mixpeek 0.81.1

package/dist/models/vector-index-definition.d.ts

@@ -0,0 +1,55 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+import type { Index } from './index';
+/**
+ * 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
+ * @export
+ * @interface VectorIndexDefinition
+ */
+export interface VectorIndexDefinition {
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndexDefinition
+     */
+    'feature_uri'?: string;
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndexDefinition
+     */
+    'name': string;
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndexDefinition
+     */
+    'description': string;
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndexDefinition
+     */
+    'type': VectorIndexDefinitionTypeEnum;
+    /**
+     *
+     * @type {Index}
+     * @memberof VectorIndexDefinition
+     */
+    'index': Index;
+}
+export declare const VectorIndexDefinitionTypeEnum: {
+    readonly Single: "single";
+    readonly Multi: "multi";
+};
+export type VectorIndexDefinitionTypeEnum = typeof VectorIndexDefinitionTypeEnum[keyof typeof VectorIndexDefinitionTypeEnum];
+//# sourceMappingURL=vector-index-definition.d.ts.map

package/dist/models/vector-index-definition.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"vector-index-definition.d.ts","sourceRoot":"","sources":["../../models/vector-index-definition.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAKH,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,SAAS,CAAC;AAErC;;;;GAIG;AACH,MAAM,WAAW,qBAAqB;IAClC;;;;OAIG;IACH,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB;;;;OAIG;IACH,MAAM,EAAE,MAAM,CAAC;IACf;;;;OAIG;IACH,aAAa,EAAE,MAAM,CAAC;IACtB;;;;OAIG;IACH,MAAM,EAAE,6BAA6B,CAAC;IACtC;;;;OAIG;IACH,OAAO,EAAE,KAAK,CAAC;CAClB;AAED,eAAO,MAAM,6BAA6B;;;CAGhC,CAAC;AAEX,MAAM,MAAM,6BAA6B,GAAG,OAAO,6BAA6B,CAAC,MAAM,OAAO,6BAA6B,CAAC,CAAC"}

package/dist/models/vector-index.d.ts

@@ -0,0 +1,101 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+import type { BucketSchemaFieldType } from './bucket-schema-field-type';
+import type { VectorDataType } from './vector-data-type';
+import type { VectorPurpose } from './vector-purpose';
+import type { VectorType } from './vector-type';
+/**
+ * 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
+ * @export
+ * @interface VectorIndex
+ */
+export interface VectorIndex {
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndex
+     */
+    'name'?: string;
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndex
+     */
+    'description': string;
+    /**
+     * 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.
+     * @type {number}
+     * @memberof VectorIndex
+     */
+    'dimensions'?: number;
+    /**
+     * 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.
+     * @type {VectorType}
+     * @memberof VectorIndex
+     */
+    'type': VectorType;
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndex
+     */
+    'distance'?: string;
+    /**
+     * 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.
+     * @type {VectorDataType}
+     * @memberof VectorIndex
+     */
+    'datatype'?: VectorDataType;
+    /**
+     * 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.
+     * @type {boolean}
+     * @memberof VectorIndex
+     */
+    'on_disk'?: boolean;
+    /**
+     * 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.
+     * @type {Array<BucketSchemaFieldType>}
+     * @memberof VectorIndex
+     */
+    'supported_inputs'?: Array<BucketSchemaFieldType>;
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndex
+     */
+    'inference_name'?: string;
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndex
+     */
+    'inference_service_id'?: string;
+    /**
+     * 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.
+     * @type {VectorPurpose}
+     * @memberof VectorIndex
+     */
+    'purpose'?: VectorPurpose;
+    /**
+     * 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.
+     * @type {string}
+     * @memberof VectorIndex
+     */
+    'vector_name_override'?: string;
+    /**
+     * 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).
+     * @type {boolean}
+     * @memberof VectorIndex
+     */
+    'supports_multi_query'?: boolean;
+}
+//# sourceMappingURL=vector-index.d.ts.map

