{
"name": "CreateSchemaObject",
"fully_qualified_name": "WeaviateApi.CreateSchemaObject@0.1.0",
"description": "Create a new collection (class) in Weaviate.\n\nThis tool is used to define and create a new collection (class) in Weaviate. It provides explicit control over the schema definition, which is essential when `AutoSchema` is not relied upon. Use this tool to ensure accurate schema setup in a Weaviate instance.",
"toolkit": {
"name": "ArcadeWeaviateApi",
"description": null,
"version": "0.1.0"
},
"input": {
"parameters": [
{
"name": "collection_definition",
"required": true,
"description": "JSON object defining the collection to create, including class name and configurations.",
"value_schema": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"class": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Name of the collection (formerly 'class') (required). Multiple words should be concatenated in CamelCase, e.g. `ArticleAuthor`."
},
"vectorConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Configure named vectors. Either use this field or `vectorizer`, `vectorIndexType`, and `vectorIndexConfig` fields. Available from `v1.24.0`."
},
"vectorIndexType": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Name of the vector index type to use for the collection (e.g. `hnsw` or `flat`)."
},
"vectorIndexConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Vector-index config, that is specific to the type of index selected in vectorIndexType"
},
"shardingConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Manage how the index should be sharded and distributed in the cluster"
},
"replicationConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"factor": {
"val_type": "integer",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Number of times a collection (class) is replicated (default: 1)."
},
"asyncEnabled": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Enable asynchronous replication (default: `false`)."
},
"deletionStrategy": {
"val_type": "string",
"inner_val_type": null,
"enum": [
"NoAutomatedResolution",
"DeleteOnConflict",
"TimeBasedResolution"
],
"properties": null,
"inner_properties": null,
"description": "Conflict resolution strategy for deleted objects."
}
},
"inner_properties": null,
"description": "Configure how replication is executed in a cluster"
},
"invertedIndexConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"cleanupIntervalSeconds": {
"val_type": "number",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Asynchronous index clean up happens every n seconds (default: 60)."
},
"bm25": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"k1": {
"val_type": "number",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Calibrates term-weight scaling based on the term frequency within a document (default: 1.2)."
},
"b": {
"val_type": "number",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Calibrates term-weight scaling based on the document length (default: 0.75)."
}
},
"inner_properties": null,
"description": "Tuning parameters for the BM25 algorithm."
},
"stopwords": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"preset": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Pre-existing list of common words by language (default: `en`). Options: [`en`, `none`]."
},
"additions": {
"val_type": "array",
"inner_val_type": "string",
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Stopwords to be considered additionally (default: []). Can be any array of custom strings."
},
"removals": {
"val_type": "array",
"inner_val_type": "string",
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Stopwords to be removed from consideration (default: []). Can be any array of custom strings."
}
},
"inner_properties": null,
"description": "Fine-grained control over stopword list usage."
},
"indexTimestamps": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Index each object by its internal timestamps (default: `false`)."
},
"indexNullState": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Index each object with the null state (default: `false`)."
},
"indexPropertyLength": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Index length of properties (default: `false`)."
},
"usingBlockMaxWAND": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Using BlockMax WAND for query execution (default: `false`, will be `true` for new collections created after 1.30)."
}
},
"inner_properties": null,
"description": "Configure the inverted index built into Weaviate. See [Reference: Inverted index](https://docs.weaviate.io/weaviate/config-refs/indexing/inverted-index#inverted-index-parameters) for details."
},
"multiTenancyConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"enabled": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Whether or not multi-tenancy is enabled for this collection (class) (default: `false`)."
},
"autoTenantCreation": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Nonexistent tenants should (not) be created implicitly (default: `false`)."
},
"autoTenantActivation": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Existing tenants should (not) be turned HOT implicitly when they are accessed and in another activity status (default: `false`)."
}
},
"inner_properties": null,
"description": "Configuration related to multi-tenancy within a collection (class)"
},
"vectorizer": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Specify how the vectors for this collection should be determined. The options are either `none` - this means you have to import a vector with each object yourself - or the name of a module that provides vectorization capabilities, such as `text2vec-weaviate`. If left empty, it will use the globally configured default ([`DEFAULT_VECTORIZER_MODULE`](https://docs.weaviate.io/deploy/configuration/env-vars)) which can itself either be `none` or a specific module."
},
"moduleConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Configuration specific to modules in a collection context."
},
"description": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Description of the collection for metadata purposes."
},
"properties": {
"val_type": "array",
"inner_val_type": "json",
"enum": null,
"properties": null,
"inner_properties": {
"dataType": {
"val_type": "array",
"inner_val_type": "string",
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Data type of the property (required). If it starts with a capital (for example Person), may be a reference to another type."
},
"description": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Description of the property."
},
"moduleConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Configuration specific to modules in a collection context."
},
"name": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "The name of the property (required). Multiple words should be concatenated in camelCase, e.g. `nameOfAuthor`."
