> ## Documentation Index > Fetch the complete documentation index at: https://docs.mixpeek.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Get extractor details > Get detailed information about a specific extractor. Works for both builtin extractors and custom plugins. **Parameters:** - `extractor_id`: Extractor identifier (e.g., 'text_extractor_v1', 'my_custom_plugin_1_0_0') **Response includes:** - Full schema information (input, output, parameters) - Vector index configuration - For custom plugins: deployment status, validation status ## OpenAPI ````yaml get /v1/namespaces/{namespace_id}/extractors/{extractor_id} openapi: 3.1.0 info: title: Mixpeek API description: >- This is the Mixpeek API, providing access to various endpoints for data processing and retrieval. termsOfService: https://mixpeek.com/terms contact: name: Mixpeek Support url: https://mixpeek.com/contact email: info@mixpeek.com version: '0.82' servers: - url: https://api.mixpeek.com description: Production security: [] paths: /v1/namespaces/{namespace_id}/extractors/{extractor_id}: get: tags: - Namespace Extractors summary: Get extractor details description: >- Get detailed information about a specific extractor. Works for both builtin extractors and custom plugins. **Parameters:** - `extractor_id`: Extractor identifier (e.g., 'text_extractor_v1', 'my_custom_plugin_1_0_0') **Response includes:** - Full schema information (input, output, parameters) - Vector index configuration - For custom plugins: deployment status, validation status operationId: get_extractor_v1_namespaces__namespace_id__extractors__extractor_id__get parameters: - name: namespace_id in: path required: true schema: type: string title: Namespace Id - name: extractor_id in: path required: true schema: type: string title: Extractor Id responses: '200': description: Extractor details content: application/json: schema: $ref: '#/components/schemas/UnifiedExtractorResponse' '400': description: Bad Request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '403': description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Extractor not found content: application/json: example: detail: Extractor 'unknown_extractor_v1' not found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '500': description: Internal Server Error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: UnifiedExtractorResponse: properties: feature_extractor_name: type: string title: Feature Extractor Name description: Name of the feature extractor version: type: string title: Version description: Version of the feature extractor feature_extractor_id: type: string title: Feature Extractor Id description: Unique identifier (name_version) source: $ref: '#/components/schemas/ExtractorSource' description: >- Origin of this extractor: 'builtin' (shipped with Mixpeek), 'custom' (user-uploaded plugin), or 'community' (marketplace) description: type: string title: Description description: Human-readable description icon: type: string title: Icon description: Lucide-react icon name for frontend rendering default: box input_schema: additionalProperties: true type: object title: Input Schema description: JSON schema for input data output_schema: additionalProperties: true type: object title: Output Schema description: JSON schema for output data parameter_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Parameter Schema description: JSON schema for parameters type_mode: anyOf: - type: string - type: 'null' title: Type Mode description: >- What input types this extractor can handle: 'type_specific' (only one type, e.g. video-only) or 'multimodal' (handles multiple types with conditional processing). Type-specific extractors cannot use automatic-typed bucket properties. expected_input_types: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Expected Input Types description: >- For type-specific extractors: maps input keys to required types (e.g., {'video': 'video', 'thumbnail': 'image'}). For multimodal extractors: null. inference_type: anyOf: - type: string - type: 'null' title: Inference Type description: >- Kind of real-time inference this extractor provides: 'embedding', 'rerank', 'classify', 'generate', or 'general'. Determines which retriever stages are compatible. Null if the extractor is batch-only. supported_input_types: items: type: string type: array title: Supported Input Types description: Supported input types (video, image, text, etc.) max_inputs: additionalProperties: type: integer type: object title: Max Inputs description: Maximum number of inputs per type default_parameters: additionalProperties: true type: object title: Default Parameters description: Default parameter values costs: anyOf: - $ref: '#/components/schemas/CostsInfo' - type: 'null' description: Credit cost information (builtin extractors only) required_vector_indexes: anyOf: - items: $ref: '#/components/schemas/VectorIndexDefinition' type: array - type: 'null' title: Required Vector Indexes description: Vector indexes this extractor produces required_payload_indexes: anyOf: - items: $ref: '#/components/schemas/PayloadIndexConfig-Output' type: array - type: 'null' title: Required Payload Indexes description: Payload indexes required by this extractor position_fields: items: type: string type: array title: Position Fields description: >- Fields that identify unique positions within output documents. Used for deterministic document ID generation. feature_uri: anyOf: - type: string - type: 'null' title: Feature Uri description: Primary feature URI (e.g., mixpeek://text_extractor@v1/embedding) capabilities: items: type: string type: array title: Capabilities description: >- What this extractor can do: 'batch' (feature extraction during ingestion), 'realtime' (query-time inference for retriever stages) example_usage: anyOf: - additionalProperties: true type: object - type: 'null' title: Example Usage description: >- Minimal working configuration for namespace + collection + input_mappings + parameters plugin_id: anyOf: - type: string - type: 'null' title: Plugin Id description: Plugin ID (custom plugins only) deployed: anyOf: - type: boolean - type: 'null' title: Deployed description: Whether the plugin is deployed (custom plugins only) validation_status: anyOf: - type: string enum: - passed - failed - pending - type: 'null' title: Validation Status description: Validation status (custom plugins only) created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation timestamp (custom plugins only) updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Last update timestamp (custom plugins only) type: object required: - feature_extractor_name - version - feature_extractor_id - source - description - input_schema - output_schema title: UnifiedExtractorResponse description: |- Unified extractor response combining builtin and custom plugins. This model provides a consistent view of all extractors available to a namespace, regardless of whether they are builtin or custom. ErrorResponse: properties: success: type: boolean title: Success description: Always false for error responses default: false status: type: integer title: Status description: HTTP status code for this error error: $ref: '#/components/schemas/ErrorDetail' description: Error details payload type: object required: - status - error title: ErrorResponse description: Error response model. examples: - error: details: id: ns_123 resource: namespace message: Namespace not found type: NotFoundError status: 404 success: false HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ExtractorSource: type: string enum: - builtin - custom - community title: ExtractorSource description: |- The source/origin of a feature extractor. Values: BUILTIN: Core extractors shipped with Mixpeek (text, image, multimodal, etc.) CUSTOM: User-created extractors uploaded to their namespace (Enterprise only) COMMUNITY: Community-contributed extractors from the Mixpeek marketplace This field helps API consumers understand: - What level of support/maintenance to expect - Whether the extractor is available to all users or namespace-specific - Licensing and attribution requirements CostsInfo: properties: tier: type: integer maximum: 4 minimum: 1 title: Tier description: 'Cost tier (1-4): 1=SIMPLE, 2=MODERATE, 3=COMPLEX, 4=PREMIUM' tier_label: type: string title: Tier Label description: Human-readable tier label (SIMPLE, MODERATE, COMPLEX, PREMIUM) rates: items: $ref: '#/components/schemas/CostRate' type: array title: Rates description: >- List of cost rates for different input types this extractor processes type: object required: - tier - tier_label - rates title: CostsInfo description: >- Credit cost information for a feature extractor. Describes the pricing tier and standardized cost rates for using this extractor. Rates are defined using CostUnit types that align with