package/dist/models/vector-index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"vector-index.d.ts","sourceRoot":"","sources":["../../models/vector-index.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAKH,OAAO,KAAK,EAAE,qBAAqB,EAAE,MAAM,4BAA4B,CAAC;AAGxE,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,oBAAoB,CAAC;AAGzD,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAC;AAGtD,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAEhD;;;;GAIG;AACH,MAAM,WAAW,WAAW;IACxB;;;;OAIG;IACH,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB;;;;OAIG;IACH,aAAa,EAAE,MAAM,CAAC;IACtB;;;;OAIG;IACH,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB;;;;OAIG;IACH,MAAM,EAAE,UAAU,CAAC;IACnB;;;;OAIG;IACH,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB;;;;OAIG;IACH,UAAU,CAAC,EAAE,cAAc,CAAC;IAC5B;;;;OAIG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IACpB;;;;OAIG;IACH,kBAAkB,CAAC,EAAE,KAAK,CAAC,qBAAqB,CAAC,CAAC;IAClD;;;;OAIG;IACH,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B;;;;OAIG;IACH,sBAAsB,CAAC,EAAE,MAAM,CAAC;IAChC;;;;OAIG;IACH,SAAS,CAAC,EAAE,aAAa,CAAC;IAC1B;;;;OAIG;IACH,sBAAsB,CAAC,EAAE,MAAM,CAAC;IAChC;;;;OAIG;IACH,sBAAsB,CAAC,EAAE,OAAO,CAAC;CACpC"}

package/dist/models/vector-purpose.d.ts

@@ -0,0 +1,27 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+/**
+ * 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.
+ * @export
+ * @enum {string}
+ */
+export declare const VectorPurpose: {
+    readonly Text: "text";
+    readonly Code: "code";
+    readonly Image: "image";
+    readonly Multimodal: "multimodal";
+    readonly Video: "video";
+    readonly Audio: "audio";
+    readonly Sparse: "sparse";
+};
+export type VectorPurpose = typeof VectorPurpose[keyof typeof VectorPurpose];
+//# sourceMappingURL=vector-purpose.d.ts.map

package/dist/models/vector-purpose.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"vector-purpose.d.ts","sourceRoot":"","sources":["../../models/vector-purpose.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAIH;;;;GAIG;AAEH,eAAO,MAAM,aAAa;;;;;;;;CAQhB,CAAC;AAEX,MAAM,MAAM,aAAa,GAAG,OAAO,aAAa,CAAC,MAAM,OAAO,aAAa,CAAC,CAAC"}

package/dist/models/vector-type.d.ts

@@ -0,0 +1,23 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+/**
+ * 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
+ * @export
+ * @enum {string}
+ */
+export declare const VectorType: {
+    readonly Dense: "dense";
+    readonly Sparse: "sparse";
+    readonly MultiDense: "multi_dense";
+};
+export type VectorType = typeof VectorType[keyof typeof VectorType];
+//# sourceMappingURL=vector-type.d.ts.map

package/dist/models/vector-type.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"vector-type.d.ts","sourceRoot":"","sources":["../../models/vector-type.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAIH;;;;GAIG;AAEH,eAAO,MAAM,UAAU;;;;CAIb,CAAC;AAEX,MAAM,MAAM,UAAU,GAAG,OAAO,UAAU,CAAC,MAAM,OAAO,UAAU,CAAC,CAAC"}

package/dist/models/vectors.d.ts

@@ -0,0 +1,32 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+import type { RangeBucketBoundariesInner } from './range-bucket-boundaries-inner';
+/**
+ * Vector representation of the feature. Can be any supported vector type.
+ * @export
+ * @interface Vectors
+ */
+export interface Vectors {
+    /**
+     * Indices of non-zero elements
+     * @type {Array<RangeBucketBoundariesInner>}
+     * @memberof Vectors
+     */
+    'indices': Array<RangeBucketBoundariesInner>;
+    /**
+     * Values of non-zero elements
+     * @type {Array<number>}
+     * @memberof Vectors
+     */
+    'values': Array<number>;
+}
+//# sourceMappingURL=vectors.d.ts.map