},
"indexInverted": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "(Deprecated). Whether to include this property in the inverted index. If `false`, this property cannot be used in `where` filters, `bm25` or `hybrid` search.
Unrelated to vectorization behavior (deprecated as of v1.19; use indexFilterable or/and indexSearchable instead)"
},
"indexFilterable": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Whether to include this property in the filterable, Roaring Bitmap index. If `false`, this property cannot be used in `where` filters.
Note: Unrelated to vectorization behavior."
},
"indexSearchable": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Optional. Should this property be indexed in the inverted index. Defaults to true. Applicable only to properties of data type text and text[]. If you choose false, you will not be able to use this property in bm25 or hybrid search. This property has no affect on vectorization decisions done by modules"
},
"indexRangeFilters": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Whether to include this property in the filterable, range-based Roaring Bitmap index. Provides better performance for range queries compared to filterable index in large datasets. Applicable only to properties of data type int, number, date."
},
"tokenization": {
"val_type": "string",
"inner_val_type": null,
"enum": [
"word",
"lowercase",
"whitespace",
"field",
"trigram",
"gse",
"kagome_kr",
"kagome_ja",
"gse_ch"
],
"properties": null,
"inner_properties": null,
"description": "Determines how a property is indexed. This setting applies to `text` and `text[]` data types. The following tokenization methods are available:
- `word` (default): Splits the text on any non-alphanumeric characters and lowercases the tokens.
- `lowercase`: Splits the text on whitespace and lowercases the tokens.
- `whitespace`: Splits the text on whitespace. This tokenization is case-sensitive.
- `field`: Indexes the entire property value as a single token after trimming whitespace.
- `trigram`: Splits the property into rolling trigrams (three-character sequences).
- `gse`: Uses the `gse` tokenizer, suitable for Chinese language text. [See `gse` docs](https://pkg.go.dev/github.com/go-ego/gse#section-readme).
- `kagome_ja`: Uses the `Kagome` tokenizer with a Japanese (IPA) dictionary. [See `kagome` docs](https://github.com/ikawaha/kagome).
- `kagome_kr`: Uses the `Kagome` tokenizer with a Korean dictionary. [See `kagome` docs](https://github.com/ikawaha/kagome).
See [Reference: Tokenization](https://docs.weaviate.io/weaviate/config-refs/collections#tokenization) for details."
},
"nestedProperties": {
"val_type": "array",
"inner_val_type": "json",
"enum": null,
"properties": null,
"inner_properties": {
"dataType": {
"val_type": "array",
"inner_val_type": "string",
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"description": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"name": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"indexFilterable": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"indexSearchable": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"indexRangeFilters": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"tokenization": {
"val_type": "string",
"inner_val_type": null,
"enum": [
"word",
"lowercase",
"whitespace",
"field",
"trigram",
"gse",
"kagome_kr",
"kagome_ja",
"gse_ch"
],
"properties": null,
"inner_properties": null,
"description": null
},
"nestedProperties": {
"val_type": "array",
"inner_val_type": "json",
"enum": null,
"properties": null,
"inner_properties": {},
"description": "The properties of the nested object(s). Applies to object and object[] data types."
}
},
"description": "The properties of the nested object(s). Applies to object and object[] data types."
}
},
"description": "Define properties of the collection."
}
},
"inner_properties": null,
"description": "The definition of the collection (class) to create."
},
"inferrable": true,
"http_endpoint_parameter_name": "requestBody"
}
]
},
"output": {
"description": "Response from the API endpoint 'schema.objects.create'.",
"available_modes": [
"value",
"error",
"null"
],
"value_schema": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
}
},
"requirements": {
"authorization": null,
"secrets": [
{
"key": "WEAVIATE_API_KEY"
},
{
"key": "WEAVIATE_SERVER_URL"
}
],
"metadata": null
},
"deprecation_message": null,
"metadata": {
"object_type": "api_wrapper_tool",
"version": "1.1.0",
"description": "Tools that enable LLMs to interact directly with the weaviate API."
},
"http_endpoint": {
"metadata": {
"object_type": "http_endpoint",
"version": "1.2.0",
"description": ""
},
"url": "{weaviate_server_url}/v1/schema",
"http_method": "POST",
"headers": {},
"parameters": [
{
"name": "requestBody",
"tool_parameter_name": "collection_definition",
"description": "The definition of the collection (class) to create.",
"value_schema": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"class": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Name of the collection (formerly 'class') (required). Multiple words should be concatenated in CamelCase, e.g. `ArticleAuthor`."
},
"vectorConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Configure named vectors. Either use this field or `vectorizer`, `vectorIndexType`, and `vectorIndexConfig` fields. Available from `v1.24.0`."
},
"vectorIndexType": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Name of the vector index type to use for the collection (e.g. `hnsw` or `flat`)."
