openapi: 3.0.3 info: title: Llama Platform Agent Data Pipelines API version: 0.1.0 tags: - name: Pipelines paths: /api/v1/pipelines: get: tags: - Pipelines summary: Search Pipelines description: Search for pipelines by name, type, or project. operationId: search_pipelines_api_v1_pipelines_get security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: project_name in: query required: false schema: anyOf: - type: string - type: 'null' title: Project Name - name: pipeline_name in: query required: false schema: anyOf: - type: string - type: 'null' title: Pipeline Name - name: pipeline_type in: query required: false schema: anyOf: - $ref: '#/components/schemas/PipelineType' - type: 'null' title: Pipeline Type - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/Pipeline' title: Response Search Pipelines Api V1 Pipelines Get '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' post: tags: - Pipelines summary: Create Pipeline description: 'Create a new managed ingestion pipeline. A pipeline connects data sources to a vector store for RAG. After creation, call `POST /pipelines/{id}/sync` to start ingesting documents.' operationId: create_pipeline_api_v1_pipelines_post security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/PipelineCreate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/Pipeline' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' put: tags: - Pipelines summary: Upsert Pipeline description: 'Upsert a pipeline. Updates the pipeline if one with the same name and project already exists, otherwise creates a new one.' operationId: upsert_pipeline_api_v1_pipelines_put security: - HTTPBearer: [] parameters: - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/PipelineCreate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/Pipeline' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}: get: tags: - Pipelines summary: Get Pipeline description: Get a pipeline by ID. operationId: get_pipeline_api_v1_pipelines__pipeline_id__get security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/Pipeline' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' put: tags: - Pipelines summary: Update Existing Pipeline description: Update an existing pipeline's configuration. operationId: update_existing_pipeline_api_v1_pipelines__pipeline_id__put security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/PipelineUpdate' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/Pipeline' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - Pipelines summary: Delete Pipeline description: 'Delete a pipeline and all associated resources. Removes pipeline files, data sources, and vector store data. This operation is irreversible.' operationId: delete_pipeline_api_v1_pipelines__pipeline_id__delete security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '204': description: Successful Response '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/status: get: tags: - Pipelines summary: Get Pipeline Status description: 'Get the ingestion status of a managed pipeline. Returns document counts, sync progress, and the last effective timestamp. Only available for managed pipelines.' operationId: get_pipeline_status_api_v1_pipelines__pipeline_id__status_get security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: full_details in: query required: false schema: anyOf: - type: boolean - type: 'null' title: Full Details - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ManagedIngestionStatusResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/sync: post: tags: - Pipelines summary: Sync Pipeline description: 'Trigger an incremental sync for a managed pipeline. Processes new and updated documents from data sources and files, then updates the index for retrieval.' operationId: sync_pipeline_api_v1_pipelines__pipeline_id__sync_post security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/Pipeline' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/sync/cancel: post: tags: - Pipelines summary: Cancel Pipeline Sync description: Cancel all running sync jobs for a pipeline. operationId: cancel_pipeline_sync_api_v1_pipelines__pipeline_id__sync_cancel_post security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/Pipeline' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/force-delete: post: tags: - Pipelines summary: Force Delete Pipeline operationId: force_delete_pipeline_api_v1_pipelines__pipeline_id__force_delete_post security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '204': description: Successful Response '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/copy: post: tags: - Pipelines summary: Copy Pipeline description: 'Copy a pipeline including its files and documents. Creates a new pipeline with the same configuration and triggers a sync to populate the new vector store.' operationId: copy_pipeline_api_v1_pipelines__pipeline_id__copy_post security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/Pipeline' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/retrieve: post: tags: - Pipelines summary: Run Search description: 'Run a retrieval query against a managed pipeline. Searches the pipeline''s vector store using the provided query and retrieval parameters. Supports dense, sparse, and hybrid search modes with configurable top-k and reranking.' operationId: run_search_api_v1_pipelines__pipeline_id__retrieve_post security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: project_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Project Id - name: organization_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: Organization Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/RetrievalParams' responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/RetrieveResults' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/playground-session: get: tags: - Pipelines summary: Get Playground Session description: Get a playground session for a user and pipeline. operationId: get_playground_session_api_v1_pipelines__pipeline_id__playground_session_get security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PlaygroundSession' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/chat: post: tags: - Pipelines summary: Chat description: 'Chat with a managed pipeline using RAG. Combines retrieval from the pipeline''s vector store with an LLM chat completion. Returns a streaming response.' operationId: chat_api_v1_pipelines__pipeline_id__chat_post security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatInputParams' responses: '200': description: Successful Response content: application/json: schema: {} '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/documents: post: tags: - Pipelines summary: Create Batch Pipeline Documents description: Batch create documents for a pipeline. operationId: create_batch_pipeline_documents_api_v1_pipelines__pipeline_id__documents_post security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: type: array items: $ref: '#/components/schemas/CloudDocumentCreate' title: Documents responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/CloudDocument' title: Response Create Batch Pipeline Documents Api V1 Pipelines Pipeline Id Documents Post '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' get: tags: - Pipelines summary: List Pipeline Documents description: Return a list of documents for a pipeline. operationId: list_pipeline_documents_api_v1_pipelines__pipeline_id__documents_get security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: skip in: query required: false schema: type: integer minimum: 0 default: 0 title: Skip - name: limit in: query required: false schema: type: integer minimum: 0 default: 10 title: Limit - name: file_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: File Id - name: only_direct_upload in: query required: false schema: anyOf: - type: boolean - type: 'null' default: false title: Only Direct Upload - name: only_api_data_source_documents in: query required: false schema: anyOf: - type: boolean - type: 'null' default: false title: Only Api Data Source Documents - name: status_refresh_policy in: query required: false schema: enum: - cached - ttl type: string default: cached title: Status Refresh Policy - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/CloudDocument' title: Response List Pipeline Documents Api V1 Pipelines Pipeline Id Documents Get '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' put: tags: - Pipelines summary: Upsert Batch Pipeline Documents description: Batch create or update a document for a pipeline. operationId: upsert_batch_pipeline_documents_api_v1_pipelines__pipeline_id__documents_put security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session requestBody: required: true content: application/json: schema: type: array items: $ref: '#/components/schemas/CloudDocumentCreate' title: Documents responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/CloudDocument' title: Response Upsert Batch Pipeline Documents Api V1 Pipelines Pipeline Id Documents Put '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/documents/paginated: get: tags: - Pipelines summary: Paginated List Pipeline Documents description: Return a list of documents for a pipeline. operationId: paginated_list_pipeline_documents_api_v1_pipelines__pipeline_id__documents_paginated_get security: - HTTPBearer: [] parameters: - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: skip in: query required: false schema: type: integer minimum: 0 default: 0 title: Skip - name: limit in: query required: false schema: type: integer minimum: 0 default: 10 title: Limit - name: file_id in: query required: false schema: anyOf: - type: string format: uuid - type: 'null' title: File Id - name: only_direct_upload in: query required: false schema: anyOf: - type: boolean - type: 'null' default: false title: Only Direct Upload - name: only_api_data_source_documents in: query required: false schema: anyOf: - type: boolean - type: 'null' default: false title: Only Api Data Source Documents - name: status_refresh_policy in: query required: false schema: enum: - cached - ttl type: string default: cached title: Status Refresh Policy - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/PaginatedListCloudDocumentsResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/documents/{document_id}: get: tags: - Pipelines summary: Get Pipeline Document description: Return a single document for a pipeline. operationId: get_pipeline_document_api_v1_pipelines__pipeline_id__documents__document_id__get security: - HTTPBearer: [] parameters: - name: document_id in: path required: true schema: type: string title: Document Id - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/CloudDocument' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' delete: tags: - Pipelines summary: Delete Pipeline Document description: Delete a document from a pipeline; runs async (vectors first, then MongoDB record). operationId: delete_pipeline_document_api_v1_pipelines__pipeline_id__documents__document_id__delete security: - HTTPBearer: [] parameters: - name: document_id in: path required: true schema: type: string title: Document Id - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '204': description: Successful Response '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/documents/{document_id}/status: get: tags: - Pipelines summary: Get Pipeline Document Status description: Return a single document for a pipeline. operationId: get_pipeline_document_status_api_v1_pipelines__pipeline_id__documents__document_id__status_get security: - HTTPBearer: [] parameters: - name: document_id in: path required: true schema: type: string title: Document Id - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ManagedIngestionStatusResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/documents/{document_id}/sync: post: tags: - Pipelines summary: Sync Pipeline Document description: Sync a specific document for a pipeline. operationId: sync_pipeline_document_api_v1_pipelines__pipeline_id__documents__document_id__sync_post security: - HTTPBearer: [] parameters: - name: document_id in: path required: true schema: type: string title: Document Id - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: {} '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' /api/v1/pipelines/{pipeline_id}/documents/{document_id}/chunks: get: tags: - Pipelines summary: List Pipeline Document Chunks description: Return a list of chunks for a pipeline document. operationId: list_pipeline_document_chunks_api_v1_pipelines__pipeline_id__documents__document_id__chunks_get security: - HTTPBearer: [] parameters: - name: document_id in: path required: true schema: type: string title: Document Id - name: pipeline_id in: path required: true schema: type: string format: uuid title: Pipeline Id - name: session in: cookie required: false schema: anyOf: - type: string - type: 'null' title: Session responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/TextNode' title: Response List Pipeline Document Chunks Api V1 Pipelines Pipeline Id Documents Document Id Chunks Get '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: ChatMessage: properties: id: type: string format: uuid title: Id index: type: integer title: Index description: The index of the message in the chat. annotations: items: $ref: '#/components/schemas/MessageAnnotation' type: array title: Annotations description: Retrieval annotations for the message. role: $ref: '#/components/schemas/MessageRole' description: The role of the message. content: anyOf: - type: string - type: 'null' title: Content description: Text content of the generation additional_kwargs: additionalProperties: type: string type: object title: Additional Kwargs description: Additional arguments passed to the model class_name: type: string title: Class Name default: base_component type: object required: - id - index - role title: ChatMessage CloudMilvusVectorStore: properties: supports_nested_metadata_filters: type: boolean title: Supports Nested Metadata Filters default: false uri: type: string title: Uri collection_name: anyOf: - type: string - type: 'null' title: Collection Name token: anyOf: - type: string format: password writeOnly: true - type: 'null' title: Token embedding_dimension: anyOf: - type: integer - type: 'null' title: Embedding Dimension class_name: type: string title: Class Name default: CloudMilvusVectorStore type: object required: - uri title: CloudMilvusVectorStore description: Cloud Milvus Vector Store. CloudPineconeVectorStore: properties: supports_nested_metadata_filters: type: boolean const: true title: Supports Nested Metadata Filters default: true api_key: type: string format: password title: Api Key description: The API key for authenticating with Pinecone writeOnly: true index_name: type: string title: Index Name namespace: anyOf: - type: string - type: 'null' title: Namespace insert_kwargs: anyOf: - additionalProperties: true type: object - type: 'null' title: Insert Kwargs class_name: type: string title: Class Name default: CloudPineconeVectorStore type: object required: - api_key - index_name title: CloudPineconeVectorStore description: "Cloud Pinecone Vector Store.\n\nThis class is used to store the configuration for a Pinecone vector store, so that it can be\ncreated and used in LlamaCloud.\n\nArgs:\n api_key (str): API key for authenticating with Pinecone\n index_name (str): name of the Pinecone index\n namespace (optional[str]): namespace to use in the Pinecone index\n insert_kwargs (optional[dict]): additional kwargs to pass during insertion" VertexAIEmbeddingConfig: properties: type: type: string const: VERTEXAI_EMBEDDING title: Type description: Type of the embedding model. default: VERTEXAI_EMBEDDING component: $ref: '#/components/schemas/VertexTextEmbedding' description: Configuration for the VertexAI embedding model. type: object title: VertexAIEmbeddingConfig TokenChunkingConfig: properties: chunk_size: type: integer exclusiveMinimum: 0.0 title: Chunk Size default: 1024 chunk_overlap: type: integer title: Chunk Overlap default: 200 gte: 0 mode: type: string const: token title: Mode default: token separator: type: string title: Separator default: ' ' type: object title: TokenChunkingConfig HuggingFaceInferenceAPIEmbeddingConfig: properties: type: type: string const: HUGGINGFACE_API_EMBEDDING title: Type description: Type of the embedding model. default: HUGGINGFACE_API_EMBEDDING component: $ref: '#/components/schemas/HuggingFaceInferenceAPIEmbedding' description: Configuration for the HuggingFace Inference API embedding model. type: object title: HuggingFaceInferenceAPIEmbeddingConfig DataSinkCreate: properties: name: type: string title: Name description: The name of the data sink. sink_type: $ref: '#/components/schemas/ConfigurableDataSinkNames' component: anyOf: - additionalProperties: true type: object - $ref: '#/components/schemas/CloudPineconeVectorStore' - $ref: '#/components/schemas/CloudPostgresVectorStore' - $ref: '#/components/schemas/CloudQdrantVectorStore' - $ref: '#/components/schemas/CloudAzureAISearchVectorStore' - $ref: '#/components/schemas/CloudMongoDBAtlasVectorSearch' - $ref: '#/components/schemas/CloudMilvusVectorStore' - $ref: '#/components/schemas/CloudAstraDBVectorStore' title: DataSinkCreateComponent description: Component that implements the data sink type: object required: - name - sink_type - component title: DataSinkCreate description: Schema for creating a data sink. RetrievalParams: properties: dense_similarity_top_k: anyOf: - type: integer maximum: 100.0 minimum: 1.0 - type: 'null' title: Dense Similarity Top K description: Number of nodes for dense retrieval. default: 30 dense_similarity_cutoff: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Dense Similarity Cutoff description: Minimum similarity score wrt query for retrieval default: 0.0 sparse_similarity_top_k: anyOf: - type: integer maximum: 100.0 minimum: 1.0 - type: 'null' title: Sparse Similarity Top K description: Number of nodes for sparse retrieval. default: 30 enable_reranking: anyOf: - type: boolean - type: 'null' title: Enable Reranking description: Enable reranking for retrieval rerank_top_n: anyOf: - type: integer maximum: 100.0 minimum: 1.0 - type: 'null' title: Rerank Top N description: Number of reranked nodes for returning. default: 6 alpha: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Alpha description: Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. search_filters: anyOf: - $ref: '#/components/schemas/MetadataFilters' - type: 'null' description: Search filters for retrieval. search_filters_inference_schema: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Search Filters Inference Schema description: JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. files_top_k: anyOf: - type: integer maximum: 5.0 minimum: 1.0 - type: 'null' title: Files Top K description: Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). default: 1 retrieval_mode: $ref: '#/components/schemas/RetrievalMode' description: The retrieval mode for the query. default: chunks retrieve_image_nodes: type: boolean title: Retrieve Image Nodes description: Whether to retrieve image nodes. default: false deprecated: true retrieve_page_screenshot_nodes: type: boolean title: Retrieve Page Screenshot Nodes description: Whether to retrieve page screenshot nodes. default: false retrieve_page_figure_nodes: type: boolean title: Retrieve Page Figure Nodes description: Whether to retrieve page figure nodes. default: false query: type: string minLength: 1 title: Query description: The query to retrieve against. class_name: type: string title: Class Name default: base_component type: object required: - query title: RetrievalParams description: Schema for the search params for an retrieval execution. MessageAnnotation: properties: type: type: string title: Type data: type: string contentMediaType: application/json contentSchema: {} title: Data class_name: type: string title: Class Name default: base_component type: object required: - type - data title: MessageAnnotation CohereEmbedding: properties: model_name: type: string title: Model Name description: The modelId of the Cohere model to use. default: embed-english-v3.0 embed_batch_size: type: integer maximum: 2048.0 exclusiveMinimum: 0.0 title: Embed Batch Size description: The batch size for embedding calls. default: 10 num_workers: anyOf: - type: integer - type: 'null' title: Num Workers description: The number of workers to use for async embedding calls. api_key: anyOf: - type: string - type: 'null' title: Api Key description: The Cohere API key. truncate: type: string title: Truncate description: Truncation type - START/ END/ NONE default: END input_type: anyOf: - type: string - type: 'null' title: Input Type description: Model Input type. If not provided, search_document and search_query are used when needed. embedding_type: type: string title: Embedding Type description: Embedding type. If not provided float embedding_type is used when needed. default: float class_name: type: string title: Class Name default: CohereEmbedding type: object required: - api_key title: CohereEmbedding CloudDocumentCreate: properties: text: type: string title: Text metadata: additionalProperties: true type: object title: Metadata excluded_embed_metadata_keys: items: type: string type: array title: Excluded Embed Metadata Keys default: [] excluded_llm_metadata_keys: items: type: string type: array title: Excluded Llm Metadata Keys default: [] page_positions: anyOf: - items: type: integer type: array - type: 'null' title: Page Positions description: indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]. id: anyOf: - type: string - type: 'null' title: Id type: object required: - text - metadata title: CloudDocumentCreate description: Create a new cloud document. PageSegmentationConfig: properties: mode: type: string const: page title: Mode default: page page_separator: type: string title: Page Separator default: ' --- ' type: object title: PageSegmentationConfig ElementSegmentationConfig: properties: mode: type: string const: element title: Mode default: element type: object title: ElementSegmentationConfig SupportedLLMModelNames: type: string enum: - GPT_4O - GPT_4O_MINI - GPT_4_1 - GPT_4_1_NANO - GPT_4_1_MINI - AZURE_OPENAI_GPT_4O - AZURE_OPENAI_GPT_4O_MINI - AZURE_OPENAI_GPT_4_1 - AZURE_OPENAI_GPT_4_1_MINI - AZURE_OPENAI_GPT_4_1_NANO - CLAUDE_4_5_SONNET - BEDROCK_CLAUDE_3_5_SONNET_V1 - BEDROCK_CLAUDE_3_5_SONNET_V2 title: SupportedLLMModelNames PageFigureMetadata: properties: figure_name: type: string title: Figure Name description: The name of the figure