openapi: 3.0.3
info:
  title: Llama Platform Agent Data Pipeline Data Sources API
  version: 0.1.0
tags:
- name: Pipeline Data Sources
paths:
  /api/v1/pipelines/{pipeline_id}/data-sources:
    get:
      tags:
      - Pipeline Data Sources
      summary: List Pipeline Data Sources
      description: Get data sources for a pipeline.
      operationId: list_pipeline_data_sources_api_v1_pipelines__pipeline_id__data_sources_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:
                type: array
                items:
                  $ref: '#/components/schemas/PipelineDataSource'
                title: Response List Pipeline Data Sources Api V1 Pipelines  Pipeline Id  Data Sources Get
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
    put:
      tags:
      - Pipeline Data Sources
      summary: Add Data Sources To Pipeline
      description: Add data sources to a pipeline.
      operationId: add_data_sources_to_pipeline_api_v1_pipelines__pipeline_id__data_sources_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/PipelineDataSourceCreate'
              title: Pipeline Data Source Creates
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/PipelineDataSource'
                title: Response Add Data Sources To Pipeline Api V1 Pipelines  Pipeline Id  Data Sources Put
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}:
    put:
      tags:
      - Pipeline Data Sources
      summary: Update Pipeline Data Source
      description: Update the configuration of a data source in a pipeline.
      operationId: update_pipeline_data_source_api_v1_pipelines__pipeline_id__data_sources__data_source_id__put
      security:
      - HTTPBearer: []
      parameters:
      - name: data_source_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Data Source 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
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PipelineDataSourceUpdate'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PipelineDataSource'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
  /api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}/sync:
    post:
      tags:
      - Pipeline Data Sources
      summary: Sync Pipeline Data Source
      description: 'Run incremental ingestion: pull upstream changes from the data source into the data sink.'
      operationId: sync_pipeline_data_source_api_v1_pipelines__pipeline_id__data_sources__data_source_id__sync_post
      security:
      - HTTPBearer: []
      parameters:
      - name: data_source_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Data Source 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
      requestBody:
        content:
          application/json:
            schema:
              anyOf:
              - $ref: '#/components/schemas/DataSourceSyncRequest'
              - type: 'null'
              title: Payload
      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}/data-sources/{data_source_id}/status:
    get:
      tags:
      - Pipeline Data Sources
      summary: Get Pipeline Data Source Status
      description: Get the status of a data source for a pipeline.
      operationId: get_pipeline_data_source_status_api_v1_pipelines__pipeline_id__data_sources__data_source_id__status_get
      security:
      - HTTPBearer: []
      parameters:
      - name: data_source_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
          title: Data Source 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'
components:
  schemas:
    ConfigurableDataSourceNames:
      type: string
      enum:
      - S3
      - AZURE_STORAGE_BLOB
      - GOOGLE_DRIVE
      - MICROSOFT_ONEDRIVE
      - MICROSOFT_SHAREPOINT
      - SLACK
      - NOTION_PAGE
      - CONFLUENCE
      - JIRA
      - JIRA_V2
      - BOX
      title: ConfigurableDataSourceNames
    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
    CloudAzStorageBlobDataSource:
      properties:
        supports_access_control:
          type: boolean
          title: Supports Access Control
          default: false
        container_name:
          type: string
          title: Container Name
          description: The name of the Azure Storage Blob container to read from.
        account_url:
          type: string
          title: Account Url
          description: The Azure Storage Blob account URL to use for authentication.
        blob:
          anyOf:
          - type: string
          - type: 'null'
          title: Blob
          description: The blob name to read from.
        prefix:
          anyOf:
          - type: string
          - type: 'null'
          title: Prefix
          description: The prefix of the Azure Storage Blob objects to read from.
        account_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Account Name
          description: The Azure Storage Blob account name to use for authentication.
        account_key:
          anyOf:
          - type: string
            format: password
            writeOnly: true
          - type: 'null'
          title: Account Key
          description: The Azure Storage Blob account key to use for authentication.
        tenant_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Tenant Id
          description: The Azure AD tenant ID to use for authentication.
        client_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Client Id
          description: The Azure AD client ID to use for authentication.
        client_secret:
          anyOf:
          - type: string
            format: password
            writeOnly: true
          - type: 'null'
          title: Client Secret
          description: The Azure AD client secret to use for authentication.