},
"vectorIndexConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Vector-index config, that is specific to the type of index selected in vectorIndexType"
},
"shardingConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Manage how the index should be sharded and distributed in the cluster"
},
"replicationConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"factor": {
"val_type": "integer",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Number of times a collection (class) is replicated (default: 1)."
},
"asyncEnabled": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Enable asynchronous replication (default: `false`)."
},
"deletionStrategy": {
"val_type": "string",
"inner_val_type": null,
"enum": [
"NoAutomatedResolution",
"DeleteOnConflict",
"TimeBasedResolution"
],
"properties": null,
"inner_properties": null,
"description": "Conflict resolution strategy for deleted objects."
}
},
"inner_properties": null,
"description": "Configure how replication is executed in a cluster"
},
"invertedIndexConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"cleanupIntervalSeconds": {
"val_type": "number",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Asynchronous index clean up happens every n seconds (default: 60)."
},
"bm25": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"k1": {
"val_type": "number",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Calibrates term-weight scaling based on the term frequency within a document (default: 1.2)."
},
"b": {
"val_type": "number",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Calibrates term-weight scaling based on the document length (default: 0.75)."
}
},
"inner_properties": null,
"description": "Tuning parameters for the BM25 algorithm."
},
"stopwords": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"preset": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Pre-existing list of common words by language (default: `en`). Options: [`en`, `none`]."
},
"additions": {
"val_type": "array",
"inner_val_type": "string",
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Stopwords to be considered additionally (default: []). Can be any array of custom strings."
},
"removals": {
"val_type": "array",
"inner_val_type": "string",
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Stopwords to be removed from consideration (default: []). Can be any array of custom strings."
}
},
"inner_properties": null,
"description": "Fine-grained control over stopword list usage."
},
"indexTimestamps": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Index each object by its internal timestamps (default: `false`)."
},
"indexNullState": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Index each object with the null state (default: `false`)."
},
"indexPropertyLength": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Index length of properties (default: `false`)."
},
"usingBlockMaxWAND": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Using BlockMax WAND for query execution (default: `false`, will be `true` for new collections created after 1.30)."
}
},
"inner_properties": null,
"description": "Configure the inverted index built into Weaviate. See [Reference: Inverted index](https://docs.weaviate.io/weaviate/config-refs/indexing/inverted-index#inverted-index-parameters) for details."
},
"multiTenancyConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": {
"enabled": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Whether or not multi-tenancy is enabled for this collection (class) (default: `false`)."
},
"autoTenantCreation": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Nonexistent tenants should (not) be created implicitly (default: `false`)."
},
"autoTenantActivation": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Existing tenants should (not) be turned HOT implicitly when they are accessed and in another activity status (default: `false`)."
}
},
"inner_properties": null,
"description": "Configuration related to multi-tenancy within a collection (class)"
},
"vectorizer": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Specify how the vectors for this collection should be determined. The options are either `none` - this means you have to import a vector with each object yourself - or the name of a module that provides vectorization capabilities, such as `text2vec-weaviate`. If left empty, it will use the globally configured default ([`DEFAULT_VECTORIZER_MODULE`](https://docs.weaviate.io/deploy/configuration/env-vars)) which can itself either be `none` or a specific module."
},
"moduleConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Configuration specific to modules in a collection context."
},
"description": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Description of the collection for metadata purposes."
},
"properties": {
"val_type": "array",
"inner_val_type": "json",
"enum": null,
"properties": null,
"inner_properties": {
"dataType": {
"val_type": "array",
"inner_val_type": "string",
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Data type of the property (required). If it starts with a capital (for example Person), may be a reference to another type."
},
"description": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Description of the property."
},
"moduleConfig": {
"val_type": "json",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Configuration specific to modules in a collection context."
},
"name": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "The name of the property (required). Multiple words should be concatenated in camelCase, e.g. `nameOfAuthor`."
},
"indexInverted": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "(Deprecated). Whether to include this property in the inverted index. If `false`, this property cannot be used in `where` filters, `bm25` or `hybrid` search.
Unrelated to vectorization behavior (deprecated as of v1.19; use indexFilterable or/and indexSearchable instead)"
},
"indexFilterable": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Whether to include this property in the filterable, Roaring Bitmap index. If `false`, this property cannot be used in `where` filters.
Note: Unrelated to vectorization behavior."
},
"indexSearchable": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Optional. Should this property be indexed in the inverted index. Defaults to true. Applicable only to properties of data type text and text[]. If you choose false, you will not be able to use this property in bm25 or hybrid search. This property has no affect on vectorization decisions done by modules"
},
"indexRangeFilters": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": "Whether to include this property in the filterable, range-based Roaring Bitmap index. Provides better performance for range queries compared to filterable index in large datasets. Applicable only to properties of data type int, number, date."