file_id: type: string format: uuid title: File Id description: The ID of the file that the figure was taken from page_index: type: integer minimum: 0.0 title: Page Index description: The index of the page for which the figure is taken (0-indexed) figure_size: type: integer minimum: 0.0 title: Figure Size description: The size of the figure in bytes is_likely_noise: type: boolean title: Is Likely Noise description: Whether the figure is likely to be noise default: false confidence: type: number maximum: 1.0 minimum: 0.0 title: Confidence description: The confidence of the figure metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata description: Metadata for the figure type: object required: - figure_name - file_id - page_index - figure_size - confidence title: PageFigureMetadata SparseModelConfig: properties: model_type: $ref: '#/components/schemas/SparseModelType' description: The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). default: bm25 class_name: type: string title: Class Name default: SparseModelConfig type: object title: SparseModelConfig description: 'Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks.' ManagedOpenAIEmbedding: properties: model_name: type: string const: openai-text-embedding-3-small title: Model Name description: The name of the OpenAI embedding model. default: openai-text-embedding-3-small embed_batch_size: type: integer maximum: 2048.0 exclusiveMinimum: 0.0 title: Embed Batch Size description: The batch size for embedding calls. default: 10 num_workers: anyOf: - type: integer - type: 'null' title: Num Workers description: The number of workers to use for async embedding calls. class_name: type: string title: Class Name default: ManagedOpenAIEmbedding type: object title: ManagedOpenAIEmbedding ManagedIngestionStatusResponse: properties: job_id: anyOf: - type: string format: uuid - type: 'null' title: Job Id description: ID of the latest job. deployment_date: anyOf: - type: string format: date-time - type: 'null' title: Deployment Date description: Date of the deployment. status: $ref: '#/components/schemas/ManagedIngestionStatus' description: Status of the ingestion. error: anyOf: - items: $ref: '#/components/schemas/IngestionErrorResponse' type: array - type: 'null' title: Error description: List of errors that occurred during ingestion. effective_at: anyOf: - type: string format: date-time - type: 'null' title: Effective At description: When the status is effective type: object required: - status title: ManagedIngestionStatusResponse GeminiEmbedding: properties: model_name: type: string title: Model Name description: The modelId of the Gemini model to use. default: models/embedding-001 embed_batch_size: type: integer maximum: 2048.0 exclusiveMinimum: 0.0 title: Embed Batch Size description: The batch size for embedding calls. default: 10 num_workers: anyOf: - type: integer - type: 'null' title: Num Workers description: The number of workers to use for async embedding calls. title: anyOf: - type: string - type: 'null' title: Title description: Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. default: '' task_type: anyOf: - type: string - type: 'null' title: Task Type description: The task for embedding model. default: retrieval_document api_key: anyOf: - type: string - type: 'null' title: Api Key description: API key to access the model. Defaults to None. api_base: anyOf: - type: string - type: 'null' title: Api Base description: API base to access the model. Defaults to None. transport: anyOf: - type: string - type: 'null' title: Transport description: Transport to access the model. Defaults to None. output_dimensionality: anyOf: - type: integer - type: 'null' title: Output Dimensionality description: Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. class_name: type: string title: Class Name default: GeminiEmbedding type: object title: GeminiEmbedding CloudAstraDBVectorStore: properties: supports_nested_metadata_filters: type: boolean const: true title: Supports Nested Metadata Filters default: true token: type: string format: password title: Token description: The Astra DB Application Token to use writeOnly: true api_endpoint: type: string title: Api Endpoint description: The Astra DB JSON API endpoint for your database collection_name: type: string title: Collection Name description: Collection name to use. If not existing, it will be created embedding_dimension: type: integer title: Embedding Dimension description: Length of the embedding vectors in use keyspace: anyOf: - type: string - type: 'null' title: Keyspace description: The keyspace to use. If not provided, 'default_keyspace' class_name: type: string title: Class Name default: CloudAstraDBVectorStore type: object required: - token - api_endpoint - collection_name - embedding_dimension title: CloudAstraDBVectorStore description: "Cloud AstraDB Vector Store.\n\nThis class is used to store the configuration for an AstraDB vector store, so that it can be\ncreated and used in LlamaCloud.\n\nArgs:\n token (str): The Astra DB Application Token to use.\n api_endpoint (str): The Astra DB JSON API endpoint for your database.\n collection_name (str): Collection name to use. If not existing, it will be created.\n embedding_dimension (int): Length of the embedding vectors in use.\n keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace'" HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError OpenAIEmbeddingConfig: properties: type: type: string const: OPENAI_EMBEDDING title: Type description: Type of the embedding model. default: OPENAI_EMBEDDING component: $ref: '#/components/schemas/OpenAIEmbedding' description: Configuration for the OpenAI embedding model. type: object title: OpenAIEmbeddingConfig AdvancedModeTransformConfig: properties: mode: type: string const: advanced title: Mode default: advanced segmentation_config: anyOf: - $ref: '#/components/schemas/NoneSegmentationConfig' - $ref: '#/components/schemas/PageSegmentationConfig' - $ref: '#/components/schemas/ElementSegmentationConfig' title: Segmentation Config description: Configuration for the segmentation. chunking_config: anyOf: - $ref: '#/components/schemas/NoneChunkingConfig' - $ref: '#/components/schemas/CharacterChunkingConfig' - $ref: '#/components/schemas/TokenChunkingConfig' - $ref: '#/components/schemas/SentenceChunkingConfig' - $ref: '#/components/schemas/SemanticChunkingConfig' title: Chunking Config description: Configuration for the chunking. type: object title: AdvancedModeTransformConfig NoneChunkingConfig: properties: mode: type: string const: none title: Mode default: none type: object title: NoneChunkingConfig FilterOperator: type: string enum: - == - '>' - < - '!=' - '>=' - <= - in - nin - any - all - text_match - text_match_insensitive - contains - is_empty title: FilterOperator description: Vector store filter operator. CohereEmbeddingConfig: properties: type: type: string const: COHERE_EMBEDDING title: Type description: Type of the embedding model. default: COHERE_EMBEDDING component: $ref: '#/components/schemas/CohereEmbedding' description: Configuration for the Cohere embedding model. type: object title: CohereEmbeddingConfig FilterCondition: type: string enum: - and - or - not title: FilterCondition description: Vector store filter conditions to combine different filters. TextNode: properties: id_: type: string title: Id description: Unique ID of the node. embedding: anyOf: - items: type: number type: array - type: 'null' title: Embedding description: Embedding of the node. extra_info: additionalProperties: true type: object title: Extra Info description: A flat dictionary of metadata fields excluded_embed_metadata_keys: items: type: string type: array title: Excluded Embed Metadata Keys description: Metadata keys that are excluded from text for the embed model. excluded_llm_metadata_keys: items: type: string type: array title: Excluded Llm Metadata Keys description: Metadata keys that are excluded from text for the LLM. relationships: additionalProperties: anyOf: - $ref: '#/components/schemas/RelatedNodeInfo' - items: $ref: '#/components/schemas/RelatedNodeInfo' type: array propertyNames: $ref: '#/components/schemas/NodeRelationship' type: object title: Relationships description: A mapping of relationships to other node information. metadata_template: type: string title: Metadata Template description: Template for how metadata is formatted, with {key} and {value} placeholders. default: '{key}: {value}' metadata_seperator: type: string title: Metadata Seperator description: Separator between metadata fields when converting to string. default: ' ' text: type: string title: Text description: Text content of the node. default: '' mimetype: type: string title: Mimetype description: MIME type of the node content. default: text/plain start_char_idx: anyOf: - type: integer - type: 'null' title: Start Char Idx description: Start char index of the node. end_char_idx: anyOf: - type: integer - type: 'null' title: End Char Idx description: End char index of the node. text_template: type: string title: Text Template description: Template for how text is formatted, with {content} and {metadata_str} placeholders. default: '{metadata_str} {content}' class_name: type: string title: Class Name default: TextNode type: object title: TextNode description: Provided for backward compatibility. PGVectorDistanceMethod: type: string enum: - l2 - ip - cosine - l1 - hamming - jaccard title: PGVectorDistanceMethod description: 'Distance methods for PGVector. Docs: https://github.com/pgvector/pgvector?tab=readme-ov-file#query-options' Pooling: type: string enum: - cls - mean - last title: Pooling description: Enum of possible pooling choices with pooling behaviors. ChatData: properties: retrieval_parameters: $ref: '#/components/schemas/PresetRetrievalParams' llm_parameters: anyOf: - $ref: '#/components/schemas/LLMParameters' - type: 'null' class_name: type: string title: Class Name default: base_component type: object title: ChatData CloudDocument: properties: text: type: string title: Text metadata: additionalProperties: true type: object title: Metadata excluded_embed_metadata_keys: items: type: string type: array title: Excluded Embed Metadata Keys default: [] excluded_llm_metadata_keys: items: type: string type: array title: Excluded Llm Metadata Keys default: [] page_positions: anyOf: - items: type: integer type: array - type: 'null' title: Page Positions description: indices in the CloudDocument.text where a new page begins. e.g. Second page starts at index specified by page_positions[1]. id: type: string title: Id status_metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Status Metadata type: object required: - text - metadata - id title: CloudDocument description: Cloud document stored in S3. MetadataFilter: properties: key: type: string title: Key value: anyOf: - type: integer - type: number - type: string - items: type: string type: array - items: type: number type: array - items: type: integer type: array - type: 'null' title: Value operator: $ref: '#/components/schemas/FilterOperator' default: == type: object required: - key - value title: MetadataFilter description: 'Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types' TextNodeWithScore: properties: node: $ref: '#/components/schemas/TextNode' score: anyOf: - type: number - type: 'null' title: Score class_name: type: string title: Class Name default: TextNodeWithScore type: object required: - node title: TextNodeWithScore description: 'Same as NodeWithScore but type for node is a TextNode instead of BaseNode. FastAPI doesn''t accept abstract classes like BaseNode.' PageScreenshotNodeWithScore: properties: node: $ref: '#/components/schemas/PageScreenshotMetadata' score: type: number title: Score description: The score of the screenshot node class_name: type: string title: Class Name default: NodeWithScore type: object required: - node - score title: PageScreenshotNodeWithScore description: Page screenshot metadata with score SparseModelType: type: string enum: - splade - bm25 - auto title: SparseModelType description: 'Enum for sparse model types supported in LlamaCloud. SPLADE: Uses HuggingFace Splade model for sparse embeddings BM25: Uses Qdrant''s FastEmbed BM25 model for sparse embeddings AUTO: Automatically selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade)' Pipeline: properties: id: type: string format: uuid title: Id description: Unique identifier created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime name: type: string title: Name project_id: type: string format: uuid title: Project Id embedding_model_config_id: anyOf: - type: string format: uuid - type: 'null' title: Embedding Model Config Id description: The ID of the EmbeddingModelConfig this pipeline is using. embedding_model_config: anyOf: - $ref: '#/components/schemas/EmbeddingModelConfig' - type: 'null' description: The embedding model configuration for this pipeline. pipeline_type: $ref: '#/components/schemas/PipelineType' description: Type of pipeline. Either PLAYGROUND or MANAGED. default: MANAGED managed_pipeline_id: anyOf: - type: string format: uuid - type: 'null' title: Managed Pipeline Id description: The ID of the ManagedPipeline this playground pipeline is linked to. embedding_config: oneOf: - $ref: '#/components/schemas/ManagedOpenAIEmbeddingConfig' - $ref: '#/components/schemas/AzureOpenAIEmbeddingConfig' - $ref: '#/components/schemas/CohereEmbeddingConfig' - $ref: '#/components/schemas/GeminiEmbeddingConfig' - $ref: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig' - $ref: '#/components/schemas/OpenAIEmbeddingConfig' - $ref: '#/components/schemas/VertexAIEmbeddingConfig' - $ref: '#/components/schemas/BedrockEmbeddingConfig' title: Embedding Config discriminator: propertyName: type mapping: AZURE_EMBEDDING: '#/components/schemas/AzureOpenAIEmbeddingConfig' BEDROCK_EMBEDDING: '#/components/schemas/BedrockEmbeddingConfig' COHERE_EMBEDDING: '#/components/schemas/CohereEmbeddingConfig' GEMINI_EMBEDDING: '#/components/schemas/GeminiEmbeddingConfig' HUGGINGFACE_API_EMBEDDING: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig' MANAGED_OPENAI_EMBEDDING: '#/components/schemas/ManagedOpenAIEmbeddingConfig' OPENAI_EMBEDDING: '#/components/schemas/OpenAIEmbeddingConfig' VERTEXAI_EMBEDDING: '#/components/schemas/VertexAIEmbeddingConfig' sparse_model_config: anyOf: - $ref: '#/components/schemas/SparseModelConfig' - type: 'null' description: Configuration for the sparse model used in hybrid search. config_hash: anyOf: - $ref: '#/components/schemas/PipelineConfigurationHashes' - type: 'null' description: Hashes for the configuration of the pipeline. transform_config: anyOf: - $ref: '#/components/schemas/AutoTransformConfig' - $ref: '#/components/schemas/AdvancedModeTransformConfig' title: Transform Config description: Configuration for the transformation. preset_retrieval_parameters: $ref: '#/components/schemas/PresetRetrievalParams' description: Preset retrieval parameters for the pipeline. llama_parse_parameters: anyOf: - $ref: '#/components/schemas/LlamaParseParameters' - type: 'null' description: Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. data_sink: anyOf: - $ref: '#/components/schemas/DataSink' - type: 'null' description: The data sink for the pipeline. If None, the pipeline will use the fully managed data sink. status: anyOf: - type: string enum: - CREATED - DELETING - type: 'null' title: Status description: Status of the pipeline. metadata_config: anyOf: - $ref: '#/components/schemas/PipelineMetadataConfig' - type: 'null' description: Metadata configuration for the pipeline. type: object required: - id - name - project_id - embedding_config title: Pipeline description: Schema for a pipeline. AzureOpenAIEmbeddingConfig: properties: type: type: string const: AZURE_EMBEDDING title: Type description: Type of the embedding model. default: AZURE_EMBEDDING component: $ref: '#/components/schemas/AzureOpenAIEmbedding' description: Configuration for the Azure OpenAI embedding model. type: object title: AzureOpenAIEmbeddingConfig PageFigureNodeWithScore: properties: node: $ref: '#/components/schemas/PageFigureMetadata' score: type: number title: Score description: The score of the figure node class_name: type: string title: Class Name default: PageFigureNodeWithScore type: object required: - node - score title: PageFigureNodeWithScore description: Page figure metadata with score SemanticChunkingConfig: properties: mode: type: string const: semantic title: Mode default: semantic buffer_size: type: integer title: Buffer Size default: 1 breakpoint_percentile_threshold: type: integer title: Breakpoint Percentile Threshold default: 95 type: object title: SemanticChunkingConfig AutoTransformConfig: properties: mode: type: string const: auto title: Mode default: auto chunk_size: type: integer exclusiveMinimum: 0.0 title: Chunk Size description: Chunk size for the transformation. default: 1024 chunk_overlap: type: integer title: Chunk Overlap description: Chunk overlap for the transformation. default: 200 gte: 0 type: object title: AutoTransformConfig FailPageMode: type: string enum: - raw_text - blank_page - error_message title: FailPageMode description: Enum for representing the different available page error handling modes. PipelineMetadataConfig: properties: excluded_embed_metadata_keys: items: type: string type: array title: Excluded Embed Metadata Keys description: List of metadata keys to exclude from embeddings excluded_llm_metadata_keys: items: type: string type: array title: Excluded Llm Metadata Keys description: List of metadata keys to exclude from LLM during retrieval type: object title: PipelineMetadataConfig IngestionErrorResponse: properties: job_id: type: string format: uuid title: Job Id description: ID of the job that failed. message: type: string title: Message description: List of errors that occurred during ingestion. step: $ref: '#/components/schemas/JobNameMapping' description: Name of the job that failed. type: object required: - job_id - message - step title: IngestionErrorResponse CloudPostgresVectorStore: properties: supports_nested_metadata_filters: type: boolean title: Supports Nested Metadata Filters default: true database: type: string title: Database host: type: string title: Host password: type: string format: password title: Password writeOnly: true port: type: integer title: Port user: type: string title: User table_name: type: string title: Table Name schema_name: type: string title: Schema Name embed_dim: type: integer title: Embed Dim hybrid_search: anyOf: - type: boolean - type: 'null' title: Hybrid Search default: true perform_setup: type: boolean title: Perform Setup default: true hnsw_settings: anyOf: - $ref: '#/components/schemas/PGVectorHNSWSettings' - type: 'null' description: HNSW settings for PGVector index. Set to null to disable HNSW indexing in favor of a brute force indexing/exact search strategy instead. class_name: type: string title: Class Name default: CloudPostgresVectorStore type: object required: - database - host - password - port - user - table_name - schema_name - embed_dim title: CloudPostgresVectorStore PresetRetrievalParams: properties: dense_similarity_top_k: anyOf: - type: integer maximum: 100.0 minimum: 1.0 - type: 'null' title: Dense Similarity Top K description: Number of nodes for dense retrieval. default: 30 dense_similarity_cutoff: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Dense Similarity Cutoff description: Minimum similarity score wrt query for retrieval default: 0.0 sparse_similarity_top_k: anyOf: - type: integer maximum: 100.0 minimum: 1.0 - type: 'null' title: Sparse Similarity Top K description: Number of nodes for sparse retrieval. default: 30 enable_reranking: anyOf: - type: boolean - type: 'null' title: Enable Reranking description: Enable reranking for retrieval rerank_top_n: anyOf: - type: integer maximum: 100.0 minimum: 1.0 - type: 'null' title: Rerank Top N description: Number of reranked nodes for returning. default: 6 alpha: anyOf: - type: number maximum: 1.0 minimum: 0.0 - type: 'null' title: Alpha description: Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. search_filters: anyOf: - $ref: '#/components/schemas/MetadataFilters' - type: 'null' description: Search filters for retrieval. search_filters_inference_schema: anyOf: - additionalProperties: anyOf: - additionalProperties: true type: object - items: {} type: array - type: string - type: integer - type: number - type: boolean - type: 'null' type: object - type: 'null' title: Search Filters Inference Schema description: JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. files_top_k: anyOf: - type: integer maximum: 5.0 minimum: 1.0 - type: 'null' title: Files Top K description: Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). default: 1 retrieval_mode: $ref: '#/components/schemas/RetrievalMode' description: The retrieval mode for the query. default: chunks retrieve_image_nodes: type: boolean title: Retrieve Image Nodes description: Whether to retrieve image nodes. default: false deprecated: true retrieve_page_screenshot_nodes: type: boolean title: Retrieve Page Screenshot Nodes description: Whether to retrieve page screenshot nodes. default: false retrieve_page_figure_nodes: type: boolean title: Retrieve Page Figure Nodes description: Whether to retrieve page figure nodes. default: false class_name: type: string title: Class Name default: base_component type: object title: PresetRetrievalParams description: Schema for the search params for an retrieval execution that can be preset for a pipeline. PipelineType: type: string enum: - PLAYGROUND - MANAGED title: PipelineType description: Enum for representing the type of a pipeline OpenAIEmbedding: properties: model_name: type: string title: Model Name description: The name of the OpenAI embedding model. default: text-embedding-ada-002 embed_batch_size: type: integer maximum: 2048.0 exclusiveMinimum: 0.0 title: Embed Batch Size description: The batch size for embedding calls. default: 10 num_workers: anyOf: - type: integer - type: 'null' title: Num Workers description: The number of workers to use for async embedding calls. additional_kwargs: additionalProperties: true type: object title: Additional Kwargs description: Additional kwargs for the OpenAI API. api_key: anyOf: - type: string - type: 'null' title: Api Key description: The OpenAI API key. api_base: anyOf: - type: string - type: 'null' title: Api Base description: The base URL for OpenAI API. default: https://api.openai.com/v1 api_version: anyOf: - type: string - type: 'null' title: Api Version description: The version for OpenAI API. default: '' max_retries: type: integer minimum: 0.0 title: Max Retries description: Maximum number of retries. default: 10 timeout: type: number minimum: 0.0 title: Timeout description: Timeout for each request. default: 60.0 default_headers: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Default Headers description: The default headers for API requests. reuse_client: type: boolean title: Reuse Client description: Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. default: true dimensions: anyOf: - type: integer - type: 'null' title: Dimensions description: The number of dimensions on the output embedding vectors. Works only with v3 embedding models. class_name: type: string title: Class Name default: OpenAIEmbedding type: object title: OpenAIEmbedding PageScreenshotMetadata: properties: page_index: type: integer minimum: 0.0 title: Page Index description: The index of the page for which the screenshot is taken (0-indexed) file_id: type: string format: uuid title: File Id description: The ID of the file that the page screenshot was taken from image_size: type: integer minimum: 0.0 title: Image Size description: The size of the image in bytes metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata description: Metadata for the screenshot type: object required: - page_index - file_id - image_size title: PageScreenshotMetadata ObjectType: type: string enum: - '1' - '2' - '3' - '4' - '5' title: ObjectType JobNameMapping: type: string enum: - MANAGED_INGESTION - DATA_SOURCE - FILE_UPDATER - PARSE - TRANSFORM - INGESTION - METADATA_UPDATE title: JobNameMapping description: Enum for mapping original job names to readable names. LLMParameters: properties: model_name: $ref: '#/components/schemas/SupportedLLMModelNames' description: The name of the model to use for LLM completions. default: GPT_4_1_MINI system_prompt: anyOf: - type: string maxLength: 3000 - type: 'null' title: System Prompt description: The system prompt to use for the completion. temperature: anyOf: - type: number - type: 'null' title: Temperature description: The temperature value for the model. default: 0.1 use_chain_of_thought_reasoning: anyOf: - type: boolean - type: 'null' title: Use Chain Of Thought Reasoning description: Whether to use chain of thought reasoning. use_citation: anyOf: - type: boolean - type: 'null' title: Use Citation description: Whether to show citations in the response. default: true class_name: type: string title: Class Name default: base_component type: object title: LLMParameters ManagedOpenAIEmbeddingConfig: properties: type: type: string const: MANAGED_OPENAI_EMBEDDING title: Type description: Type of the embedding model. default: MANAGED_OPENAI_EMBEDDING component: $ref: '#/components/schemas/ManagedOpenAIEmbedding' description: Configuration for the Managed OpenAI embedding model. type: object title: ManagedOpenAIEmbeddingConfig SentenceChunkingConfig: properties: chunk_size: type: integer exclusiveMinimum: 0.0 title: Chunk Size default: 1024 chunk_overlap: type: integer title: Chunk Overlap default: 200 gte: 0 mode: type: string const: sentence title: Mode default: sentence separator: type: string title: Separator default: ' ' paragraph_separator: type: string title: Paragraph Separator default: ' ' type: object title: SentenceChunkingConfig NoneSegmentationConfig: properties: mode: type: string const: none title: Mode default: none type: object title: NoneSegmentationConfig CloudAzureAISearchVectorStore: properties: supports_nested_metadata_filters: type: boolean const: true title: Supports Nested Metadata Filters default: true search_service_api_key: type: string format: password title: Search Service Api Key writeOnly: true search_service_endpoint: type: string title: Search Service Endpoint search_service_api_version: anyOf: - type: string - type: 'null' title: Search Service Api Version index_name: anyOf: - type: string - type: 'null' title: Index Name filterable_metadata_field_keys: anyOf: - additionalProperties: true type: object - type: 'null' title: Filterable Metadata Field Keys embedding_dimension: anyOf: - type: integer - type: 'null' title: Embedding Dimension client_id: anyOf: - type: string - type: 'null' title: Client Id client_secret: anyOf: - type: string format: password writeOnly: true - type: 'null' title: Client Secret tenant_id: anyOf: - type: string - type: 'null' title: Tenant Id class_name: type: string title: Class Name default: CloudAzureAISearchVectorStore type: object required: - search_service_api_key - search_service_endpoint title: CloudAzureAISearchVectorStore description: Cloud Azure AI Search Vector Store. RetrievalMode: type: string enum: - chunks - files_via_metadata - files_via_content - auto_routed title: RetrievalMode MetadataFilters: properties: filters: items: anyOf: - $ref: '#/components/schemas/MetadataFilter' - $ref: '#/components/schemas/MetadataFilters' type: array title: Filters condition: anyOf: - $ref: '#/components/schemas/FilterCondition' - type: 'null' default: and type: object required: - filters title: MetadataFilters description: Metadata filters for vector stores. PlaygroundSession: properties: id: type: string format: uuid title: Id description: Unique identifier created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime pipeline_id: type: string format: uuid title: Pipeline Id user_id: type: string title: User Id llm_params_id: type: string format: uuid title: Llm Params Id llm_params: $ref: '#/components/schemas/LLMParameters' description: LLM parameters last used in this session. retrieval_params_id: type: string format: uuid title: Retrieval Params Id retrieval_params: $ref: '#/components/schemas/PresetRetrievalParams' description: Preset retrieval parameters last used in this session. chat_messages: items: $ref: '#/components/schemas/ChatMessage' type: array title: Chat Messages description: Chat message history for this session. type: object required: - id - pipeline_id - user_id - llm_params_id - retrieval_params_id title: PlaygroundSession description: A playground session for a user. PGVectorHNSWSettings: properties: ef_construction: type: integer minimum: 1.0 title: Ef Construction description: The number of edges to use during the construction phase. default: 64 ef_search: type: integer minimum: 1.0 title: Ef Search description: The number of edges to use during the search phase. default: 40 m: type: integer minimum: 1.0 title: M description: The number of bi-directional links created for each new element. default: 16 vector_type: $ref: '#/components/schemas/PGVectorVectorType' description: The type of vector to use. default: vector distance_method: $ref: '#/components/schemas/PGVectorDistanceMethod' description: The distance method to use. default: cosine type: object title: PGVectorHNSWSettings description: HNSW settings for PGVector. GeminiEmbeddingConfig: properties: type: type: string const: GEMINI_EMBEDDING title: Type description: Type of the embedding model. default: GEMINI_EMBEDDING component: $ref: '#/components/schemas/GeminiEmbedding' description: Configuration for the Gemini embedding model. type: object title: GeminiEmbeddingConfig ParsingMode: type: string enum: - parse_page_without_llm - parse_page_with_llm - parse_page_with_lvm - parse_page_with_agent - parse_page_with_layout_agent - parse_document_with_llm - parse_document_with_lvm - parse_document_with_agent title: ParsingMode description: Enum for representing the mode of parsing to be used. CharacterChunkingConfig: properties: chunk_size: type: integer exclusiveMinimum: 0.0 title: Chunk Size default: 1024 chunk_overlap: type: integer title: Chunk Overlap default: 200 gte: 0 mode: type: string const: character title: Mode default: character type: object title: CharacterChunkingConfig NodeRelationship: type: string enum: - '1' - '2' - '3' - '4' - '5' title: NodeRelationship description: "Node relationships used in `BaseNode` class.\n\nAttributes:\n SOURCE: The node is the source document.\n PREVIOUS: The node is the previous node in the document.\n NEXT: The node is the next node in the document.\n PARENT: The node is the parent node in the document.\n CHILD: The node is a child node in the document." VertexTextEmbedding: properties: model_name: type: string title: Model Name description: The modelId of the VertexAI model to use. default: textembedding-gecko@003 embed_batch_size: type: integer maximum: 2048.0 exclusiveMinimum: 0.0 title: Embed Batch Size description: The batch size for embedding calls. default: 10 num_workers: anyOf: - type: integer - type: 'null' title: Num Workers description: The number of workers to use for async embedding calls. location: type: string title: Location description: The default location to use when making API calls. project: type: string title: Project description: The default GCP project to use when making Vertex API calls. embed_mode: $ref: '#/components/schemas/VertexEmbeddingMode' description: The embedding mode to use. default: retrieval additional_kwargs: additionalProperties: true type: object title: Additional Kwargs description: Additional kwargs for the Vertex. client_email: anyOf: - type: string - type: 'null' title: Client Email description: The client email for the VertexAI credentials. token_uri: anyOf: - type: string - type: 'null' title: Token Uri description: The token URI for the VertexAI credentials. private_key_id: anyOf: - type: string - type: 'null' title: Private Key Id description: The private key ID for the VertexAI credentials. private_key: anyOf: - type: string - type: 'null' title: Private Key description: The private key for the VertexAI credentials. class_name: type: string title: Class Name default: VertexTextEmbedding type: object required: - location - project - client_email - token_uri - private_key_id - private_key title: VertexTextEmbedding ChatInputParams: properties: messages: items: $ref: '#/components/schemas/InputMessage' type: array minItems: 1 title: Messages data: $ref: '#/components/schemas/ChatData' class_name: type: string title: Class Name default: base_component type: object title: ChatInputParams VertexEmbeddingMode: type: string enum: - default - classification - clustering - similarity - retrieval title: VertexEmbeddingMode description: 'Copied from llama_index.embeddings.vertex.base.VertexEmbeddingMode since importing llama_index.embeddings.vertex.base incurs a lot of memory usage.' ParserLanguages: type: string enum: - af - az - bs - cs - cy - da - de - en - es - et - fr - ga - hr - hu - id - is - it - ku - la - lt - lv - mi - ms - mt - nl - 'no' - oc - pi - pl - pt - ro - rs_latin - sk - sl - sq - sv - sw - tl - tr - uz - vi - ar - fa - ug - ur - bn - as - mni - ru - rs_cyrillic - be - bg - uk - mn - abq - ady - kbd - ava - dar - inh - che - lbe - lez - tab - tjk - hi - mr - ne - bh - mai - ang - bho - mah - sck - new - gom - sa - bgc - th - ch_sim - ch_tra - ja - ko - ta - te - kn title: ParserLanguages description: Enum for representing the languages supported by the parser. CloudMongoDBAtlasVectorSearch: properties: supports_nested_metadata_filters: type: boolean title: Supports Nested Metadata Filters default: false mongodb_uri: type: string format: password title: Mongodb Uri writeOnly: true db_name: type: string title: Db Name collection_name: type: string title: Collection Name vector_index_name: anyOf: - type: string - type: 'null' title: Vector Index Name fulltext_index_name: anyOf: - type: string - type: 'null' title: Fulltext Index Name embedding_dimension: anyOf: - type: integer - type: 'null' title: Embedding Dimension class_name: type: string title: Class Name default: CloudMongoDBAtlasVectorSearch type: object required: - mongodb_uri - db_name - collection_name title: CloudMongoDBAtlasVectorSearch description: "Cloud MongoDB Atlas Vector Store.