        class_name:
          type: string
          title: Class Name
          default: CloudAzStorageBlobDataSource
      type: object
      required:
      - container_name
      - account_url
      title: CloudAzStorageBlobDataSource
    PipelineDataSource:
      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 source.
        source_type:
          $ref: '#/components/schemas/ConfigurableDataSourceNames'
        custom_metadata:
          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: Custom Metadata
          description: Custom metadata that will be present on all data loaded from the data source
        component:
          anyOf:
          - additionalProperties: true
            type: object
          - $ref: '#/components/schemas/CloudS3DataSource'
          - $ref: '#/components/schemas/CloudAzStorageBlobDataSource'
          - $ref: '#/components/schemas/CloudGoogleDriveDataSource'
          - $ref: '#/components/schemas/CloudOneDriveDataSource'
          - $ref: '#/components/schemas/CloudSharepointDataSource'
          - $ref: '#/components/schemas/CloudSlackDataSource'
          - $ref: '#/components/schemas/CloudNotionPageDataSource'
          - $ref: '#/components/schemas/CloudConfluenceDataSource'
          - $ref: '#/components/schemas/CloudJiraDataSource'
          - $ref: '#/components/schemas/CloudJiraDataSourceV2'
          - $ref: '#/components/schemas/CloudBoxDataSource'
          title: DataSourceCreateComponent
          description: Component that implements the data source
        version_metadata:
          anyOf:
          - $ref: '#/components/schemas/DataSourceReaderVersionMetadata'
          - type: 'null'
          description: Version metadata for the data source
        project_id:
          type: string
          format: uuid
          title: Project Id
        data_source_id:
          type: string
          format: uuid
          title: Data Source Id
          description: The ID of the data source.
        pipeline_id:
          type: string
          format: uuid
          title: Pipeline Id
          description: The ID of the pipeline.
        last_synced_at:
          type: string
          format: date-time
          title: Last Synced At
          description: The last time the data source was automatically synced.
        sync_interval:
          anyOf:
          - type: number
          - type: 'null'
          title: Sync Interval
          description: The interval at which the data source should be synced.
        sync_schedule_set_by:
          anyOf:
          - type: string
          - type: 'null'
          title: Sync Schedule Set By
          description: The id of the user who set the sync schedule.
        status:
          anyOf:
          - type: string
            enum:
            - NOT_STARTED
            - IN_PROGRESS
            - SUCCESS
            - ERROR
            - CANCELLED
          - type: 'null'
          title: Status
          description: The status of the data source in the pipeline.
        status_updated_at:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Status Updated At
          description: The last time the status was updated.
      type: object
      required:
      - id
      - name
      - source_type
      - component
      - project_id
      - data_source_id
      - pipeline_id
      - last_synced_at
      title: PipelineDataSource
      description: Schema for a data source in a pipeline.
    CloudOneDriveDataSource:
      properties:
        supports_access_control:
          type: boolean
          const: true
          title: Supports Access Control
          default: true
        user_principal_name:
          type: string
          title: User Principal Name
          description: The user principal name to use for authentication.
        folder_path:
          anyOf:
          - type: string
          - type: 'null'
          title: Folder Path
          description: The path of the OneDrive folder to read from.
        folder_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Folder Id
          description: The ID of the OneDrive folder to read from.
        client_id:
          type: string
          title: Client Id
          description: The client ID to use for authentication.
        client_secret:
          type: string
          format: password
          title: Client Secret
          description: The client secret to use for authentication.
          writeOnly: true
        tenant_id:
          type: string
          title: Tenant Id
          description: The tenant ID to use for authentication.
        required_exts:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Required Exts
          description: The list of required file extensions.
        class_name:
          type: string
          title: Class Name
          default: CloudOneDriveDataSource
      type: object
      required:
      - user_principal_name
      - client_id
      - client_secret
      - tenant_id
      title: CloudOneDriveDataSource
    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
    CloudSharepointDataSource:
      properties:
        supports_access_control:
          type: boolean
          const: true
          title: Supports Access Control
          default: true
        site_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Site Name
          description: The name of the SharePoint site to download from.
        site_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Site Id
          description: The ID of the SharePoint site to download from.
        folder_path:
          anyOf:
          - type: string
          - type: 'null'
          title: Folder Path
          description: The path of the Sharepoint folder to read from.
        folder_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Folder Id
          description: The ID of the Sharepoint folder to read from.