},
"tokenization": {
"val_type": "string",
"inner_val_type": null,
"enum": [
"word",
"lowercase",
"whitespace",
"field",
"trigram",
"gse",
"kagome_kr",
"kagome_ja",
"gse_ch"
],
"properties": null,
"inner_properties": null,
"description": "Determines how a property is indexed. This setting applies to `text` and `text[]` data types. The following tokenization methods are available:
- `word` (default): Splits the text on any non-alphanumeric characters and lowercases the tokens.
- `lowercase`: Splits the text on whitespace and lowercases the tokens.
- `whitespace`: Splits the text on whitespace. This tokenization is case-sensitive.
- `field`: Indexes the entire property value as a single token after trimming whitespace.
- `trigram`: Splits the property into rolling trigrams (three-character sequences).
- `gse`: Uses the `gse` tokenizer, suitable for Chinese language text. [See `gse` docs](https://pkg.go.dev/github.com/go-ego/gse#section-readme).
- `kagome_ja`: Uses the `Kagome` tokenizer with a Japanese (IPA) dictionary. [See `kagome` docs](https://github.com/ikawaha/kagome).
- `kagome_kr`: Uses the `Kagome` tokenizer with a Korean dictionary. [See `kagome` docs](https://github.com/ikawaha/kagome).
See [Reference: Tokenization](https://docs.weaviate.io/weaviate/config-refs/collections#tokenization) for details."
},
"nestedProperties": {
"val_type": "array",
"inner_val_type": "json",
"enum": null,
"properties": null,
"inner_properties": {
"dataType": {
"val_type": "array",
"inner_val_type": "string",
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"description": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"name": {
"val_type": "string",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"indexFilterable": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"indexSearchable": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"indexRangeFilters": {
"val_type": "boolean",
"inner_val_type": null,
"enum": null,
"properties": null,
"inner_properties": null,
"description": null
},
"tokenization": {
"val_type": "string",
"inner_val_type": null,
"enum": [
"word",
"lowercase",
"whitespace",
"field",
"trigram",
"gse",
"kagome_kr",
"kagome_ja",
"gse_ch"
],
"properties": null,
"inner_properties": null,
"description": null
},
"nestedProperties": {
"val_type": "array",
"inner_val_type": "json",
"enum": null,
"properties": null,
"inner_properties": {},
"description": "The properties of the nested object(s). Applies to object and object[] data types."
}
},
"description": "The properties of the nested object(s). Applies to object and object[] data types."
}
},
"description": "Define properties of the collection."
}
},
"inner_properties": null,
"description": "The definition of the collection (class) to create."
},
"accepted_as": "body",
"required": true,
"deprecated": false,
"default": null,
"documentation_urls": []
}
],
"documentation_urls": [],
"secrets": [
{
"arcade_key": "WEAVIATE_API_KEY",
"parameter_name": "Authorization",
"accepted_as": "header",
"formatted_value": "Bearer {authorization}",
"description": "",
"is_auth_token": false
},
{
"arcade_key": "WEAVIATE_SERVER_URL",
"parameter_name": "weaviate_server_url",
"accepted_as": "path",
"formatted_value": null,
"description": "",
"is_auth_token": false
}
],
"request_body_spec": "{\n \"description\": \"The definition of the collection (class) to create.\",\n \"content\": {\n \"application/yaml\": {\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"class\": {\n \"type\": \"string\",\n \"description\": \"Name of the collection (formerly 'class') (required). Multiple words should be concatenated in CamelCase, e.g. `ArticleAuthor`.\"\n },\n \"vectorConfig\": {\n \"type\": \"object\",\n \"additionalProperties\": {\n \"type\": \"object\",\n \"properties\": {\n \"vectorizer\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Configuration of a specific vectorizer used by this vector\"\n },\n \"vectorIndexType\": {\n \"type\": \"string\",\n \"description\": \"Name of the vector index to use, eg. (HNSW)\"\n },\n \"vectorIndexConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Vector-index config, that is specific to the type of index selected in vectorIndexType\"\n }\n }\n },\n \"description\": \"Configure named vectors. Either use this field or `vectorizer`, `vectorIndexType`, and `vectorIndexConfig` fields. Available from `v1.24.0`.\"\n },\n \"vectorIndexType\": {\n \"type\": \"string\",\n \"description\": \"Name of the vector index type to use for the collection (e.g. `hnsw` or `flat`).\"\n },\n \"vectorIndexConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Vector-index config, that is specific to the type of index selected in vectorIndexType\"\n },\n \"shardingConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Manage how the index should be sharded and distributed in the cluster\"\n },\n \"replicationConfig\": {\n \"type\": \"object\",\n \"properties\": {\n \"factor\": {\n \"type\": \"integer\",\n \"description\": \"Number of times a collection (class) is replicated (default: 1).\"\n },\n \"asyncEnabled\": {\n \"type\": \"boolean\",\n \"description\": \"Enable asynchronous replication (default: `false`).