extractor input types. VectorIndexDefinition: properties: feature_uri: anyOf: - type: string - type: 'null' title: Feature Uri description: >- Full feature URI for this vector index. Format: mixpeek://{extractor}@{version}/{output_name}. Populated at collection creation time. Use this URI in retriever feature_filter stages. examples: - mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1 - mixpeek://multimodal_extractor@v1/vertex_multimodal_embedding name: type: string minLength: 1 title: Name description: >- REQUIRED. Short user-facing output name used in feature URIs. This is NOT the Qdrant collection name - it's the clean identifier for this output. Format: Simple snake_case name (e.g., 'embedding', 'video_embedding', 'sparse_embedding'). Used in feature URIs: mixpeek://{extractor}@{version}/{THIS_NAME}. Must be unique within this extractor's outputs. examples: - embedding - video_embedding - transcription_embedding - sparse_embedding description: type: string minLength: 10 title: Description description: >- REQUIRED. Human-readable description of this vector output. Explain what content this output embeds and when to use it. Appears in API documentation and helps users choose the right feature URI. Be specific about the embedding type and use cases. examples: - Vector index for video segment embeddings - Dense text embeddings for semantic search - Sparse keyword embeddings for explainable retrieval type: type: string enum: - single - multi title: Type description: >- REQUIRED. Index type - 'single' or 'multi'. 'single': One vector per document (most common). Use for standard embeddings. 'multi': Multiple named vectors per document (rare). Use for hybrid/ensemble. Determines whether 'index' field contains VectorIndex or MultiVectorIndex. examples: - single - multi index: anyOf: - $ref: '#/components/schemas/VectorIndex' - $ref: '#/components/schemas/MultiVectorIndex' title: Index description: >- REQUIRED. Nested index configuration. VectorIndex if type='single' (most common case). MultiVectorIndex if type='multi' (rare, for hybrid search). Contains the full storage configuration including Qdrant collection name, dimensions, distance metric, and inference service. type: object required: - name - description - type - index title: VectorIndexDefinition description: >- Complete vector index definition that can be either single or multi-vector. This is the USER-FACING representation that appears in feature extractor definitions and API responses. It wraps a VectorIndex (or MultiVectorIndex) and adds metadata. Key Concepts - Two-Name System: - VectorIndexDefinition.name: SHORT user-facing name (e.g., "embedding") Used in feature URIs: mixpeek://text_extractor@v1/multilingual_e5_large_instruct_v1 ^^^^^^^^^^ - VectorIndex.name: FULL storage name (e.g., "text_extractor_v1_embedding") Used as Qdrant collection name for namespace isolation This two-level naming allows clean URIs while preventing storage collisions. Use Cases: - Define extractor outputs in feature extractor definitions - Expose available vector indexes in collection metadata - Enable feature URI resolution (short name → full storage name) Requirements: - name: REQUIRED - Short output name for feature URIs - description: REQUIRED - Explain what this output produces - type: REQUIRED - "single" (most common) or "multi" (rare) - index: REQUIRED - Nested VectorIndex or MultiVectorIndex - feature_uri: OPTIONAL - Populated at collection creation time examples: - description: Vector index for text embeddings using E5-Large model. index: datatype: float32 description: Dense vector embedding for text content dimensions: 1024 distance: cosine inference_name: multilingual_e5_large_instruct_v1 name: text_extractor_v1_embedding supported_inputs: - text - string type: dense name: embedding type: single - description: Vector index for video segment embeddings using multimodal model. index: datatype: float32 description: Dense vector embeddings for video segments dimensions: 1408 distance: cosine inference_name: vertex_multimodal_embedding name: multimodal_extractor_v1_video_embedding supported_inputs: - video - image type: dense name: video_embedding type: single - description: Hybrid dense + sparse embeddings for enhanced retrieval. index: description: Combined dense and sparse embeddings name: hybrid_extractor_v1_multi vectors: dense: description: Dense semantic embedding dimensions: 1024 distance: cosine inference_name: multilingual_e5_large_instruct_v1 name: hybrid_v1_dense type: dense sparse: description: Sparse keyword embedding distance: dot inference_name: splade_plus_plus_v1 name: hybrid_v1_sparse type: sparse name: hybrid_embedding type: multi PayloadIndexConfig-Output: properties: field_name: type: string maxLength: 255 minLength: 1 title: Field Name description: >- Name of the payload field to index. Must be unique within the namespace. Use dot notation for nested fields (e.g., 'metadata.title'). Cannot use protected system field names when is_protected=False. examples: - metadata.title - user_id - tags type: $ref: '#/components/schemas/PayloadSchemaType' description: >- Data type of the indexed field. Determines query capabilities and storage optimization. TEXT: Full-text search. KEYWORD: Exact matching, filtering. INTEGER/FLOAT: Range queries, sorting. DATETIME: Temporal queries. GEO: Geospatial queries. BOOL: Boolean filtering. UUID: Unique identifier matching. field_schema: anyOf: - $ref: '#/components/schemas/TextIndexParams' - $ref: '#/components/schemas/IntegerIndexParams' - $ref: '#/components/schemas/KeywordIndexParams' - $ref: '#/components/schemas/FloatIndexParams' - $ref: '#/components/schemas/GeoIndexParams' - $ref: '#/components/schemas/DatetimeIndexParams' - $ref: '#/components/schemas/UuidIndexParams' - $ref: '#/components/schemas/BoolIndexParams' - type: 'null' title: Field Schema description: >- Optional schema configuration for the index. If not provided, uses default parameters for the specified type. Different types support different parameters (e.g., KeywordIndexParams.is_tenant). is_protected: type: boolean title: Is Protected description: >- Whether this index is system-managed and cannot be modified by users. Protected indexes (is_protected=True) are created automatically by Mixpeek and are essential for internal operations like tenant isolation, lineage tracking, and document management. Users cannot create, modify, or delete protected indexes. User-created indexes always have is_protected=False. default: false type: object required: - field_name - type title: PayloadIndexConfig description: >- Configuration for a payload index. Defines the structure and behavior of a payload field index in Qdrant collections. Payload indexes enable efficient filtering and searching on document metadata. Protected Indexes: System-managed indexes (is_protected=True) cannot be modified or deleted by users. These are essential for Mixpeek's internal operations: - internal_id: Tenant isolation - namespace_id: Namespace scoping - collection_id, document_id: Document lineage - bucket_id, object_id, root_object_id, root_bucket_id, source_object_id: Object lineage - created_at, updated_at: Timestamps Use Cases: - Create custom metadata indexes for efficient filtering - Configure full-text search on text fields - Set up geospatial queries on location data - Enable range queries on numeric fields Requirements: - field_name: REQUIRED - Must be unique within the namespace - type: REQUIRED - Must match PayloadSchemaType enum - field_schema: OPTIONAL - Auto-generated from type if not provided - is_protected: OPTIONAL - Defaults to False (user-managed index) examples: - description: User-created text index for full-text search field_name: metadata.description is_protected: false type: text - description: User-created keyword index for exact filtering field_name: user_id is_protected: false type: keyword - description: System-managed protected index (created automatically) field_name: internal_id field_schema: is_tenant: true is_protected: true type: keyword ErrorDetail: properties: message: type: string title: Message description: Human-readable error message type: type: string title: Type description: Stable error type identifier (machine-readable) code: anyOf: - type: string - type: 'null' title: Code description: >- Fine-grained error code for programmatic handling (e.g., namespace_name_taken, feature_extractor_not_found). Present only when consumers may need to branch on a specific error condition. details: anyOf: - additionalProperties: true type: object - type: 'null' title: Details description: >- Optional structured details to help debugging (validation errors, IDs, etc.) type: object required: - message - type title: ErrorDetail description: Error detail model. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError CostRate: properties: unit: $ref: '#/components/schemas/CostUnit' description: The billing unit type credits_per_unit: type: integer minimum: 1 title: Credits Per Unit description: Number of credits charged per unit description: anyOf: - type: string - type: 'null' title: Description description: Human-readable description of what this rate covers type: object required: - unit - credits_per_unit title: CostRate description: |- Cost rate for a specific billing unit. Defines how many credits are charged per unit of a specific type. Example: CostRate( unit=CostUnit.MINUTE, credits_per_unit=200, description="Video processing" ) # Means: 200 credits per minute of video VectorIndex: properties: name: anyOf: - type: string - type: 'null' title: Name description: >- OPTIONAL. Qdrant named vector identifier. If not provided, auto-derived from inference_service_id using the same conversion as inference_name (org/model -> org__model with hyphens as underscores). This enables cross-extractor compatibility: extractors using the same model will share the same named vector in Qdrant, allowing direct vector search across collections without fusion logic. examples: - intfloat__multilingual_e5_large_instruct - google__siglip_base_patch16_224 - jinaai__jina_embeddings_v2_base_code description: type: string minLength: 10 title: Description description: >- REQUIRED. Human-readable description of what this vector index represents. Explain the content type, use cases, and search characteristics. Shown in API documentation and collection metadata. Be specific about what embeddings are stored here. examples: - Dense vector embedding for text content using E5-Large model - Video segment embeddings for semantic visual search - Sparse keyword expansion embeddings for explainable search dimensions: anyOf: - type: integer minimum: 1 - type: 'null' title: Dimensions description: >- Number of vector dimensions. REQUIRED for DENSE vectors (e.g., 1024 for E5-Large, 1408 for multimodal). NOT REQUIRED for SPARSE vectors (dimensions determined dynamically). Must match the output dimensions of the inference service. Cannot be changed after index creation without recreating the collection. examples: - 1024 - 1408 - 768 - 512 type: $ref: '#/components/schemas/VectorType' description: >- REQUIRED. Vector storage format type. Determines how vectors are stored and searched in Qdrant. Use DENSE for traditional embeddings (most common), SPARSE for keyword-based models like SPLADE, MULTI_DENSE for late-interaction models like ColBERT. Must match the output format of your inference service. examples: - dense - sparse - multi_dense distance: anyOf: - type: string - type: 'null' title: Distance description: >- Distance metric for similarity search. OPTIONAL - defaults to 'cosine' (normalized dot product). Options: 'cosine' (most common, normalized), 'dot' (raw dot product), 'euclidean' (L2 distance), 'manhattan' (L1 distance). Cosine recommended for most embeddings as it's scale-invariant. Must match the metric your model was trained with. default: cosine examples: - cosine - dot - euclidean datatype: anyOf: - $ref: '#/components/schemas/VectorDataType' - type: 'null' description: >- Data type for storing vector values. OPTIONAL - defaults to FLOAT32 (standard precision). Use FLOAT32 for general use (4 bytes per dimension). Use FLOAT16 to save 50% storage with minimal quality loss. Use UINT8 for maximum compression (quantization, ~2% quality loss). Lower precision = smaller storage + faster search, slightly lower accuracy. default: float32 examples: - float32 - float16 - uint8 on_disk: anyOf: - type: boolean - type: 'null' title: On Disk description: >- OPTIONAL. If true, vectors stored on disk instead of RAM. Defaults to true for memory efficiency. Set to false for faster search with higher memory usage. Trade-off: on_disk=true saves ~95% RAM but ~10x slower search. Recommended to keep default (true) unless RAM is abundant and low latency critical. supported_inputs: anyOf: - items: $ref: '#/components/schemas/BucketSchemaFieldType' type: array - type: 'null' title: Supported Inputs description: >- OPTIONAL. List of bucket schema field types this vector can process. Validates that input fields are compatible with this index. Examples: TEXT and STRING for text embeddings, VIDEO and IMAGE for multimodal embeddings, DOCUMENT for PDF extractors. Used for validation during collection creation. examples: - - text - string - - video - image - - document inference_name: anyOf: - type: string - type: 'null' title: Inference Name description: >- DEPRECATED: Use inference_service_id instead. Identifier of the inference service to generate embeddings. Must reference a valid inference service registered in the system. Examples: 'multilingual_e5_large_instruct_v1' for text, 'vertex_multimodal_embedding' for video, 'laion_clip_vit_l_14_v1' for images. This determines which model creates the vectors during ingestion. Cannot be changed after collection creation. examples: - multilingual_e5_large_instruct_v1 - vertex_multimodal_embedding - laion_clip_vit_l_14_v1 - openai_text_embedding_3_small inference_service_id: anyOf: - type: string - type: 'null' title: Inference Service Id description: >- RECOMMENDED. Service ID in org/name format (e.g., 'intfloat/e5-large'). When set, dimensions and distance are automatically derived from the registry. This is the canonical identifier for cross-plugin compatibility. Plugins using the same service_id can search across each other's vectors. Takes precedence over inference_name when both are set. examples: - intfloat/e5-large - google/vertex-multimodal - google/siglip - jinaai/jina-code-v2 purpose: anyOf: - $ref: '#/components/schemas/VectorPurpose' - type: 'null' description: >- RECOMMENDED. Semantic purpose of this vector index. Enables pipelines to look up vector configs by purpose (text, code, image) without needing to know the specific inference_service_id. This provides automatic configuration - the pipeline just says 'give me the text vector' and gets the correct column name. If not specified, pipeline must use inference_service_id lookup. examples: - text - code - image - multimodal vector_name_override: anyOf: - type: string - type: 'null' title: Vector Name Override description: >- OPTIONAL. Override for Qdrant named vector identifier. When set, this value is used as the Qdrant vector name instead of auto-deriving from inference_service_id. This enables multiple vectors from the same embedding model with different storage names. The inference_service_id is still used for cross-extractor compatibility checking, but storage uses this custom name. Use case: A single extractor producing N vectors (e.g., title_embedding, body_embedding) using the same model but needing separate storage. examples: - title_embedding - body_embedding - summary_embedding supports_multi_query: type: boolean title: Supports Multi Query description: >- Whether this vector index supports multi-content queries at retrieval time. When True, the feature_search stage accepts input_mode='multi_content' — a list of URLs and/or text strings that are embedded together in one API call to produce a single query vector. Only set for extractors whose underlying model natively supports multi-file input (e.g., gemini_multifile_extractor using Gemini Embedding 2). default: false type: object required: - description - type title: VectorIndex description: >- Configuration for a single vector index in Qdrant. Defines the fully-qualified vector index including storage name, dimensions, distance metric, and inference service. This is the actual index that gets created in Qdrant and used for vector similarity search. Key Concepts: - The `name` field is the FULL qualified name used as the Qdrant collection name - Format: {extractor}_{version}_{output} (e.g., "text_extractor_v1_embedding") - This ensures namespace isolation between extractors and versions - Different from VectorIndexDefinition.name which is the short user-facing name Use Cases: - Define vector storage configuration for feature extractors - Specify inference service and model parameters - Configure distance metrics for similarity search - Set storage optimization (on-disk for large vectors) Requirements: - name: REQUIRED - Must be unique across all extractors in namespace - description: REQUIRED - Explain what this vector represents - dimensions: REQUIRED for DENSE vectors, OPTIONAL for SPARSE - type: REQUIRED - Must match VectorType enum - inference_name: REQUIRED - Must reference a valid inference service examples: - datatype: float32 description: >- Dense vector embedding for text content using E5-Large multilingual model. Optimized for semantic search across 100+ languages. dimensions: 1024 distance: cosine inference_name: multilingual_e5_large_instruct_v1 name: text_extractor_v1_embedding