        drive_name:
          anyOf:
          - type: string
          - type: 'null'
          title: Drive Name
          description: The name of the Sharepoint drive to read from.
        client_id:
          type: string
          title: Client Id
          description: The client ID to use for authentication.
        client_secret:
          type: string
          format: password
          title: Client Secret
          description: The client secret to use for authentication.
          writeOnly: true
        tenant_id:
          type: string
          title: Tenant Id
          description: The tenant ID to use for authentication.
        required_exts:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Required Exts
          description: The list of required file extensions.
        get_permissions:
          type: boolean
          title: Get Permissions
          description: Whether to get permissions for the sharepoint site.
          default: true
        include_path_patterns:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Include Path Patterns
          description: 'List of regex patterns for file paths to include. Full paths (including filename) must match at least one pattern to be included. Example: [''/reports/'', ''/docs/.*\.pdf$'', ''^Report.*\.pdf$'']'
        exclude_path_patterns:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Exclude Path Patterns
          description: 'List of regex patterns for file paths to exclude. Files whose paths (including filename) match any pattern will be excluded. Example: [''/temp/'', ''/backup/'', ''\.git/'', ''\.tmp$'', ''^~'']'
        class_name:
          type: string
          title: Class Name
          default: CloudSharepointDataSource
      type: object
      required:
      - client_id
      - client_secret
      - tenant_id
      title: CloudSharepointDataSource
    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
    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.'
    CloudGoogleDriveDataSource:
      properties:
        supports_access_control:
          type: boolean
          title: Supports Access Control
          default: false
        folder_id:
          type: string
          title: Folder Id
          description: The ID of the Google Drive folder to read from.
        service_account_key:
          anyOf:
          - additionalProperties:
              type: string
            type: object
            description: A dictionary containing secret values
          - type: 'null'
          title: Service Account Key
          description: The service account key JSON to use for authentication.
        class_name:
          type: string
          title: Class Name
          default: CloudGoogleDriveDataSource
      type: object
      required:
      - folder_id
      title: CloudGoogleDriveDataSource
    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
    PipelineDataSourceUpdate:
      properties:
        sync_interval:
          anyOf:
          - type: number
          - type: 'null'
          title: Sync Interval
          description: The interval at which the data source should be synced.
      type: object
      title: PipelineDataSourceUpdate
      description: Schema for updating an association between a data source and a pipeline.
    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.
    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'
    BoxAuthMechanism:
      type: string
      enum:
      - developer_token
      - ccg
      title: BoxAuthMechanism
    Pooling:
      type: string
      enum:
      - cls
      - mean
      - last
      title: Pooling
      description: Enum of possible pooling choices with pooling behaviors.
    FailureHandlingConfig:
      properties:
        skip_list_failures:
          type: boolean
          title: Skip List Failures
          description: Whether to skip failed batches/lists and continue processing
          default: false
      type: object
      title: FailureHandlingConfig
      description: Configuration for handling different types of failures during data source processing.
    CloudConfluenceDataSource:
      properties:
        supports_access_control:
          type: boolean
          title: Supports Access Control
          default: false
        server_url:
          type: string
          title: Server Url
          description: The server URL of the Confluence instance.
        authentication_mechanism:
          type: string
          title: Authentication Mechanism
          description: Type of Authentication for connecting to Confluence APIs.
        user_name:
          anyOf:
          - type: string
          - type: 'null'
          title: User Name
          description: The username to use for authentication.
        api_token:
          anyOf:
          - type: string
            format: password
            writeOnly: true
          - type: 'null'
          title: Api Token
          description: The API token to use for authentication.
        space_key:
          anyOf:
          - type: string
          - type: 'null'
          title: Space Key
          description: The space key to read from.
        page_ids:
          anyOf:
          - type: string
          - type: 'null'
          title: Page Ids
          description: The page IDs of the Confluence to read from.
        cql:
          anyOf:
          - type: string
          - type: 'null'
          title: Cql
          description: The CQL query to use for fetching pages.
        label:
          anyOf:
          - type: string
          - type: 'null'
          title: Label
          description: The label to use for fetching pages.
        index_restricted_pages:
          type: boolean
          title: Index Restricted Pages
          description: Whether to index restricted pages.
          default: false
        keep_markdown_format:
          type: boolean
          title: Keep Markdown Format
          description: Whether to keep the markdown format.
