> ## 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. # Describe collection features > List feature addresses and metadata available in this collection ## OpenAPI ````yaml get /v1/collections/{collection_identifier}/features 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/collections/{collection_identifier}/features: get: tags: - Collections summary: Describe collection features description: List feature addresses and metadata available in this collection operationId: >- describe_collection_features_route_v1_collections__collection_identifier__features_get parameters: - name: collection_identifier in: path required: true schema: type: string description: The ID or name of the collection to describe title: Collection Identifier description: The ID or name of the collection to describe responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/DescribeCollectionFeaturesResponse' '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: Not Found content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '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: DescribeCollectionFeaturesResponse: properties: features: items: $ref: '#/components/schemas/CollectionFeatureDescriptor' type: array title: Features description: Feature extractors and fields enabled on this collection type: object required: - features title: DescribeCollectionFeaturesResponse examples: - features: - feature_extractor_name: text_extractor inputs: - path: text type: string outputs: - dim: 1024 path: features.text_embedding type: vector version: v1 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 CollectionFeatureDescriptor: properties: feature_address: type: string title: Feature Address description: Fully qualified feature address feature_extractor_name: type: string title: Feature Extractor Name description: Extractor name version: type: string title: Version description: Extractor version vector_index: $ref: '#/components/schemas/VectorIndex' description: >- Vector index configuration (name, dimensions, type, distance, inference_name) primary: type: boolean title: Primary description: True if this is the primary output (short address allowed) default: false type: object required: - feature_address - feature_extractor_name - version - vector_index title: CollectionFeatureDescriptor description: >- Descriptor for a collection's available feature using existing models/keys. 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 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 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. ````