
      "type": "object",
      "title": "Dataframe Config Options",
      "description": "Sets additional key-value configuration options passed to the Spark DataFrame reader at load time.",
      "properties": {},
      "additionalProperties": {
        "type": "string"
      },
      "hints": ["advanced"]
    },
    "trainingDataFilterQuery": {
      "type": "string",
      "title": "Training data filter query",
      "description": "Filters training data using a Solr query when reading from Solr, or a SQL expression for other data sources.",
      "default": "*:*",
      "hints": ["advanced"]
    },
    "sparkSQL": {
      "type": "string",
      "title": "Spark SQL filter query",
      "description": "Filters the loaded DataFrame using a Spark SQL query before processing. The input data is registered as a temporary table named `spark_input`.",
      "default": "SELECT * from spark_input",
      "hints": ["code/sql", "advanced"]
    },
    "trainingDataSamplingFraction": {
      "type": "number",
      "title": "Training data sampling fraction",
      "description": "Sets the fraction of training data to sample before processing. Use a value between `0` and `1`. `1.0` uses all available data.",
      "default": 1,
      "hints": ["advanced"],
      "maximum": 1,
      "exclusiveMaximum": false
    },
    "randomSeed": {
      "type": "integer",
      "title": "Random seed",
      "description": "Sets the random seed for deterministic operations including sampling and initialization. Fix this value to reproduce identical results across runs.",
      "default": 1234,
      "hints": ["advanced"]
    },
    "outputCollection": {
      "type": "string",
      "title": "Output Collection",
      "description": "Specifies the Solr collection where output documents are written."
    },
    "overwriteOutput": {
      "type": "boolean",
      "title": "Overwrite Output",
      "description": "When enabled, overwrites the output collection before writing new results.",
      "default": true,
      "hints": ["hidden"]
    },
    "dataOutputFormat": {
      "type": "string",
      "title": "Data output format",
      "description": "Specifies the Spark-compatible output format, such as `solr`, `parquet`, or `orc`.",
      "default": "solr",
      "hints": ["advanced"],
      "minLength": 1
    },
    "sourceFields": {
      "type": "string",
      "title": "Fields to Load",
      "description": "Specifies the document fields to load from the input source.",
      "hints": ["advanced"]
    },
    "partitionCols": {
      "type": "string",
      "title": "Partition fields",
      "description": "Specifies a comma-delimited list of column names used to partition output when writing to non-Solr sinks.",
      "hints": ["advanced"]
    },
    "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"
          }
        }
      }
    },
    "modelId": {
      "type": "string",
      "title": "Model ID",
      "description": "Specifies the identifier for the trained model. Defaults to the Spark job ID if not provided.",
      "hints": ["advanced"],
      "minLength": 1
    },
    "analyzerConfig": {
      "type": "string",
      "title": "Lucene Analyzer Schema",
      "description": "Specifies the Lucene analyzer configuration in JSON format used for text tokenization and processing.",
      "default": "{ \"analyzers\": [{ \"name\": \"StdTokLowerStop\",\"charFilters\": [ { \"type\": \"htmlstrip\" } ],\"tokenizer\": { \"type\": \"standard\" },\"filters\": [{ \"type\": \"lowercase\" },{ \"type\": \"KStem\" },{ \"type\": \"length\", \"min\": \"2\", \"max\": \"32767\" },{ \"type\": \"fusionstop\", \"ignoreCase\": \"true\", \"format\": \"snowball\", \"words\": \"org/apache/lucene/analysis/snowball/english_stop.txt\" }] }],\"fields\": [{ \"regex\": \".+\", \"analyzer\": \"StdTokLowerStop\" } ]}",
      "hints": ["advanced", "code/json", "lengthy"]
    },
    "withIdf": {
      "type": "boolean",
      "title": "IDF Weighting",
      "description": "When enabled, weights feature vector components using inverse document frequency (IDF).",
      "default": true,
      "hints": ["advanced"]
    },
    "w2vDimension": {
      "type": "integer",
      "title": "Embedding Dimension",
      "description": "Sets the dimensionality of the Word2Vec word vectors.",
      "default": 50,
      "hints": ["dummy"],
      "minimum": 0,
      "exclusiveMinimum": false
    },
    "w2vWindowSize": {
      "type": "integer",
      "title": "Window Size",
      "description": "Sets the context window size for Word2Vec training. The model considers words within `[-window, window]` of each target word.",
      "default": 5,
      "hints": ["dummy"],
      "minimum": 3,
      "exclusiveMinimum": false
    },
    "w2vMaxSentenceLength": {
      "type": "integer",
      "title": "Max Sentence Length",
      "description": "Sets the maximum sentence length in words for Word2Vec. Sentences longer than this are truncated.",
      "default": 1000,
      "hints": ["dummy"],
      "minimum": 3,
      "exclusiveMinimum": false
    },