supported_inputs: - text - string type: dense - datatype: float32 description: >- Dense vector embeddings for video segments using Google's multimodal model. Supports visual semantic search. dimensions: 1408 distance: cosine inference_name: vertex_multimodal_embedding name: multimodal_extractor_v1_video_embedding supported_inputs: - video - image type: dense - datatype: float32 description: >- Dense vector embeddings for images using SigLIP model. Supports visual semantic search. dimensions: 768 distance: cosine inference_name: siglip_base_v1 name: image_extractor_v1_embedding supported_inputs: - image type: dense - description: >- Title embedding using E5-Large - same model as body but stored separately. inference_service_id: intfloat/multilingual-e5-large-instruct type: dense vector_name_override: title_embedding - description: >- Body embedding using E5-Large - same model as title but stored separately. inference_service_id: intfloat/multilingual-e5-large-instruct type: dense vector_name_override: body_embedding MultiVectorIndex: properties: name: type: string minLength: 1 title: Name description: >- REQUIRED. Fully-qualified name for the multi-vector index. Format: {extractor}_{version}_{output} (e.g., 'hybrid_extractor_v1_multi'). Must be unique across namespace. examples: - hybrid_extractor_v1_multi - ensemble_v1_combined description: type: string minLength: 10 title: Description description: >- REQUIRED. Human-readable description of the multi-vector index. Explain what vector types are included and their purposes. Describe use cases for this multi-vector configuration. examples: - Hybrid dense + sparse embeddings for enhanced retrieval - Multi-model ensemble with BERT + RoBERTa embeddings vectors: additionalProperties: $ref: '#/components/schemas/VectorIndex' type: object title: Vectors description: >- REQUIRED. Dictionary mapping vector output names to their VectorIndex configurations. Each key is a unique identifier for that vector type within this multi-index. Each value is a complete VectorIndex with its own dimensions, type, and inference service. Example keys: 'dense', 'sparse', 'primary', 'secondary'. examples: - dense: dimensions: 1024 inference_name: e5_large name: hybrid_v1_dense type: dense sparse: inference_name: splade name: hybrid_v1_sparse type: sparse type: object required: - name - description - vectors title: MultiVectorIndex description: >- Configuration for multi-vector indexes. Allows a single extractor to produce multiple named vector outputs in one index. Useful for hybrid search combining different embedding types or multiple models. Use Cases: - Hybrid dense + sparse embeddings in one index - Multiple models for ensemble retrieval - Different granularities (sentence + paragraph embeddings) Requirements: - name: REQUIRED - Full qualified name for the multi-vector index - description: REQUIRED - Explain what vector combinations are included - vectors: REQUIRED - Dictionary mapping output names to VectorIndex configs Note: Currently less common than single VectorIndex. Most extractors use separate VectorIndexDefinitions for each output instead. examples: - description: >- Combined dense and sparse embeddings for hybrid search. Dense provides semantic understanding, sparse adds keyword precision. name: hybrid_extractor_v1_multi vectors: dense: datatype: float32 description: Dense semantic embedding dimensions: 1024 distance: cosine inference_name: multilingual_e5_large_instruct_v1 name: hybrid_v1_dense type: dense sparse: datatype: float32 description: Sparse keyword embedding distance: dot inference_name: splade_plus_plus_v1 name: hybrid_v1_sparse type: sparse PayloadSchemaType: type: string enum: - keyword - integer - float - bool - geo - datetime - text - uuid title: PayloadSchemaType description: Payload schema type. TextIndexParams: properties: type: type: string title: Type default: text tokenizer: $ref: '#/components/schemas/TokenizerType' default: word min_token_len: type: integer title: Min Token Len default: 2 max_token_len: type: integer title: Max Token Len default: 15 lowercase: type: boolean title: Lowercase default: true type: object title: TextIndexParams description: Configuration for text index. IntegerIndexParams: properties: type: type: string title: Type default: integer lookup: type: boolean title: Lookup default: true range: type: boolean title: Range default: true type: object