\",\n \"x-omitempty\": false\n },\n \"deletionStrategy\": {\n \"type\": \"string\",\n \"description\": \"Conflict resolution strategy for deleted objects.\",\n \"enum\": [\n \"NoAutomatedResolution\",\n \"DeleteOnConflict\",\n \"TimeBasedResolution\"\n ],\n \"x-omitempty\": true\n }\n },\n \"description\": \"Configure how replication is executed in a cluster\"\n },\n \"invertedIndexConfig\": {\n \"type\": \"object\",\n \"properties\": {\n \"cleanupIntervalSeconds\": {\n \"type\": \"number\",\n \"description\": \"Asynchronous index clean up happens every n seconds (default: 60).\",\n \"format\": \"int\"\n },\n \"bm25\": {\n \"type\": \"object\",\n \"properties\": {\n \"k1\": {\n \"type\": \"number\",\n \"description\": \"Calibrates term-weight scaling based on the term frequency within a document (default: 1.2).\",\n \"format\": \"float\"\n },\n \"b\": {\n \"type\": \"number\",\n \"description\": \"Calibrates term-weight scaling based on the document length (default: 0.75).\",\n \"format\": \"float\"\n }\n },\n \"description\": \"Tuning parameters for the BM25 algorithm.\"\n },\n \"stopwords\": {\n \"type\": \"object\",\n \"properties\": {\n \"preset\": {\n \"type\": \"string\",\n \"description\": \"Pre-existing list of common words by language (default: `en`). Options: [`en`, `none`].\"\n },\n \"additions\": {\n \"type\": \"array\",\n \"description\": \"Stopwords to be considered additionally (default: []). Can be any array of custom strings.\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"removals\": {\n \"type\": \"array\",\n \"description\": \"Stopwords to be removed from consideration (default: []). Can be any array of custom strings.\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"description\": \"Fine-grained control over stopword list usage.\"\n },\n \"indexTimestamps\": {\n \"type\": \"boolean\",\n \"description\": \"Index each object by its internal timestamps (default: `false`).\"\n },\n \"indexNullState\": {\n \"type\": \"boolean\",\n \"description\": \"Index each object with the null state (default: `false`).\"\n },\n \"indexPropertyLength\": {\n \"type\": \"boolean\",\n \"description\": \"Index length of properties (default: `false`).\"\n },\n \"usingBlockMaxWAND\": {\n \"type\": \"boolean\",\n \"description\": \"Using BlockMax WAND for query execution (default: `false`, will be `true` for new collections created after 1.30).\"\n }\n },\n \"description\": \"Configure the inverted index built into Weaviate. See [Reference: Inverted index](https://docs.weaviate.io/weaviate/config-refs/indexing/inverted-index#inverted-index-parameters) for details.\"\n },\n \"multiTenancyConfig\": {\n \"type\": \"object\",\n \"properties\": {\n \"enabled\": {\n \"type\": \"boolean\",\n \"description\": \"Whether or not multi-tenancy is enabled for this collection (class) (default: `false`).\",\n \"x-omitempty\": false\n },\n \"autoTenantCreation\": {\n \"type\": \"boolean\",\n \"description\": \"Nonexistent tenants should (not) be created implicitly (default: `false`).\",\n \"x-omitempty\": false\n },\n \"autoTenantActivation\": {\n \"type\": \"boolean\",\n \"description\": \"Existing tenants should (not) be turned HOT implicitly when they are accessed and in another activity status (default: `false`).\",\n \"x-omitempty\": false\n }\n },\n \"description\": \"Configuration related to multi-tenancy within a collection (class)\"\n },\n \"vectorizer\": {\n \"type\": \"string\",\n \"description\": \"Specify how the vectors for this collection should be determined. The options are either `none` - this means you have to import a vector with each object yourself - or the name of a module that provides vectorization capabilities, such as `text2vec-weaviate`. If left empty, it will use the globally configured default ([`DEFAULT_VECTORIZER_MODULE`](https://docs.weaviate.io/deploy/configuration/env-vars)) which can itself either be `none` or a specific module.\"\n },\n \"moduleConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Configuration specific to modules in a collection context.\"\n },\n \"description\": {\n \"type\": \"string\",\n \"description\": \"Description of the collection for metadata purposes.\"\n },\n \"properties\": {\n \"type\": \"array\",\n \"description\": \"Define properties of the collection.\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"dataType\": {\n \"type\": \"array\",\n \"description\": \"Data type of the property (required). If it starts with a capital (for example Person), may be a reference to another type.\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"description\": {\n \"type\": \"string\",\n \"description\": \"Description of the property.\"\n },\n \"moduleConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Configuration specific to modules in a collection context.\"\n },\n \"name\": {\n \"type\": \"string\",\n \"description\": \"The name of the property (required). Multiple words should be concatenated in camelCase, e.g. `nameOfAuthor`.\"\n },\n \"indexInverted\": {\n \"type\": \"boolean\",\n \"description\": \"(Deprecated). Whether to include this property in the inverted index. If `false`, this property cannot be used in `where` filters, `bm25` or `hybrid` search.