    "w2vMaxIter": {
      "type": "integer",
      "title": "Max Iterations",
      "description": "Sets the maximum number of training iterations for Word2Vec.",
      "default": 1,
      "hints": ["advanced"]
    },
    "w2vStepSize": {
      "type": "number",
      "title": "Step Size",
      "description": "Sets the learning rate for Word2Vec convergence.",
      "default": 0.025,
      "hints": ["advanced"],
      "minimum": 0.005,
      "exclusiveMinimum": false
    },
    "minDF": {
      "type": "number",
      "title": "Minimum Term Document Frequency",
      "description": "Sets the minimum document frequency for terms to be included. Values less than `1.0` are treated as a fraction. `1.0` or above as an absolute count.",
      "default": 0,
      "hints": ["advanced"]
    },
    "maxDF": {
      "type": "number",
      "title": "Max Term Document Frequency",
      "description": "Sets the maximum document frequency for terms to be included. Values less than `1.0` are treated as a fraction. `1.0` or above as an absolute count.",
      "default": 1,
      "hints": ["advanced"]
    },
    "norm": {
      "type": "integer",
      "title": "Vector normalization",
      "description": "Sets the p-norm used to normalize feature vectors. Use `-1` to disable normalization.",
      "enum": [-1, 0, 1, 2],
      "default": 2,
      "hints": ["advanced"]
    },
    "predictedLabelField": {
      "type": "string",
      "title": "Word2Vec Feature Field",
      "description": "Specifies the document field where the Word2Vec feature vector is stored.",
      "default": "w2vFeatures",
      "hints": ["hidden"]
    },
    "serializeAsMleap": {
      "type": "boolean",
      "title": "Serialize as Mleap Bundle",
      "description": "When enabled, serializes the output model as an MLeap bundle for portable deployment.",
      "default": true,
      "hints": ["hidden"]
    },
    "minSparkPartitions": {
      "type": "integer",
      "title": "Minimum Number of Spark Partitions",
      "description": "Sets the minimum number of Spark partitions for the training job.",
      "default": 200,
      "hints": ["advanced"],
      "minimum": 1,
      "exclusiveMinimum": false
    },
    "stopwordsList": {
      "type": "array",
      "title": "List of stopwords",
      "description": "Specifies stop words defined in the Lucene analyzer configuration to exclude from processing.",
      "hints": ["readonly", "hidden"],
      "items": {
        "type": "string",
        "minLength": 1,
        "reference": "blob",
        "blobType": "file:spark"
      }
    },
    "overwriteExistingModel": {
      "type": "boolean",
      "title": "Overwrite existing model",
      "description": "When enabled, overwrites an existing model with the same ID in the model store.",
      "default": true,
      "hints": ["advanced"]
    },
    "outputField": {
      "type": "string",
      "title": "Output Field",
      "description": "Specifies the document field where the projected vector embedding is stored.",
      "default": "related_terms_txt"
    },
    "uidField": {
      "type": "string",
      "title": "ID Field Name",
      "description": "Specifies the document field used as the unique identifier.",
      "minLength": 1
    },
    "numRelatedTerms": {
      "type": "integer",
      "title": "Number of Related Words",
      "description": "Sets the number of Word2Vec-related terms to find for each input word.",
      "default": 10,
      "minimum": 1,
      "exclusiveMinimum": false
    },
    "type": {
      "type": "string",
      "title": "Spark Job Type",
      "enum": ["word2vec"],
      "default": "word2vec",
      "hints": ["readonly"]
    }
  },
  "additionalProperties": true,
  "category": "Other",
  "categoryPriority": 1,
  "propertyGroups": [{
    "label": "Input/Output Parameters",
    "properties": ["trainingCollection", "outputCollection", "dataFormat", "trainingDataFilterQuery", "readOptions", "writeOptions", "trainingDataFrameConfigOptions", "trainingDataSamplingFraction", "randomSeed"]
  }, {
    "label": "Field Parameters",
    "properties": ["fieldToVectorize", "sourceFields", "predictedLabelField", "uidField", "outputField"]
  }, {
    "label": "Model Tuning Parameters",
    "properties": ["w2vDimension", "w2vWindowSize", "w2vMaxIter", "w2vMaxSentenceLength", "w2vStepSize", "withIdf", "maxDF", "minDF", "norm", "numRelatedTerms"]
  }, {
    "label": "Featurization Parameters",
    "properties": ["analyzerConfig"]
  }, {
    "label": "Misc. Parameters",
    "properties": ["modelId"]
  }]
};

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/jobs/word2vec-model-training

[mintlify link]: https://doc.lucidworks.com/docs/lucidworks-search/09-developer-documentation/config-specs/jobs/word2vec-model-training

[old doc.lw link]: https://doc.lucidworks.com/managed-fusion/5.9/jem3fe

Train a shallow neural model, and project each document onto this vector embedding space.

<Note>
  This job is deprecated in Fusion 5.2.0.
</Note>

<LwTemplate />

## Configuration properties

<SchemaParamFields schema={schema} />