package/dist/models/vectors.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"vectors.d.ts","sourceRoot":"","sources":["../../models/vectors.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAKH,OAAO,KAAK,EAAE,0BAA0B,EAAE,MAAM,iCAAiC,CAAC;AAKlF;;;;GAIG;AACH,MAAM,WAAW,OAAO;IACpB;;;;OAIG;IACH,SAAS,EAAE,KAAK,CAAC,0BAA0B,CAAC,CAAC;IAC7C;;;;OAIG;IACH,QAAQ,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;CAC3B"}

package/dist/models/verify-password-request.d.ts

@@ -0,0 +1,25 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+/**
+ * Request to verify password for a password-protected retriever.
+ * @export
+ * @interface VerifyPasswordRequest
+ */
+export interface VerifyPasswordRequest {
+    /**
+     * The password to verify against the retriever\'s password
+     * @type {string}
+     * @memberof VerifyPasswordRequest
+     */
+    'password': string;
+}
+//# sourceMappingURL=verify-password-request.d.ts.map

package/dist/models/verify-password-request.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"verify-password-request.d.ts","sourceRoot":"","sources":["../../models/verify-password-request.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAIH;;;;GAIG;AACH,MAAM,WAAW,qBAAqB;IAClC;;;;OAIG;IACH,UAAU,EAAE,MAAM,CAAC;CACtB"}

package/dist/models/verify-password-response.d.ts

@@ -0,0 +1,31 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+/**
+ * Response from password verification.
+ * @export
+ * @interface VerifyPasswordResponse
+ */
+export interface VerifyPasswordResponse {
+    /**
+     * Whether the provided password is valid
+     * @type {boolean}
+     * @memberof VerifyPasswordResponse
+     */
+    'valid': boolean;
+    /**
+     * DEPRECATED: API keys are no longer required. After password verification, call the execute endpoint directly.
+     * @type {string}
+     * @memberof VerifyPasswordResponse
+     */
+    'public_api_key'?: string;
+}
+//# sourceMappingURL=verify-password-response.d.ts.map

package/dist/models/verify-password-response.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"verify-password-response.d.ts","sourceRoot":"","sources":["../../models/verify-password-response.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAIH;;;;GAIG;AACH,MAAM,WAAW,sBAAsB;IACnC;;;;OAIG;IACH,OAAO,EAAE,OAAO,CAAC;IACjB;;;;OAIG;IACH,gBAAgB,CAAC,EAAE,MAAM,CAAC;CAC7B"}

package/dist/models/version-list-response.d.ts

@@ -0,0 +1,31 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+/**
+ *
+ * @export
+ * @interface VersionListResponse
+ */
+export interface VersionListResponse {
+    /**
+     *
+     * @type {Array<any>}
+     * @memberof VersionListResponse
+     */
+    'versions': Array<any>;
+    /**
+     *
+     * @type {number}
+     * @memberof VersionListResponse
+     */
+    'total': number;
+}
+//# sourceMappingURL=version-list-response.d.ts.map

package/dist/models/version-list-response.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"version-list-response.d.ts","sourceRoot":"","sources":["../../models/version-list-response.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAIH;;;;GAIG;AACH,MAAM,WAAW,mBAAmB;IAChC;;;;OAIG;IACH,UAAU,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC;IACvB;;;;OAIG;IACH,OAAO,EAAE,MAAM,CAAC;CACnB"}

