> ## 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 shallow neural model, and projects each document onto this vector embedding space. Deprecated as of Fusion 5.2.0 and will be removed in a future release.", "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 (_). Maximum length: 63 characters.", "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": "Solr Collection containing labeled training data", "minLength": 1 }, "fieldToVectorize": { "type": "string", "title": "Field to Vectorize", "description": "Solr field containing text training data. Data from multiple fields with different weights can be combined by specifying them as field1:weight1,field2:weight2 etc.", "minLength": 1 }, "dataFormat": { "type": "string", "title": "Data format", "description": "Spark-compatible format that contains training data (like 'solr', 'parquet', 'orc' etc)", "default": "solr", "minLength": 1 }, "trainingDataFrameConfigOptions": { "type": "object", "title": "Dataframe Config Options", "description": "Additional spark dataframe loading configuration options", "properties": {}, "additionalProperties": { "type": "string" }, "hints": ["advanced"] }, "trainingDataFilterQuery": { "type": "string", "title": "Training data filter query", "description": "Solr query to use when loading training data if using Solr", "default": "*:*", "hints": ["advanced"] }, "sparkSQL": { "type": "string", "title": "Spark SQL filter query", "description": "Use this field to create a Spark SQL query for filtering your input data. The input data will be registered as spark_input", "default": "SELECT * from spark_input", "hints": ["code/sql", "advanced"] }, "trainingDataSamplingFraction": { "type": "number", "title": "Training data sampling fraction", "description": "Fraction of the training data to use", "default": 1, "hints": ["advanced"], "maximum": 1, "exclusiveMaximum": false }, "randomSeed": { "type": "integer", "title": "Random seed", "description": "For any deterministic pseudorandom number generation", "default": 1234, "hints": ["advanced"] }, "outputCollection": { "type": "string", "title": "Output Collection", "description": "Solr Collection to store model-labeled data to" }, "overwriteOutput": { "type": "boolean", "title": "Overwrite Output", "description": "Overwrite output collection", "default": true, "hints": ["hidden"] }, "dataOutputFormat": { "type": "string", "title": "Data output format", "description": "Spark-compatible output format (like 'solr', 'parquet', etc)", "default": "solr", "hints": ["advanced"], "minLength": 1 }, "sourceFields": { "type": "string", "title": "Fields to Load", "description": "Solr fields to load (comma-delimited). Leave empty to allow the job to select the required fields to load at runtime.", "hints": ["advanced"] }, "partitionCols": { "type": "string", "title": "Partition fields", "description": "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 ", "hints": ["advanced"] }, "writeOptions": { "type": "array", "title": "Write Options", "description": "Options used when writing output to Solr or other sources", "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": "Options used when reading 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": "Identifier for the model to be trained; uses the supplied Spark Job ID if not provided.", "hints": ["advanced"], "minLength": 1 }, "analyzerConfig": { "type": "string", "title": "Lucene Analyzer Schema", "description": "LuceneTextAnalyzer schema for tokenization (JSON-encoded)", "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": "Weight vector components based on inverse document frequency", "default": true, "hints": ["advanced"] }, "w2vDimension": { "type": "integer", "title": "Embedding Dimension", "description": "Word-vector dimensionality to represent text", "default": 50, "hints": ["dummy"], "minimum": 0, "exclusiveMinimum": false }, "w2vWindowSize": { "type": "integer", "title": "Window Size", "description": "The window size (context words from [-window, window]) for word2vec", "default": 5, "hints": ["dummy"], "minimum": 3, "exclusiveMinimum": false }, "w2vMaxSentenceLength": { "type": "integer", "title": "Max Sentence Length", "description": "Sets the maximum length (in words) of each sentence in the input data. Any sentence longer than this threshold will be divided into chunks of up to `maxSentenceLength` size.", "default": 1000, "hints": ["dummy"], "minimum": 3, "exclusiveMinimum": false }, "w2vMaxIter": { "type": "integer", "title": "Max Iterations", "description": "Maximum number of iterations of the word2vec training", "default": 1, "hints": ["advanced"] }, "w2vStepSize": { "type": "number", "title": "Step Size", "description": "Training parameter for word2vec convergence (change at your own peril)", "default": 0.025, "hints": ["advanced"], "minimum": 0.005, "exclusiveMinimum": false }, "minDF": { "type": "number", "title": "Minimum Term Document Frequency", "description": "To be kept, terms must occur in at least this number of documents (if > 1.0), or at least this fraction of documents (if <= 1.0)", "default": 0, "hints": ["advanced"] }, "maxDF": { "type": "number", "title": "Max Term Document Frequency", "description": "To be kept, terms must occur in no more than this number of documents (if > 1.0), or no more than this fraction of documents (if <= 1.0)", "default": 1, "hints": ["advanced"] }, "norm": { "type": "integer", "title": "Vector normalization", "description": "p-norm to normalize vectors with (choose -1 to turn normalization off)", "enum": [-1, 0, 1, 2], "default": 2, "hints": ["advanced"] }, "predictedLabelField": { "type": "string", "title": "Word2Vec Feature Field", "description": "Solr field which will contain vector features when the word2vec model is applied to documents", "default": "w2vFeatures", "hints": ["hidden"] }, "serializeAsMleap": { "type": "boolean", "title": "Serialize as Mleap Bundle", "description": "Serialize the output model as Mleap Bundle", "default": true, "hints": ["hidden"] }, "minSparkPartitions": { "type": "integer", "title": "Minimum Number of Spark Partitions", "description": "Minimum number of Spark partitions for training job.", "default": 200, "hints": ["advanced"], "minimum": 1, "exclusiveMinimum": false }, "stopwordsList": { "type": "array", "title": "List of stopwords", "description": "Stopwords defined in Lucene analyzer config", "hints": ["readonly", "hidden"], "items": { "type": "string", "minLength": 1, "reference": "blob", "blobType": "file:spark" } }, "overwriteExistingModel": { "type": "boolean", "title": "Overwrite existing model", "description": "If a model exists in the model store, overwrite when this job runs", "default": true, "hints": ["advanced"] }, "outputField": { "type": "string", "title": "Output Field", "description": "Solr field which will contain terms which the word2vec model considers are related to the input", "default": "related_terms_txt" }, "uidField": { "type": "string", "title": "ID Field Name", "description": "Field containing the unique ID for each document", "minLength": 1 }, "numRelatedTerms": { "type": "integer", "title": "Number of Related Words", "description": "For each collection of input words, find this many word2vec-related words", "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 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
{description &&

{formatDescription(description)}

} {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: [<>API property: {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 {prop.description &&

{formatDescription(prop.description)}

} {isComplexDefault &&

Default: 

                  
                    {JSON.stringify(rawDefault, null, 2)}
} {isArrayOfObjects &&

Object attributes: 

                
                  {'{\n'}
                  {Object.entries(prop.items.properties).map(([iname, iprop]) => <>
                      {`  ${iname}`}
                      {prop.items?.required?.includes(iname) &&  required}
                      {`: {\n    display name: ${sanitize(iprop.title || '')}\n    type: ${iprop.type}\n  }\n`}
                    )}
                  {'}'}
} {isObject && } ; })}
; }; 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
{isLoaded && ` }} />} Powered by Lucidworks Agent Studio
; }; [localhost link]: http://localhost:3000/docs/5/fusion/reference/config-ref/jobs/word2vec-model-training [mintlify link]: https://doc.lucidworks.com/docs/5/fusion/reference/config-ref/jobs/word2vec-model-training [old doc.lw link]: https://doc.lucidworks.com/fusion/5.9/560 Train a shallow neural model, and project each document onto this vector embedding space. This job is deprecated in Fusion 5.2.0. ## Configuration properties