        failure_handling:
          $ref: '#/components/schemas/FailureHandlingConfig'
          description: "Configuration for handling failures during processing. Key-value object controlling failure handling behaviors.\n\nExample:\n{\n  \"skip_list_failures\": true\n}\n\nCurrently supports:\n- skip_list_failures: Skip failed batches/lists and continue processing"
        class_name:
          type: string
          title: Class Name
          default: CloudConfluenceDataSource
      type: object
      required:
      - authentication_mechanism
      - server_url
      title: CloudConfluenceDataSource
    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'
    DataSourceReaderVersionMetadata:
      properties:
        reader_version:
          anyOf:
          - type: string
            enum:
            - '1.0'
            - '2.0'
            - '2.1'
          - type: 'null'
          title: Reader Version
          description: The version of the reader to use for this data source.
      type: object
      title: DataSourceReaderVersionMetadata
    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
    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
    CloudJiraDataSourceV2:
      properties:
        supports_access_control:
          type: boolean
          title: Supports Access Control
          default: false
        email:
          anyOf:
          - type: string
          - type: 'null'
          title: Email
          description: The email address to use for authentication.
        api_token:
          anyOf:
          - type: string
            format: password
            writeOnly: true
          - type: 'null'
          title: Api Token
          description: The API Access Token used for Basic, PAT and OAuth2 authentication.
        server_url:
          type: string
          title: Server Url
          description: The server url for Jira Cloud.
        cloud_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Cloud Id
          description: The cloud ID, used in case of OAuth2.
        authentication_mechanism:
          type: string
          title: Authentication Mechanism
          description: Type of Authentication for connecting to Jira APIs.
        api_version:
          type: string
          enum:
          - '2'
          - '3'
          title: Api Version
          description: Jira REST API version to use (2 or 3). 3 supports Atlassian Document Format (ADF).
          default: '2'
        query:
          type: string
          title: Query
          description: JQL (Jira Query Language) query to search.
        fields:
          anyOf:
          - items:
              type: string
            type: array
          - type: 'null'
          title: Fields
          description: List of fields to retrieve from Jira. If None, retrieves all fields.
        expand:
          anyOf:
          - type: string
          - type: 'null'
          title: Expand
          description: Fields to expand in the response.
        requests_per_minute:
          anyOf:
          - type: integer
          - type: 'null'
          title: Requests Per Minute
          description: Rate limit for Jira API requests per minute.
        get_permissions:
          type: boolean
          title: Get Permissions
          description: Whether to fetch project role permissions and issue-level security
          default: true
        class_name:
          type: string
          title: Class Name
          default: CloudJiraDataSourceV2
      type: object
      required:
      - server_url
      - authentication_mechanism
      - query
      title: CloudJiraDataSourceV2
      description: Cloud Jira Data Source integrating JiraReaderV2.
    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
    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.
    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
    DataSourceSyncRequest:
      properties:
        pipeline_file_ids:
          anyOf:
          - items:
              type: string
              format: uuid
            type: array
          - type: 'null'
          title: Pipeline File Ids
      type: object
      title: DataSourceSyncRequest
      description: "Request model for syncing pipeline data sources.\n\nNotes:\n- This endpoint pulls from the 3p data source and parses.\n- We accept pipeline_file_ids for now because callers (e.g. add_files_to_pipeline)\n  often have these IDs handy. Internally we map them to external IDs to filter\n  the reader, which enumerates by external ID.\n- Likely to evolve to take external IDs directly; keeping this for convenience."
    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.
    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
    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
    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.
    CloudBoxDataSource:
      properties:
        supports_access_control:
          type: boolean
          title: Supports Access Control
          default: false
        folder_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Folder Id
          description: The ID of the Box folder to read from.
        authentication_mechanism:
          $ref: '#/components/schemas/BoxAuthMechanism'
          description: The type of authentication to use (Developer Token or CCG)
        developer_token:
          anyOf:
          - type: string
            format: password
            writeOnly: true
          - type: 'null'
          title: Developer Token
          description: Developer token for authentication if authentication_mechanism is 'developer_token'.
        client_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Client Id
          description: Box API key used for identifying the application the user is authenticating with
        client_secret:
          anyOf:
          - type: string
            format: password
            writeOnly: true
          - type: 'null'
          title: Client Secret
          description: Box API secret used for making auth requests.
        user_id:
          anyOf:
          - type: string
          - type: 'null'
          title: User Id
          description: Box User ID, if provided authenticates as user.