package/dist/models/web-scraper-extractor-params.d.ts

@@ -0,0 +1,234 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+import type { ChunkStrategy } from './chunk-strategy';
+import type { CrawlMode } from './crawl-mode';
+import type { DocumentIdStrategy } from './document-id-strategy';
+import type { RenderStrategy } from './render-strategy';
+import type { ResponseShape3 } from './response-shape3';
+/**
+ * Parameters for the web scraper extractor.  The web scraper extractor crawls websites and extracts content with three types of embeddings for comprehensive multimodal search:  **Embedding Types:** - Text (E5-Large): 1024D embeddings for page content - Code (Jina Code): 768D embeddings for code blocks - Images (SigLIP): 768D semantic embeddings for figures/screenshots - Images (DINOv2): 768D structure embeddings for visual layout comparison  **Crawl Modes:** - DETERMINISTIC: BFS following all links (default, predictable) - SEMANTIC: LLM-guided, prioritizes pages matching crawl_goal  **Rendering Strategies:** - STATIC: Fast HTTP fetch (default, works for most sites) - JAVASCRIPT: Playwright browser for SPAs (React/Vue/Angular) - AUTO: Tries static, falls back to JS if content too short  **Use Cases:** - Documentation freshness: Crawl docs, compare against course content - Job board ingestion: Extract job listings with structured data - Knowledge base building: Convert websites to searchable collections - Code example indexing: Find API usage patterns across docs
+ * @export
+ * @interface WebScraperExtractorParams
+ */
+export interface WebScraperExtractorParams {
+    /**
+     * Discriminator field for parameter type identification.
+     * @type {string}
+     * @memberof WebScraperExtractorParams
+     */
+    'extractor_type'?: WebScraperExtractorParamsExtractorTypeEnum;
+    /**
+     * Maximum link depth to crawl. 0=seed page only, 1=seed+direct links, etc. Default: 2. Max: 10.
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'max_depth'?: number;
+    /**
+     * Maximum pages to crawl. Default: 50. Max: 500.
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'max_pages'?: number;
+    /**
+     * Maximum total time for crawling in seconds. Default: 300 (5 minutes). Increase for large sites with many pages. Max: 3600 (1 hour).
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'crawl_timeout'?: number;
+    /**
+     * Crawl strategy. DETERMINISTIC: BFS all links (predictable). SEMANTIC: LLM-guided, prioritizes relevant pages (requires crawl_goal).
+     * @type {CrawlMode}
+     * @memberof WebScraperExtractorParams
+     */
+    'crawl_mode'?: CrawlMode;
+    /**
+     * Goal for semantic crawling. Only used when crawl_mode=SEMANTIC. Example: \'Find all S3 API documentation and examples\'
+     * @type {string}
+     * @memberof WebScraperExtractorParams
+     */
+    'crawl_goal'?: string;
+    /**
+     * How to render pages. AUTO (default): tries static, falls back to JS. STATIC: fast HTTP fetch. JAVASCRIPT: Playwright browser for SPAs.
+     * @type {RenderStrategy}
+     * @memberof WebScraperExtractorParams
+     */
+    'render_strategy'?: RenderStrategy;
+    /**
+     * Regex patterns for URLs to include. Example: [\'/docs/\', \'/api/\']
+     * @type {Array<string>}
+     * @memberof WebScraperExtractorParams
+     */
+    'include_patterns'?: Array<string>;
+    /**
+     * Regex patterns for URLs to exclude. Example: [\'/blog/\', \'\\.pdf$\']
+     * @type {Array<string>}
+     * @memberof WebScraperExtractorParams
+     */
+    'exclude_patterns'?: Array<string>;
+    /**
+     * How to split page content. NONE: one chunk per page. SENTENCES/PARAGRAPHS: semantic boundaries. WORDS/CHARACTERS: fixed size chunks.
+     * @type {ChunkStrategy}
+     * @memberof WebScraperExtractorParams
+     */
+    'chunk_strategy'?: ChunkStrategy;
+    /**
+     * Target size for each chunk (in units of chunk_strategy).
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'chunk_size'?: number;
+    /**
+     * Overlap between chunks to preserve context.
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'chunk_overlap'?: number;
+    /**
+     * How to generate document IDs. URL (default): stable across re-crawls. POSITION: order-based. CONTENT: deduplicates identical content.
+     * @type {DocumentIdStrategy}
+     * @memberof WebScraperExtractorParams
+     */
+    'document_id_strategy'?: DocumentIdStrategy;
+    /**
+     * Generate E5 embeddings for text content.
+     * @type {boolean}
+     * @memberof WebScraperExtractorParams
+     */
+    'generate_text_embeddings'?: boolean;
+    /**
+     * Generate Jina code embeddings for code blocks.
+     * @type {boolean}
+     * @memberof WebScraperExtractorParams
+     */
+    'generate_code_embeddings'?: boolean;
+    /**