Unrelated to vectorization behavior (deprecated as of v1.19; use indexFilterable or/and indexSearchable instead)\",\n \"nullable\": true\n },\n \"indexFilterable\": {\n \"type\": \"boolean\",\n \"description\": \"Whether to include this property in the filterable, Roaring Bitmap index. If `false`, this property cannot be used in `where` filters.
Note: Unrelated to vectorization behavior.\",\n \"nullable\": true\n },\n \"indexSearchable\": {\n \"type\": \"boolean\",\n \"description\": \"Optional. Should this property be indexed in the inverted index. Defaults to true. Applicable only to properties of data type text and text[]. If you choose false, you will not be able to use this property in bm25 or hybrid search. This property has no affect on vectorization decisions done by modules\",\n \"nullable\": true\n },\n \"indexRangeFilters\": {\n \"type\": \"boolean\",\n \"description\": \"Whether to include this property in the filterable, range-based Roaring Bitmap index. Provides better performance for range queries compared to filterable index in large datasets. Applicable only to properties of data type int, number, date.\",\n \"nullable\": true\n },\n \"tokenization\": {\n \"type\": \"string\",\n \"description\": \"Determines how a property is indexed. This setting applies to `text` and `text[]` data types. The following tokenization methods are available:
- `word` (default): Splits the text on any non-alphanumeric characters and lowercases the tokens.
- `lowercase`: Splits the text on whitespace and lowercases the tokens.
- `whitespace`: Splits the text on whitespace. This tokenization is case-sensitive.
- `field`: Indexes the entire property value as a single token after trimming whitespace.
- `trigram`: Splits the property into rolling trigrams (three-character sequences).
- `gse`: Uses the `gse` tokenizer, suitable for Chinese language text. [See `gse` docs](https://pkg.go.dev/github.com/go-ego/gse#section-readme).
- `kagome_ja`: Uses the `Kagome` tokenizer with a Japanese (IPA) dictionary. [See `kagome` docs](https://github.com/ikawaha/kagome).
- `kagome_kr`: Uses the `Kagome` tokenizer with a Korean dictionary. [See `kagome` docs](https://github.com/ikawaha/kagome).
See [Reference: Tokenization](https://docs.weaviate.io/weaviate/config-refs/collections#tokenization) for details.\",\n \"enum\": [\n \"word\",\n \"lowercase\",\n \"whitespace\",\n \"field\",\n \"trigram\",\n \"gse\",\n \"kagome_kr\",\n \"kagome_ja\",\n \"gse_ch\"\n ]\n },\n \"nestedProperties\": {\n \"type\": \"array\",\n \"description\": \"The properties of the nested object(s). Applies to object and object[] data types.\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"dataType\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"description\": {\n \"type\": \"string\"\n },\n \"name\": {\n \"type\": \"string\"\n },\n \"indexFilterable\": {\n \"type\": \"boolean\",\n \"nullable\": true\n },\n \"indexSearchable\": {\n \"type\": \"boolean\",\n \"nullable\": true\n },\n \"indexRangeFilters\": {\n \"type\": \"boolean\",\n \"nullable\": true\n },\n \"tokenization\": {\n \"type\": \"string\",\n \"enum\": [\n \"word\",\n \"lowercase\",\n \"whitespace\",\n \"field\",\n \"trigram\",\n \"gse\",\n \"kagome_kr\",\n \"kagome_ja\",\n \"gse_ch\"\n ]\n },\n \"nestedProperties\": {\n \"type\": \"array\",\n \"description\": \"The properties of the nested object(s). Applies to object and object[] data types.\",\n \"items\": {\n \"$ref\": \"#/components/schemas/NestedProperty\",\n \"has_circular_reference\": true\n },\n \"x-omitempty\": true\n }\n }\n },\n \"x-omitempty\": true\n }\n }\n }\n }\n }\n }\n },\n \"application/json\": {\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"class\": {\n \"type\": \"string\",\n \"description\": \"Name of the collection (formerly 'class') (required). Multiple words should be concatenated in CamelCase, e.g. `ArticleAuthor`.\"\n },\n \"vectorConfig\": {\n \"type\": \"object\",\n \"additionalProperties\": {\n \"type\": \"object\",\n \"properties\": {\n \"vectorizer\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Configuration of a specific vectorizer used by this vector\"\n },\n \"vectorIndexType\": {\n \"type\": \"string\",\n \"description\": \"Name of the vector index to use, eg. (HNSW)\"\n },\n \"vectorIndexConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Vector-index config, that is specific to the type of index selected in vectorIndexType\"\n }\n }\n },\n \"description\": \"Configure named vectors. Either use this field or `vectorizer`, `vectorIndexType`, and `vectorIndexConfig` fields. Available from `v1.24.0`.\"\n },\n \"vectorIndexType\": {\n \"type\": \"string\",\n \"description\": \"Name of the vector index type to use for the collection (e.g. `hnsw` or `flat`).\"\n },\n \"vectorIndexConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Vector-index config, that is specific to the type of index selected in vectorIndexType\"\n },\n \"shardingConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Manage how the index should be sharded and distributed in the cluster\"\n },\n \"replicationConfig\": {\n \"type\": \"object\",\n \"properties\": {\n \"factor\": {\n \"type\": \"integer\",\n \"description\": \"Number of times a collection (class) is replicated (default: 1).