\n\nThis class is used to store the configuration for a MongoDB Atlas vector store,\nso that it can be created and used in LlamaCloud.\n\nArgs:\n mongodb_uri (str): URI for connecting to MongoDB Atlas\n db_name (str): name of the MongoDB database\n collection_name (str): name of the MongoDB collection\n vector_index_name (str): name of the MongoDB Atlas vector index\n fulltext_index_name (str): name of the MongoDB Atlas full-text index" PaginatedListCloudDocumentsResponse: properties: documents: items: $ref: '#/components/schemas/CloudDocument' type: array title: Documents description: The documents to list limit: type: integer title: Limit description: The limit of the documents offset: type: integer title: Offset description: The offset of the documents total_count: type: integer title: Total Count description: The total number of documents type: object required: - documents - limit - offset - total_count title: PaginatedListCloudDocumentsResponse WebhookConfiguration: properties: webhook_url: anyOf: - type: string - type: 'null' title: Webhook Url description: URL to receive webhook POST notifications examples: - https://example.com/webhooks/llamacloud webhook_headers: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Webhook Headers description: Custom HTTP headers sent with each webhook request (e.g. auth tokens) examples: - Authorization: Bearer sk-... webhook_events: anyOf: - items: type: string enum: - extract.pending - extract.success - extract.error - extract.partial_success - extract.cancelled - parse.pending - parse.running - parse.success - parse.error - parse.partial_success - parse.cancelled - classify.pending - classify.running - classify.success - classify.error - classify.partial_success - classify.cancelled - sheets.pending - sheets.success - sheets.error - sheets.partial_success - sheets.cancelled - unmapped_event type: array - type: 'null' title: Webhook Events description: Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. examples: - - parse.success - parse.error webhook_output_format: anyOf: - type: string - type: 'null' title: Webhook Output Format description: 'Response format sent to the webhook: ''string'' (default) or ''json''' examples: - json type: object title: WebhookConfiguration description: Configuration for a single outbound webhook endpoint. CloudQdrantVectorStore: properties: supports_nested_metadata_filters: type: boolean const: true title: Supports Nested Metadata Filters default: true collection_name: type: string title: Collection Name url: type: string title: Url api_key: type: string format: password title: Api Key writeOnly: true max_retries: type: integer title: Max Retries default: 3 client_kwargs: additionalProperties: true type: object title: Client Kwargs class_name: type: string title: Class Name default: CloudQdrantVectorStore type: object required: - collection_name - url - api_key title: CloudQdrantVectorStore description: "Cloud Qdrant Vector Store.\n\nThis class is used to store the configuration for a Qdrant vector store, so that it can be\ncreated and used in LlamaCloud.\n\nArgs:\n collection_name (str): name of the Qdrant collection\n url (str): url of the Qdrant instance\n api_key (str): API key for authenticating with Qdrant\n max_retries (int): maximum number of retries in case of a failure. Defaults to 3\n client_kwargs (dict): additional kwargs to pass to the Qdrant client" RetrieveResults: properties: pipeline_id: type: string format: uuid title: Pipeline Id description: The ID of the pipeline that the query was retrieved against. retrieval_nodes: items: $ref: '#/components/schemas/TextNodeWithScore' type: array title: Retrieval Nodes description: The nodes retrieved by the pipeline for the given query. image_nodes: items: $ref: '#/components/schemas/PageScreenshotNodeWithScore' type: array title: Image Nodes description: The image nodes retrieved by the pipeline for the given query. Deprecated - will soon be replaced with 'page_screenshot_nodes'. deprecated: true page_figure_nodes: items: $ref: '#/components/schemas/PageFigureNodeWithScore' type: array title: Page Figure Nodes description: The page figure nodes retrieved by the pipeline for the given query. retrieval_latency: additionalProperties: type: number type: object title: Retrieval Latency description: The end-to-end latency for retrieval and reranking. metadata: additionalProperties: type: string type: object title: Metadata description: Metadata associated with the retrieval execution inferred_search_filters: anyOf: - $ref: '#/components/schemas/MetadataFilters' - type: 'null' description: The inferred search filters for the query. class_name: type: string title: Class Name default: RetrieveResults type: object required: - pipeline_id - retrieval_nodes title: RetrieveResults description: Schema for the result of an retrieval execution. MessageRole: type: string enum: - system - developer - user - assistant - function - tool - chatbot - model title: MessageRole description: Message role. BedrockEmbedding: properties: model_name: type: string title: Model Name description: The modelId of the Bedrock model to use. default: amazon.titan-embed-text-v1 embed_batch_size: type: integer maximum: 2048.0 exclusiveMinimum: 0.0 title: Embed Batch Size description: The batch size for embedding calls. default: 10 num_workers: anyOf: - type: integer - type: 'null' title: Num Workers description: The number of workers to use for async embedding calls. profile_name: anyOf: - type: string - type: 'null' title: Profile Name description: The name of aws profile to use. If not given, then the default profile is used. aws_access_key_id: anyOf: - type: string - type: 'null' title: Aws Access Key Id description: AWS Access Key ID to use aws_secret_access_key: anyOf: - type: string - type: 'null' title: Aws Secret Access Key description: AWS Secret Access Key to use aws_session_token: anyOf: - type: string - type: 'null' title: Aws Session Token description: AWS Session Token to use region_name: anyOf: - type: string - type: 'null' title: Region Name description: AWS region name to use. Uses region configured in AWS CLI if not passed max_retries: type: integer exclusiveMinimum: 0.0 title: Max Retries description: The maximum number of API retries. default: 10 timeout: type: number title: Timeout description: The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. default: 60.0 additional_kwargs: additionalProperties: true type: object title: Additional Kwargs description: Additional kwargs for the bedrock client. class_name: type: string title: Class Name default: BedrockEmbedding type: object title: BedrockEmbedding RelatedNodeInfo: properties: node_id: type: string title: Node Id node_type: anyOf: - $ref: '#/components/schemas/ObjectType' - type: string - type: 'null' title: Node Type metadata: additionalProperties: true type: object title: Metadata hash: anyOf: - type: string - type: 'null' title: Hash class_name: type: string title: Class Name default: RelatedNodeInfo type: object required: - node_id title: RelatedNodeInfo HuggingFaceInferenceAPIEmbedding: properties: model_name: anyOf: - type: string - type: 'null' title: Model Name description: Hugging Face model name. If None, the task will be used. embed_batch_size: type: integer maximum: 2048.0 exclusiveMinimum: 0.0 title: Embed Batch Size description: The batch size for embedding calls. default: 10 num_workers: anyOf: - type: integer - type: 'null' title: Num Workers description: The number of workers to use for async embedding calls. pooling: anyOf: - $ref: '#/components/schemas/Pooling' - type: 'null' description: Pooling strategy. If None, the model's default pooling is used. default: cls query_instruction: anyOf: - type: string - type: 'null' title: Query Instruction description: Instruction to prepend during query embedding. text_instruction: anyOf: - type: string - type: 'null' title: Text Instruction description: Instruction to prepend during text embedding. token: anyOf: - type: string - type: boolean - type: 'null' title: Token description: Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. timeout: anyOf: - type: number - type: 'null' title: Timeout description: The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. headers: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Headers description: Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. cookies: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Cookies description: Additional cookies to send to the server. task: anyOf: - type: string - type: 'null' title: Task description: Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. class_name: type: string title: Class Name default: HuggingFaceInferenceAPIEmbedding type: object title: HuggingFaceInferenceAPIEmbedding InputMessage: properties: id: type: string format: uuid title: Id description: ID of the message, if any. a UUID. role: $ref: '#/components/schemas/MessageRole' content: type: string title: Content data: anyOf: - additionalProperties: true type: object - type: 'null' title: Data description: Additional data to be stored with the message. class_name: type: string title: Class Name default: base_component type: object required: - role - content title: InputMessage description: This is distinct from a ChatMessage because this schema is enforced by the AI Chat library used in the frontend EmbeddingModelConfig: properties: id: type: string format: uuid title: Id description: Unique identifier created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime name: type: string title: Name description: The name of the embedding model config. embedding_config: oneOf: - $ref: '#/components/schemas/AzureOpenAIEmbeddingConfig' - $ref: '#/components/schemas/CohereEmbeddingConfig' - $ref: '#/components/schemas/GeminiEmbeddingConfig' - $ref: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig' - $ref: '#/components/schemas/OpenAIEmbeddingConfig' - $ref: '#/components/schemas/VertexAIEmbeddingConfig' - $ref: '#/components/schemas/BedrockEmbeddingConfig' title: Embedding Config description: The embedding configuration for the embedding model config. discriminator: propertyName: type mapping: AZURE_EMBEDDING: '#/components/schemas/AzureOpenAIEmbeddingConfig' BEDROCK_EMBEDDING: '#/components/schemas/BedrockEmbeddingConfig' COHERE_EMBEDDING: '#/components/schemas/CohereEmbeddingConfig' GEMINI_EMBEDDING: '#/components/schemas/GeminiEmbeddingConfig' HUGGINGFACE_API_EMBEDDING: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig' OPENAI_EMBEDDING: '#/components/schemas/OpenAIEmbeddingConfig' VERTEXAI_EMBEDDING: '#/components/schemas/VertexAIEmbeddingConfig' project_id: type: string format: uuid title: Project Id type: object required: - id - name - embedding_config - project_id title: EmbeddingModelConfig description: Schema for an embedding model config. PGVectorVectorType: type: string enum: - vector - half_vec - bit - sparse_vec title: PGVectorVectorType description: 'Vector storage formats for PGVector. Docs: https://github.com/pgvector/pgvector?tab=readme-ov-file#query-options' ManagedIngestionStatus: type: string enum: - NOT_STARTED - IN_PROGRESS - SUCCESS - ERROR - PARTIAL_SUCCESS - CANCELLED title: ManagedIngestionStatus description: Status of managed ingestion with partial Updates. PipelineConfigurationHashes: properties: embedding_config_hash: anyOf: - type: string - type: 'null' title: Embedding Config Hash description: Hash of the embedding config. default: '' parsing_config_hash: anyOf: - type: string - type: 'null' title: Parsing Config Hash description: Hash of the llama parse parameters. default: '' transform_config_hash: anyOf: - type: string - type: 'null' title: Transform Config Hash description: Hash of the transform config. default: '' type: object title: PipelineConfigurationHashes description: Hashes for the configuration of a pipeline. ConfigurableDataSinkNames: type: string enum: - PINECONE - POSTGRES - QDRANT - AZUREAI_SEARCH - MONGODB_ATLAS - MILVUS - ASTRA_DB title: ConfigurableDataSinkNames DataSink: properties: id: type: string format: uuid title: Id description: Unique identifier created_at: anyOf: - type: string format: date-time - type: 'null' title: Created At description: Creation datetime updated_at: anyOf: - type: string format: date-time - type: 'null' title: Updated At description: Update datetime name: type: string title: Name description: The name of the data sink. sink_type: $ref: '#/components/schemas/ConfigurableDataSinkNames' component: anyOf: - additionalProperties: true type: object - $ref: '#/components/schemas/CloudPineconeVectorStore' - $ref: '#/components/schemas/CloudPostgresVectorStore' - $ref: '#/components/schemas/CloudQdrantVectorStore' - $ref: '#/components/schemas/CloudAzureAISearchVectorStore' - $ref: '#/components/schemas/CloudMongoDBAtlasVectorSearch' - $ref: '#/components/schemas/CloudMilvusVectorStore' - $ref: '#/components/schemas/CloudAstraDBVectorStore' title: DataSinkCreateComponent description: Component that implements the data sink project_id: type: string format: uuid title: Project Id type: object required: - id - name - sink_type - component - project_id title: DataSink description: Schema for a data sink. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError LlamaParseParameters: properties: webhook_configurations: anyOf: - items: $ref: '#/components/schemas/WebhookConfiguration' type: array - type: 'null' title: Webhook Configurations description: Outbound webhook endpoints to notify on job status changes priority: anyOf: - type: string enum: - low - medium - high - critical - type: 'null' title: Priority description: The priority for the request. This field may be ignored or overwritten depending on the organization tier. languages: items: $ref: '#/components/schemas/ParserLanguages' type: array minItems: 1 title: Languages parsing_instruction: anyOf: - type: string - type: 'null' title: Parsing Instruction default: '' disable_ocr: anyOf: - type: boolean - type: 'null' title: Disable Ocr default: false annotate_links: anyOf: - type: boolean - type: 'null' title: Annotate Links default: false adaptive_long_table: anyOf: - type: boolean - type: 'null' title: Adaptive Long Table default: false compact_markdown_table: anyOf: - type: boolean - type: 'null' title: Compact Markdown Table default: false disable_reconstruction: anyOf: - type: boolean - type: 'null' title: Disable Reconstruction default: false disable_image_extraction: anyOf: - type: boolean - type: 'null' title: Disable Image Extraction default: false invalidate_cache: anyOf: - type: boolean - type: 'null' title: Invalidate Cache default: false outlined_table_extraction: anyOf: - type: boolean - type: 'null' title: Outlined Table Extraction default: false aggressive_table_extraction: anyOf: - type: boolean - type: 'null' title: Aggressive Table Extraction default: false merge_tables_across_pages_in_markdown: anyOf: - type: boolean - type: 'null' title: Merge Tables Across Pages In Markdown default: false output_pdf_of_document: anyOf: - type: boolean - type: 'null' title: Output Pdf Of Document default: false do_not_cache: anyOf: - type: boolean - type: 'null' title: Do Not Cache default: false fast_mode: anyOf: - type: boolean - type: 'null' title: Fast Mode default: false skip_diagonal_text: anyOf: - type: boolean - type: 'null' title: Skip Diagonal Text default: false preserve_layout_alignment_across_pages: anyOf: - type: boolean - type: 'null' title: Preserve Layout Alignment Across Pages default: false preserve_very_small_text: anyOf: - type: boolean - type: 'null' title: Preserve Very Small Text default: false gpt4o_mode: anyOf: - type: boolean - type: 'null' title: Gpt4O Mode default: false gpt4o_api_key: anyOf: - type: string - type: 'null' title: Gpt4O Api Key do_not_unroll_columns: anyOf: - type: boolean - type: 'null' title: Do Not Unroll Columns default: false extract_layout: anyOf: - type: boolean - type: 'null' title: Extract Layout default: false high_res_ocr: anyOf: - type: boolean - type: 'null' title: High Res Ocr default: false html_make_all_elements_visible: anyOf: - type: boolean - type: 'null' title: Html Make All Elements Visible default: false layout_aware: anyOf: - type: boolean - type: 'null' title: Layout Aware default: false specialized_chart_parsing_agentic: anyOf: - type: boolean - type: 'null' title: Specialized Chart Parsing Agentic default: false specialized_chart_parsing_plus: anyOf: - type: boolean - type: 'null' title: Specialized Chart Parsing Plus default: false specialized_chart_parsing_efficient: anyOf: - type: boolean - type: 'null' title: Specialized Chart Parsing Efficient default: false specialized_image_parsing: anyOf: - type: boolean - type: 'null' title: Specialized Image Parsing default: false precise_bounding_box: anyOf: - type: boolean - type: 'null' title: Precise Bounding Box default: false line_level_bounding_box: anyOf: - type: boolean - type: 'null' title: Line Level Bounding Box default: false html_remove_navigation_elements: anyOf: - type: boolean - type: 'null' title: Html Remove Navigation Elements default: false html_remove_fixed_elements: anyOf: - type: boolean - type: 'null' title: Html Remove Fixed Elements default: false guess_xlsx_sheet_name: anyOf: - type: boolean - type: 'null' title: Guess Xlsx Sheet Name default: false page_separator: anyOf: - type: string - type: 'null' title: Page Separator bounding_box: anyOf: - type: string - type: 'null' title: Bounding Box bbox_top: anyOf: - type: number - type: 'null' title: Bbox Top bbox_right: anyOf: - type: number - type: 'null' title: Bbox Right bbox_bottom: anyOf: - type: number - type: 'null' title: Bbox Bottom bbox_left: anyOf: - type: number - type: 'null' title: Bbox Left target_pages: anyOf: - type: string - type: 'null' title: Target Pages use_vendor_multimodal_model: anyOf: - type: boolean - type: 'null' title: Use Vendor Multimodal Model default: false vendor_multimodal_model_name: anyOf: - type: string - type: 'null' title: Vendor Multimodal Model Name model: anyOf: - type: string - type: 'null' title: Model vendor_multimodal_api_key: anyOf: - type: string - type: 'null' title: Vendor Multimodal Api Key page_prefix: anyOf: - type: string - type: 'null' title: Page Prefix page_suffix: anyOf: - type: string - type: 'null' title: Page Suffix webhook_url: anyOf: - type: string - type: 'null' title: Webhook Url preset: anyOf: - type: string - type: 'null' title: Preset take_screenshot: anyOf: - type: boolean - type: 'null' title: Take Screenshot default: false is_formatting_instruction: anyOf: - type: boolean - type: 'null' title: Is Formatting Instruction default: true premium_mode: anyOf: - type: boolean - type: 'null' title: Premium Mode default: false continuous_mode: anyOf: - type: boolean - type: 'null' title: Continuous Mode default: false input_s3_path: anyOf: - type: string - type: 'null' title: Input S3 Path input_s3_region: anyOf: - type: string - type: 'null' title: Input S3 Region output_s3_path_prefix: anyOf: - type: string - type: 'null' title: Output S3 Path Prefix output_s3_region: anyOf: - type: string - type: 'null' title: Output S3 Region project_id: anyOf: - type: string - type: 'null' title: Project Id azure_openai_deployment_name: anyOf: - type: string - type: 'null' title: Azure Openai Deployment Name azure_openai_endpoint: anyOf: - type: string - type: 'null' title: Azure Openai Endpoint azure_openai_api_version: anyOf: - type: string - type: 'null' title: Azure Openai Api Version azure_openai_key: anyOf: - type: string - type: 'null' title: Azure Openai Key input_url: anyOf: - type: string - type: 'null' title: Input Url http_proxy: anyOf: - type: string - type: 'null' title: Http Proxy auto_mode: anyOf: - type: boolean - type: 'null' title: Auto Mode default: false auto_mode_trigger_on_regexp_in_page: anyOf: - type: string - type: 'null' title: Auto Mode Trigger On Regexp In Page auto_mode_trigger_on_text_in_page: anyOf: - type: string - type: 'null' title: Auto Mode Trigger On Text In Page auto_mode_trigger_on_table_in_page: anyOf: - type: boolean - type: 'null' title: Auto Mode Trigger On Table In Page default: false auto_mode_trigger_on_image_in_page: anyOf: - type: boolean - type: 'null' title: Auto Mode Trigger On Image In Page default: false auto_mode_configuration_json: anyOf: - type: string - type: 'null' title: Auto Mode Configuration Json structured_output: anyOf: - type: boolean - type: 'null' title: Structured Output default: false structured_output_json_schema: anyOf: - type: string - type: 'null' title: Structured Output Json Schema structured_output_json_schema_name: anyOf: - type: string - type: 'null' title: Structured Output Json Schema Name max_pages: anyOf: - type: integer - type: 'null' title: Max Pages max_pages_enforced: anyOf: - type: integer - type: 'null' title: Max Pages Enforced extract_charts: anyOf: - type: boolean - type: 'null' title: Extract Charts default: false formatting_instruction: anyOf: - type: string - type: 'null' title: Formatting Instruction complemental_formatting_instruction: anyOf: - type: string - type: 'null' title: Complemental Formatting Instruction content_guideline_instruction: anyOf: - type: string - type: 'null' title: Content Guideline Instruction spreadsheet_extract_sub_tables: anyOf: - type: boolean - type: 'null' title: Spreadsheet Extract Sub Tables default: false spreadsheet_force_formula_computation: anyOf: - type: boolean - type: 'null' title: Spreadsheet Force Formula Computation default: false spreadsheet_include_hidden_sheets: anyOf: - type: boolean - type: 'null' title: Spreadsheet Include Hidden Sheets default: false inline_images_in_markdown: anyOf: - type: boolean - type: 'null' title: Inline Images In Markdown default: false job_timeout_in_seconds: anyOf: - type: number - type: 'null' title: Job Timeout In Seconds job_timeout_extra_time_per_page_in_seconds: anyOf: - type: number - type: 'null' title: Job Timeout Extra Time Per Page In Seconds strict_mode_image_extraction: anyOf: - type: boolean - type: 