+     * Generate SigLIP embeddings for images/figures.
+     * @type {boolean}
+     * @memberof WebScraperExtractorParams
+     */
+    'generate_image_embeddings'?: boolean;
+    /**
+     * Generate DINOv2 visual structure embeddings for layout comparison.
+     * @type {boolean}
+     * @memberof WebScraperExtractorParams
+     */
+    'generate_structure_embeddings'?: boolean;
+    /**
+     *
+     * @type {ResponseShape3}
+     * @memberof WebScraperExtractorParams
+     */
+    'response_shape'?: ResponseShape3;
+    /**
+     * LLM provider for structured extraction: openai, google, anthropic
+     * @type {string}
+     * @memberof WebScraperExtractorParams
+     */
+    'llm_provider'?: string;
+    /**
+     * LLM model for structured extraction.
+     * @type {string}
+     * @memberof WebScraperExtractorParams
+     */
+    'llm_model'?: string;
+    /**
+     * API key for LLM operations (BYOK - Bring Your Own Key). Supports: - Direct key: \'sk-proj-abc123...\' - Secret reference: \'{{SECRET.openai_api_key}}\'  When using secret reference, the key is loaded from your organization\'s secrets vault at runtime. Store secrets via POST /v1/organizations/secrets.  If not provided, uses Mixpeek\'s default API keys.
+     * @type {string}
+     * @memberof WebScraperExtractorParams
+     */
+    'llm_api_key'?: string;
+    /**
+     * Maximum retry attempts for failed HTTP requests. Uses exponential backoff with jitter. Default: 3.
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'max_retries'?: number;
+    /**
+     * Base delay in seconds for retry backoff. Actual delay = base * 2^attempt + jitter. Default: 1.0.
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'retry_base_delay'?: number;
+    /**
+     * Maximum delay in seconds between retries. Default: 30.
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'retry_max_delay'?: number;
+    /**
+     * Respect Retry-After header from 429/503 responses. If False, uses exponential backoff instead. Default: True.
+     * @type {boolean}
+     * @memberof WebScraperExtractorParams
+     */
+    'respect_retry_after'?: boolean;
+    /**
+     * List of proxy URLs for rotation. Supports formats: \'http://host:port\', \'http://user:pass@host:port\', \'socks5://host:port\'. Proxies rotate on errors or every N requests.
+     * @type {Array<string>}
+     * @memberof WebScraperExtractorParams
+     */
+    'proxies'?: Array<string>;
+    /**
+     * Rotate to next proxy when request fails. Default: True.
+     * @type {boolean}
+     * @memberof WebScraperExtractorParams
+     */
+    'rotate_proxy_on_error'?: boolean;
+    /**
+     * Rotate proxy every N requests (0 = disabled). Useful for avoiding IP-based rate limits. Default: 0 (disabled).
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'rotate_proxy_every_n_requests'?: number;
+    /**
+     * Captcha solving service provider: \'2captcha\', \'anti-captcha\', \'capsolver\'. If not set, captcha pages are skipped gracefully.
+     * @type {string}
+     * @memberof WebScraperExtractorParams
+     */
+    'captcha_service_provider'?: string;
+    /**
+     * API key for captcha solving service. Supports secret reference: \'{{SECRET.captcha_api_key}}\'. Required if captcha_service_provider is set.
+     * @type {string}
+     * @memberof WebScraperExtractorParams
+     */
+    'captcha_service_api_key'?: string;
+    /**
+     * Detect captcha challenges (Cloudflare, reCAPTCHA, hCaptcha). If detected and no solver configured, page is skipped. Default: True.
+     * @type {boolean}
+     * @memberof WebScraperExtractorParams
+     */
+    'detect_captcha'?: boolean;
+    /**
+     * Persist cookies across requests within a crawl session. Useful for sites requiring authentication. Default: True.
+     * @type {boolean}
+     * @memberof WebScraperExtractorParams
+     */
+    'persist_cookies'?: boolean;
+    /**
+     * Custom HTTP headers to include in all requests. Example: {\'Authorization\': \'Bearer token\', \'X-Custom\': \'value\'}
+     * @type {{ [key: string]: string; }}
+     * @memberof WebScraperExtractorParams
+     */
+    'custom_headers'?: {
+        [key: string]: string;
+    };
+    /**
+     * Delay in seconds between consecutive requests. Useful for polite crawling and avoiding rate limits. Default: 0 (no delay).
+     * @type {number}
+     * @memberof WebScraperExtractorParams
+     */
+    'delay_between_requests'?: number;
+}
+export declare const WebScraperExtractorParamsExtractorTypeEnum: {
+    readonly WebScraper: "web_scraper";
+};
+export type WebScraperExtractorParamsExtractorTypeEnum = typeof WebScraperExtractorParamsExtractorTypeEnum[keyof typeof WebScraperExtractorParamsExtractorTypeEnum];
+//# sourceMappingURL=web-scraper-extractor-params.d.ts.map