\"\n },\n \"asyncEnabled\": {\n \"type\": \"boolean\",\n \"description\": \"Enable asynchronous replication (default: `false`).\",\n \"x-omitempty\": false\n },\n \"deletionStrategy\": {\n \"type\": \"string\",\n \"description\": \"Conflict resolution strategy for deleted objects.\",\n \"enum\": [\n \"NoAutomatedResolution\",\n \"DeleteOnConflict\",\n \"TimeBasedResolution\"\n ],\n \"x-omitempty\": true\n }\n },\n \"description\": \"Configure how replication is executed in a cluster\"\n },\n \"invertedIndexConfig\": {\n \"type\": \"object\",\n \"properties\": {\n \"cleanupIntervalSeconds\": {\n \"type\": \"number\",\n \"description\": \"Asynchronous index clean up happens every n seconds (default: 60).\",\n \"format\": \"int\"\n },\n \"bm25\": {\n \"type\": \"object\",\n \"properties\": {\n \"k1\": {\n \"type\": \"number\",\n \"description\": \"Calibrates term-weight scaling based on the term frequency within a document (default: 1.2).\",\n \"format\": \"float\"\n },\n \"b\": {\n \"type\": \"number\",\n \"description\": \"Calibrates term-weight scaling based on the document length (default: 0.75).\",\n \"format\": \"float\"\n }\n },\n \"description\": \"Tuning parameters for the BM25 algorithm.\"\n },\n \"stopwords\": {\n \"type\": \"object\",\n \"properties\": {\n \"preset\": {\n \"type\": \"string\",\n \"description\": \"Pre-existing list of common words by language (default: `en`). Options: [`en`, `none`].\"\n },\n \"additions\": {\n \"type\": \"array\",\n \"description\": \"Stopwords to be considered additionally (default: []). Can be any array of custom strings.\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"removals\": {\n \"type\": \"array\",\n \"description\": \"Stopwords to be removed from consideration (default: []). Can be any array of custom strings.\",\n \"items\": {\n \"type\": \"string\"\n }\n }\n },\n \"description\": \"Fine-grained control over stopword list usage.\"\n },\n \"indexTimestamps\": {\n \"type\": \"boolean\",\n \"description\": \"Index each object by its internal timestamps (default: `false`).\"\n },\n \"indexNullState\": {\n \"type\": \"boolean\",\n \"description\": \"Index each object with the null state (default: `false`).\"\n },\n \"indexPropertyLength\": {\n \"type\": \"boolean\",\n \"description\": \"Index length of properties (default: `false`).\"\n },\n \"usingBlockMaxWAND\": {\n \"type\": \"boolean\",\n \"description\": \"Using BlockMax WAND for query execution (default: `false`, will be `true` for new collections created after 1.30).\"\n }\n },\n \"description\": \"Configure the inverted index built into Weaviate. See [Reference: Inverted index](https://docs.weaviate.io/weaviate/config-refs/indexing/inverted-index#inverted-index-parameters) for details.\"\n },\n \"multiTenancyConfig\": {\n \"type\": \"object\",\n \"properties\": {\n \"enabled\": {\n \"type\": \"boolean\",\n \"description\": \"Whether or not multi-tenancy is enabled for this collection (class) (default: `false`).\",\n \"x-omitempty\": false\n },\n \"autoTenantCreation\": {\n \"type\": \"boolean\",\n \"description\": \"Nonexistent tenants should (not) be created implicitly (default: `false`).\",\n \"x-omitempty\": false\n },\n \"autoTenantActivation\": {\n \"type\": \"boolean\",\n \"description\": \"Existing tenants should (not) be turned HOT implicitly when they are accessed and in another activity status (default: `false`).\",\n \"x-omitempty\": false\n }\n },\n \"description\": \"Configuration related to multi-tenancy within a collection (class)\"\n },\n \"vectorizer\": {\n \"type\": \"string\",\n \"description\": \"Specify how the vectors for this collection should be determined. The options are either `none` - this means you have to import a vector with each object yourself - or the name of a module that provides vectorization capabilities, such as `text2vec-weaviate`. If left empty, it will use the globally configured default ([`DEFAULT_VECTORIZER_MODULE`](https://docs.weaviate.io/deploy/configuration/env-vars)) which can itself either be `none` or a specific module.\"\n },\n \"moduleConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Configuration specific to modules in a collection context.\"\n },\n \"description\": {\n \"type\": \"string\",\n \"description\": \"Description of the collection for metadata purposes.\"\n },\n \"properties\": {\n \"type\": \"array\",\n \"description\": \"Define properties of the collection.\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"dataType\": {\n \"type\": \"array\",\n \"description\": \"Data type of the property (required). If it starts with a capital (for example Person), may be a reference to another type.\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"description\": {\n \"type\": \"string\",\n \"description\": \"Description of the property.\"\n },\n \"moduleConfig\": {\n \"type\": \"object\",\n \"properties\": {},\n \"description\": \"Configuration specific to modules in a collection context.\"\n },\n \"name\": {\n \"type\": \"string\",\n \"description\": \"The name of the property (required). Multiple words should be concatenated in camelCase, e.g. `nameOfAuthor`.\"\n },\n \"indexInverted\": {\n \"type\": \"boolean\",\n \"description\": \"(Deprecated). Whether to include this property in the inverted index. If `false`, this property cannot be used in `where` filters, `bm25` or `hybrid` search.