'null' title: Strict Mode Image Extraction default: false strict_mode_image_ocr: anyOf: - type: boolean - type: 'null' title: Strict Mode Image Ocr default: false strict_mode_reconstruction: anyOf: - type: boolean - type: 'null' title: Strict Mode Reconstruction default: false strict_mode_buggy_font: anyOf: - type: boolean - type: 'null' title: Strict Mode Buggy Font default: false save_images: anyOf: - type: boolean - type: 'null' title: Save Images default: true images_to_save: anyOf: - items: type: string enum: - screenshot - embedded - layout type: array - type: 'null' title: Images To Save hide_headers: anyOf: - type: boolean - type: 'null' title: Hide Headers default: false hide_footers: anyOf: - type: boolean - type: 'null' title: Hide Footers default: false page_header_prefix: anyOf: - type: string - type: 'null' title: Page Header Prefix page_header_suffix: anyOf: - type: string - type: 'null' title: Page Header Suffix page_footer_prefix: anyOf: - type: string - type: 'null' title: Page Footer Prefix page_footer_suffix: anyOf: - type: string - type: 'null' title: Page Footer Suffix remove_hidden_text: anyOf: - type: boolean - type: 'null' title: Remove Hidden Text default: false keep_page_separator_when_merging_tables: anyOf: - type: boolean - type: 'null' title: Keep Page Separator When Merging Tables default: false ignore_document_elements_for_layout_detection: anyOf: - type: boolean - type: 'null' title: Ignore Document Elements For Layout Detection default: false output_tables_as_HTML: anyOf: - type: boolean - type: 'null' title: Output Tables As Html default: false internal_is_screenshot_job: anyOf: - type: boolean - type: 'null' title: Internal Is Screenshot Job default: false parse_mode: anyOf: - $ref: '#/components/schemas/ParsingMode' - type: 'null' system_prompt: anyOf: - type: string - type: 'null' title: System Prompt system_prompt_append: anyOf: - type: string - type: 'null' title: System Prompt Append user_prompt: anyOf: - type: string - type: 'null' title: User Prompt page_error_tolerance: anyOf: - type: number - type: 'null' title: Page Error Tolerance default: 0.05 replace_failed_page_mode: anyOf: - $ref: '#/components/schemas/FailPageMode' - type: 'null' default: raw_text replace_failed_page_with_error_message_prefix: anyOf: - type: string - type: 'null' title: Replace Failed Page With Error Message Prefix replace_failed_page_with_error_message_suffix: anyOf: - type: string - type: 'null' title: Replace Failed Page With Error Message Suffix markdown_table_multiline_header_separator: anyOf: - type: string - type: 'null' title: Markdown Table Multiline Header Separator presentation_out_of_bounds_content: anyOf: - type: boolean - type: 'null' title: Presentation Out Of Bounds Content default: false presentation_skip_embedded_data: anyOf: - type: boolean - type: 'null' title: Presentation Skip Embedded Data default: false tier: anyOf: - type: string - type: 'null' title: Tier version: anyOf: - type: string - type: 'null' title: Version extract_printed_page_number: anyOf: - type: boolean - type: 'null' title: Extract Printed Page Number default: false enable_cost_optimizer: anyOf: - type: boolean - type: 'null' title: Enable Cost Optimizer type: object title: LlamaParseParameters BedrockEmbeddingConfig: properties: type: type: string const: BEDROCK_EMBEDDING title: Type description: Type of the embedding model. default: BEDROCK_EMBEDDING component: $ref: '#/components/schemas/BedrockEmbedding' description: Configuration for the Bedrock embedding model. type: object title: BedrockEmbeddingConfig PipelineCreate: properties: embedding_config: anyOf: - oneOf: - $ref: '#/components/schemas/AzureOpenAIEmbeddingConfig' - $ref: '#/components/schemas/CohereEmbeddingConfig' - $ref: '#/components/schemas/GeminiEmbeddingConfig' - $ref: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig' - $ref: '#/components/schemas/OpenAIEmbeddingConfig' - $ref: '#/components/schemas/VertexAIEmbeddingConfig' - $ref: '#/components/schemas/BedrockEmbeddingConfig' discriminator: propertyName: type mapping: AZURE_EMBEDDING: '#/components/schemas/AzureOpenAIEmbeddingConfig' BEDROCK_EMBEDDING: '#/components/schemas/BedrockEmbeddingConfig' COHERE_EMBEDDING: '#/components/schemas/CohereEmbeddingConfig' GEMINI_EMBEDDING: '#/components/schemas/GeminiEmbeddingConfig' HUGGINGFACE_API_EMBEDDING: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig' OPENAI_EMBEDDING: '#/components/schemas/OpenAIEmbeddingConfig' VERTEXAI_EMBEDDING: '#/components/schemas/VertexAIEmbeddingConfig' - type: 'null' title: Embedding Config transform_config: anyOf: - $ref: '#/components/schemas/AutoTransformConfig' - $ref: '#/components/schemas/AdvancedModeTransformConfig' - type: 'null' title: Transform Config description: Configuration for the transformation. sparse_model_config: anyOf: - $ref: '#/components/schemas/SparseModelConfig' - type: 'null' description: Configuration for the sparse model used in hybrid search. data_sink_id: anyOf: - type: string format: uuid - type: 'null' title: Data Sink Id description: Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID. embedding_model_config_id: anyOf: - type: string format: uuid - type: 'null' title: Embedding Model Config Id description: Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID. data_sink: anyOf: - $ref: '#/components/schemas/DataSinkCreate' - type: 'null' description: Data sink. When provided instead of data_sink_id, the data sink will be created. preset_retrieval_parameters: $ref: '#/components/schemas/PresetRetrievalParams' description: Preset retrieval parameters for the pipeline. llama_parse_parameters: $ref: '#/components/schemas/LlamaParseParameters' description: Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. status: anyOf: - type: string - type: 'null' title: Status description: Status of the pipeline deployment. metadata_config: anyOf: - $ref: '#/components/schemas/PipelineMetadataConfig' - type: 'null' description: Metadata configuration for the pipeline. name: type: string maxLength: 3000 minLength: 1 title: Name pipeline_type: $ref: '#/components/schemas/PipelineType' description: Type of pipeline. Either PLAYGROUND or MANAGED. default: MANAGED managed_pipeline_id: anyOf: - type: string format: uuid - type: 'null' title: Managed Pipeline Id description: The ID of the ManagedPipeline this playground pipeline is linked to. type: object required: - name title: PipelineCreate description: Schema for creating a pipeline. PipelineUpdate: properties: embedding_config: anyOf: - oneOf: - $ref: '#/components/schemas/AzureOpenAIEmbeddingConfig' - $ref: '#/components/schemas/CohereEmbeddingConfig' - $ref: '#/components/schemas/GeminiEmbeddingConfig' - $ref: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig' - $ref: '#/components/schemas/OpenAIEmbeddingConfig' - $ref: '#/components/schemas/VertexAIEmbeddingConfig' - $ref: '#/components/schemas/BedrockEmbeddingConfig' discriminator: propertyName: type mapping: AZURE_EMBEDDING: '#/components/schemas/AzureOpenAIEmbeddingConfig' BEDROCK_EMBEDDING: '#/components/schemas/BedrockEmbeddingConfig' COHERE_EMBEDDING: '#/components/schemas/CohereEmbeddingConfig' GEMINI_EMBEDDING: '#/components/schemas/GeminiEmbeddingConfig' HUGGINGFACE_API_EMBEDDING: '#/components/schemas/HuggingFaceInferenceAPIEmbeddingConfig' OPENAI_EMBEDDING: '#/components/schemas/OpenAIEmbeddingConfig' VERTEXAI_EMBEDDING: '#/components/schemas/VertexAIEmbeddingConfig' - type: 'null' title: Embedding Config transform_config: anyOf: - $ref: '#/components/schemas/AutoTransformConfig' - $ref: '#/components/schemas/AdvancedModeTransformConfig' - type: 'null' title: Transform Config description: Configuration for the transformation. sparse_model_config: anyOf: - $ref: '#/components/schemas/SparseModelConfig' - type: 'null' description: Configuration for the sparse model used in hybrid search. data_sink_id: anyOf: - type: string format: uuid - type: 'null' title: Data Sink Id description: Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID. embedding_model_config_id: anyOf: - type: string format: uuid - type: 'null' title: Embedding Model Config Id description: Embedding model config ID. When provided instead of embedding_config, the embedding model config will be looked up by ID. data_sink: anyOf: - $ref: '#/components/schemas/DataSinkCreate' - type: 'null' description: Data sink. When provided instead of data_sink_id, the data sink will be created. preset_retrieval_parameters: anyOf: - $ref: '#/components/schemas/PresetRetrievalParams' - type: 'null' description: Preset retrieval parameters for the pipeline. llama_parse_parameters: anyOf: - $ref: '#/components/schemas/LlamaParseParameters' - type: 'null' description: Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. deprecated: true status: anyOf: - type: string - type: 'null' title: Status description: Status of the pipeline deployment. metadata_config: anyOf: - $ref: '#/components/schemas/PipelineMetadataConfig' - type: 'null' description: Metadata configuration for the pipeline. name: anyOf: - type: string - type: 'null' title: Name managed_pipeline_id: anyOf: - type: string format: uuid - type: 'null' title: Managed Pipeline Id description: The ID of the ManagedPipeline this playground pipeline is linked to. type: object title: PipelineUpdate description: Schema for updating a pipeline. AzureOpenAIEmbedding: properties: model_name: type: string title: Model Name description: The name of the OpenAI embedding model. default: text-embedding-ada-002 embed_batch_size: type: integer maximum: 2048.0 exclusiveMinimum: 0.0 title: Embed Batch Size description: The batch size for embedding calls. default: 10 num_workers: anyOf: - type: integer - type: 'null' title: Num Workers description: The number of workers to use for async embedding calls. additional_kwargs: additionalProperties: true type: object title: Additional Kwargs description: Additional kwargs for the OpenAI API. api_key: anyOf: - type: string - type: 'null' title: Api Key description: The OpenAI API key. api_base: type: string title: Api Base description: The base URL for Azure deployment. default: '' api_version: type: string title: Api Version description: The version for Azure OpenAI API. default: '' max_retries: type: integer minimum: 0.0 title: Max Retries description: Maximum number of retries. default: 10 timeout: type: number minimum: 0.0 title: Timeout description: Timeout for each request. default: 60.0 default_headers: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Default Headers description: The default headers for API requests. reuse_client: type: boolean title: Reuse Client description: Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. default: true dimensions: anyOf: - type: integer - type: 'null' title: Dimensions description: The number of dimensions on the output embedding vectors. Works only with v3 embedding models. azure_endpoint: anyOf: - type: string - type: 'null' title: Azure Endpoint description: The Azure endpoint to use. azure_deployment: anyOf: - type: string - type: 'null' title: Azure Deployment description: The Azure deployment to use. class_name: type: string title: Class Name default: AzureOpenAIEmbedding type: object title: AzureOpenAIEmbedding securitySchemes: HTTPBearer: type: http scheme: bearer