package/dist/models/web-scraper-extractor-params.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"web-scraper-extractor-params.d.ts","sourceRoot":"","sources":["../../models/web-scraper-extractor-params.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAKH,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,kBAAkB,CAAC;AAGtD,OAAO,KAAK,EAAE,SAAS,EAAE,MAAM,cAAc,CAAC;AAG9C,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,wBAAwB,CAAC;AAGjE,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AAGxD,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,mBAAmB,CAAC;AAExD;;;;GAIG;AACH,MAAM,WAAW,yBAAyB;IACtC;;;;OAIG;IACH,gBAAgB,CAAC,EAAE,0CAA0C,CAAC;IAC9D;;;;OAIG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB;;;;OAIG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB;;;;OAIG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;;;OAIG;IACH,YAAY,CAAC,EAAE,SAAS,CAAC;IACzB;;;;OAIG;IACH,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB;;;;OAIG;IACH,iBAAiB,CAAC,EAAE,cAAc,CAAC;IACnC;;;;OAIG;IACH,kBAAkB,CAAC,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;IACnC;;;;OAIG;IACH,kBAAkB,CAAC,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;IACnC;;;;OAIG;IACH,gBAAgB,CAAC,EAAE,aAAa,CAAC;IACjC;;;;OAIG;IACH,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB;;;;OAIG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB;;;;OAIG;IACH,sBAAsB,CAAC,EAAE,kBAAkB,CAAC;IAC5C;;;;OAIG;IACH,0BAA0B,CAAC,EAAE,OAAO,CAAC;IACrC;;;;OAIG;IACH,0BAA0B,CAAC,EAAE,OAAO,CAAC;IACrC;;;;OAIG;IACH,2BAA2B,CAAC,EAAE,OAAO,CAAC;IACtC;;;;OAIG;IACH,+BAA+B,CAAC,EAAE,OAAO,CAAC;IAC1C;;;;OAIG;IACH,gBAAgB,CAAC,EAAE,cAAc,CAAC;IAClC;;;;OAIG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;;OAIG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB;;;;OAIG;IACH,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB;;;;OAIG;IACH,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB;;;;OAIG;IACH,kBAAkB,CAAC,EAAE,MAAM,CAAC;IAC5B;;;;OAIG;IACH,iBAAiB,CAAC,EAAE,MAAM,CAAC;IAC3B;;;;OAIG;IACH,qBAAqB,CAAC,EAAE,OAAO,CAAC;IAChC;;;;OAIG;IACH,SAAS,CAAC,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC;IAC1B;;;;OAIG;IACH,uBAAuB,CAAC,EAAE,OAAO,CAAC;IAClC;;;;OAIG;IACH,+BAA+B,CAAC,EAAE,MAAM,CAAC;IACzC;;;;OAIG;IACH,0BAA0B,CAAC,EAAE,MAAM,CAAC;IACpC;;;;OAIG;IACH,yBAAyB,CAAC,EAAE,MAAM,CAAC;IACnC;;;;OAIG;IACH,gBAAgB,CAAC,EAAE,OAAO,CAAC;IAC3B;;;;OAIG;IACH,iBAAiB,CAAC,EAAE,OAAO,CAAC;IAC5B;;;;OAIG;IACH,gBAAgB,CAAC,EAAE;QAAE,CAAC,GAAG,EAAE,MAAM,GAAG,MAAM,CAAC;KAAE,CAAC;IAC9C;;;;OAIG;IACH,wBAAwB,CAAC,EAAE,MAAM,CAAC;CACrC;AAED,eAAO,MAAM,0CAA0C;;CAE7C,CAAC;AAEX,MAAM,MAAM,0CAA0C,GAAG,OAAO,0CAA0C,CAAC,MAAM,OAAO,0CAA0C,CAAC,CAAC"}