Unrelated to vectorization behavior (deprecated as of v1.19; use indexFilterable or/and indexSearchable instead)\",\n \"nullable\": true\n },\n \"indexFilterable\": {\n \"type\": \"boolean\",\n \"description\": \"Whether to include this property in the filterable, Roaring Bitmap index. If `false`, this property cannot be used in `where` filters.
Note: Unrelated to vectorization behavior.\",\n \"nullable\": true\n },\n \"indexSearchable\": {\n \"type\": \"boolean\",\n \"description\": \"Optional. Should this property be indexed in the inverted index. Defaults to true. Applicable only to properties of data type text and text[]. If you choose false, you will not be able to use this property in bm25 or hybrid search. This property has no affect on vectorization decisions done by modules\",\n \"nullable\": true\n },\n \"indexRangeFilters\": {\n \"type\": \"boolean\",\n \"description\": \"Whether to include this property in the filterable, range-based Roaring Bitmap index. Provides better performance for range queries compared to filterable index in large datasets. Applicable only to properties of data type int, number, date.\",\n \"nullable\": true\n },\n \"tokenization\": {\n \"type\": \"string\",\n \"description\": \"Determines how a property is indexed. This setting applies to `text` and `text[]` data types. The following tokenization methods are available:
- `word` (default): Splits the text on any non-alphanumeric characters and lowercases the tokens.
- `lowercase`: Splits the text on whitespace and lowercases the tokens.
- `whitespace`: Splits the text on whitespace. This tokenization is case-sensitive.
- `field`: Indexes the entire property value as a single token after trimming whitespace.
- `trigram`: Splits the property into rolling trigrams (three-character sequences).
- `gse`: Uses the `gse` tokenizer, suitable for Chinese language text. [See `gse` docs](https://pkg.go.dev/github.com/go-ego/gse#section-readme).
- `kagome_ja`: Uses the `Kagome` tokenizer with a Japanese (IPA) dictionary. [See `kagome` docs](https://github.com/ikawaha/kagome).
- `kagome_kr`: Uses the `Kagome` tokenizer with a Korean dictionary. [See `kagome` docs](https://github.com/ikawaha/kagome).
See [Reference: Tokenization](https://docs.weaviate.io/weaviate/config-refs/collections#tokenization) for details.\",\n \"enum\": [\n \"word\",\n \"lowercase\",\n \"whitespace\",\n \"field\",\n \"trigram\",\n \"gse\",\n \"kagome_kr\",\n \"kagome_ja\",\n \"gse_ch\"\n ]\n },\n \"nestedProperties\": {\n \"type\": \"array\",\n \"description\": \"The properties of the nested object(s). Applies to object and object[] data types.\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"dataType\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"string\"\n }\n },\n \"description\": {\n \"type\": \"string\"\n },\n \"name\": {\n \"type\": \"string\"\n },\n \"indexFilterable\": {\n \"type\": \"boolean\",\n \"nullable\": true\n },\n \"indexSearchable\": {\n \"type\": \"boolean\",\n \"nullable\": true\n },\n \"indexRangeFilters\": {\n \"type\": \"boolean\",\n \"nullable\": true\n },\n \"tokenization\": {\n \"type\": \"string\",\n \"enum\": [\n \"word\",\n \"lowercase\",\n \"whitespace\",\n \"field\",\n \"trigram\",\n \"gse\",\n \"kagome_kr\",\n \"kagome_ja\",\n \"gse_ch\"\n ]\n },\n \"nestedProperties\": {\n \"type\": \"array\",\n \"description\": \"The properties of the nested object(s). Applies to object and object[] data types.\",\n \"items\": {\n \"$ref\": \"#/components/schemas/NestedProperty\",\n \"has_circular_reference\": true\n },\n \"x-omitempty\": true\n }\n }\n },\n \"x-omitempty\": true\n }\n }\n }\n }\n }\n }\n }\n },\n \"required\": true\n}",
"use_request_body_schema_mode": true,
"validate_request_body_schema": false
}
}