title: IntegerIndexParams description: Configuration for integer index. KeywordIndexParams: properties: type: type: string title: Type default: keyword is_tenant: type: boolean title: Is Tenant default: false type: object title: KeywordIndexParams description: Configuration for keyword index. FloatIndexParams: properties: type: type: string title: Type default: float type: object title: FloatIndexParams description: Configuration for float index. GeoIndexParams: properties: type: type: string title: Type default: geo type: object title: GeoIndexParams description: Configuration for geo index. DatetimeIndexParams: properties: type: type: string title: Type default: datetime type: object title: DatetimeIndexParams description: Configuration for datetime index. UuidIndexParams: properties: type: type: string title: Type default: uuid is_tenant: type: boolean title: Is Tenant default: false type: object title: UuidIndexParams description: Configuration for UUID index. BoolIndexParams: properties: type: type: string title: Type default: bool type: object title: BoolIndexParams description: Configuration for boolean index. CostUnit: type: string enum: - minute - image - 1k_tokens - page - face - extraction title: CostUnit description: |- Standard billing units aligned with extractor input types. Each unit represents a measurable quantity that extractors process: - MINUTE: Video/audio duration in minutes - IMAGE: Per image processed - TOKENS_1K: Text tokens in thousands - PAGE: Document pages (PDF, etc.) - FACE: Detected faces in images/video - EXTRACTION: Flat per-operation cost VectorType: type: string enum: - dense - sparse - multi_dense title: VectorType description: |- Vector types supported by the Mixpeek system. Defines the storage format and structure of embeddings in Qdrant. Values: DENSE: Traditional float array embeddings (e.g., [0.1, 0.2, 0.3]). Most common format. Used by: text_extractor, multimodal_extractor, image_extractor. Storage: ~4KB per 1024-dim vector. Fast cosine/dot similarity search. SPARSE: Index-value pairs for sparse embeddings (e.g., SPLADE, BM25). Only stores non-zero dimensions. Format: {indices: [1,5,9], values: [0.8,0.6,0.4]}. Storage: ~20KB. Keyword-based semantic search. MULTI_DENSE: List of dense vectors for late interaction models (e.g., ColBERT). Each document has multiple embeddings. Format: [[0.1,0.2], [0.3,0.4], ...]. Storage: ~500KB. High-precision retrieval. Examples: - DENSE for general semantic search (text_extractor, multimodal_extractor) - SPARSE for keyword expansion and explainability - MULTI_DENSE for maximum precision retrieval VectorDataType: type: string enum: - float32 - uint8 title: VectorDataType description: Vector data type. BucketSchemaFieldType: type: string enum: - string - number - integer - float - boolean - object - array - date - datetime - text - image - audio - video - pdf - excel title: BucketSchemaFieldType description: >- Supported data types for bucket schema fields. Types fall into two categories: 1. **Metadata Types** (JSON types): - Stored as object metadata - Standard JSON-compatible types - Not processed by extractors (unless explicitly mapped) - Examples: string, number, boolean, date 2. **File Types** (blobs): - Stored as files/blobs - Processed by extractors - Require file content (URL or base64) - Examples: text, image, video, pdf **GIF Special Handling**: GIF files can be declared as either IMAGE or VIDEO type: - As IMAGE: GIF is embedded as a single static image (first frame) - As VIDEO: GIF is decomposed frame-by-frame with embeddings per frame The multimodal extractor detects GIFs via MIME type (image/gif) and routes them based on your schema declaration. Use VIDEO for animated GIFs where frame-level search is needed, IMAGE for static/thumbnail use cases. NOTE: For retriever input schemas that need to accept document references (e.g., "find similar documents"), use RetrieverInputSchemaFieldType instead, which includes all bucket types plus document_reference. VectorPurpose: type: string enum: - text - code - image - multimodal - video - audio - sparse title: VectorPurpose description: |- Semantic purpose of a vector index. Used by pipelines to look up vector configs by purpose without needing to know the specific inference_service_id. TokenizerType: type: string enum: - word - whitespace - prefix - multilingual title: TokenizerType description: Tokenizer type. ````