package/dist/models/webhook-channel-input.d.ts

@@ -0,0 +1,33 @@
+/**
+ * Mixpeek API
+ * This is the Mixpeek API, providing access to various endpoints for data processing and retrieval.
+ *
+ * The version of the OpenAPI document: 0.81.1
+ * Contact: info@mixpeek.com
+ *
+ * NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
+ * https://openapi-generator.tech
+ * Do not edit the class manually.
+ */
+import type { Configs } from './configs';
+import type { NotificationChannel } from './notification-channel';
+/**
+ * Notification channel configuration for webhook delivery.  Defines how and where webhook event notifications should be delivered. Each webhook can have multiple channels configured for redundancy or different notification audiences.  Supported Channels:     - EMAIL: Send notifications via email to specified recipients     - SLACK: Post messages to Slack channels or direct messages     - WEBHOOK: HTTP POST to external endpoints (standard webhooks)  Use Cases:     - Route critical alerts to Slack and email simultaneously     - Send audit trail events to external webhook endpoints     - Notify team members via email for object lifecycle events     - Post cluster completion status to Slack channels  Requirements:     - Channel type must match the config type (discriminated union)     - Each config must have valid credentials/endpoints configured     - Channel configs are validated at webhook creation time
+ * @export
+ * @interface WebhookChannelInput
+ */
+export interface WebhookChannelInput {
+    /**
+     * REQUIRED. The notification channel type for delivery. Determines which delivery mechanism is used (email, Slack, webhook). Must match the type of the configs field.
+     * @type {NotificationChannel}
+     * @memberof WebhookChannelInput
+     */
+    'channel': NotificationChannel;
+    /**
+     *
+     * @type {Configs}
+     * @memberof WebhookChannelInput
+     */
+    'configs': Configs;
+}
+//# sourceMappingURL=webhook-channel-input.d.ts.map

package/dist/models/webhook-channel-input.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"webhook-channel-input.d.ts","sourceRoot":"","sources":["../../models/webhook-channel-input.ts"],"names":[],"mappings":"AAEA;;;;;;;;;;GAUG;AAKH,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AAGzC,OAAO,KAAK,EAAE,mBAAmB,EAAE,MAAM,wBAAwB,CAAC;AAElE;;;;GAIG;AACH,MAAM,WAAW,mBAAmB;IAChC;;;;OAIG;IACH,SAAS,EAAE,mBAAmB,CAAC;IAC/B;;;;OAIG;IACH,SAAS,EAAE,OAAO,CAAC;CACtB"}