        enterprise_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Enterprise Id
          description: Box Enterprise ID, if provided authenticates as service.
        class_name:
          type: string
          title: Class Name
          default: CloudBoxDataSource
      type: object
      required:
      - authentication_mechanism
      title: CloudBoxDataSource
    CloudNotionPageDataSource:
      properties:
        supports_access_control:
          type: boolean
          title: Supports Access Control
          default: false
        integration_token:
          type: string
          format: password
          title: Integration Token
          description: The integration token to use for authentication.
          writeOnly: true
        database_ids:
          anyOf:
          - type: string
          - type: 'null'
          title: Database Ids
          description: The Notion Database Id to read content from.
        page_ids:
          anyOf:
          - type: string
          - type: 'null'
          title: Page Ids
          description: The Page ID's of the Notion to read from.
        class_name:
          type: string
          title: Class Name
          default: CloudNotionPageDataSource
      type: object
      required:
      - integration_token
      title: CloudNotionPageDataSource
    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"
    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"
    CloudSlackDataSource:
      properties:
        supports_access_control:
          type: boolean
          title: Supports Access Control
          default: false
        slack_token:
          type: string
          format: password
          title: Slack Token
          description: Slack Bot Token.
          writeOnly: true
        channel_ids:
          anyOf:
          - type: string
          - type: 'null'
          title: Channel Ids
          description: Slack Channel.
        latest_date:
          anyOf:
          - type: string
          - type: 'null'
          title: Latest Date
          description: Latest date.
        earliest_date:
          anyOf:
          - type: string
          - type: 'null'
          title: Earliest Date
          description: Earliest date.
        earliest_date_timestamp:
          anyOf:
          - type: number
          - type: 'null'
          title: Earliest Date Timestamp
          description: Earliest date timestamp.
        latest_date_timestamp:
          anyOf:
          - type: number
          - type: 'null'
          title: Latest Date Timestamp
          description: Latest date timestamp.
        channel_patterns:
          anyOf:
          - type: string
          - type: 'null'
          title: Channel Patterns
          description: Slack Channel name pattern.
        class_name:
          type: string
          title: Class Name
          default: CloudSlackDataSource
      type: object
      required:
      - slack_token
      title: CloudSlackDataSource
    PipelineDataSourceCreate:
      properties:
        data_source_id:
          type: string
          format: uuid
          title: Data Source Id
          description: The ID of the data source.
        sync_interval:
          anyOf:
          - type: number
          - type: 'null'
          title: Sync Interval
          description: 'The interval at which the data source should be synced. Valid values are: 21600, 43200, 86400'
      type: object
      required:
      - data_source_id
      title: PipelineDataSourceCreate
      description: Schema for creating an association between a data source and a pipeline.
    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
    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
    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.
    CloudJiraDataSource:
      properties:
        supports_access_control:
          type: boolean
          title: Supports Access Control
          default: false
        email:
          anyOf:
          - type: string
          - type: 'null'
          title: Email
          description: The email address to use for authentication.
        api_token:
          anyOf:
          - type: string
            format: password
            writeOnly: true
          - type: 'null'
          title: Api Token
          description: The API/ Access Token used for Basic, PAT and OAuth2 authentication.
        server_url:
          anyOf:
          - type: string
          - type: 'null'
          title: Server Url
          description: The server url for Jira Cloud.
        cloud_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Cloud Id
          description: The cloud ID, used in case of OAuth2.
        authentication_mechanism:
          type: string
          title: Authentication Mechanism
          description: Type of Authentication for connecting to Jira APIs.
        query:
          type: string
          title: Query
          description: JQL (Jira Query Language) query to search.
        class_name:
          type: string
          title: Class Name
          default: CloudJiraDataSource
      type: object
      required:
      - authentication_mechanism
      - query
      title: CloudJiraDataSource
      description: Cloud Jira Data Source integrating JiraReader.
    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
    CloudS3DataSource:
      properties:
        supports_access_control:
          type: boolean
          title: Supports Access Control
          default: false
        bucket:
          type: string
          title: Bucket
          description: The name of the S3 bucket to read from.
        prefix:
          anyOf:
          - type: string
          - type: 'null'
          title: Prefix
          description: The prefix of the S3 objects to read from.
        regex_pattern:
          anyOf:
          - type: string
          - type: 'null'
          title: Regex Pattern
          description: The regex pattern to filter S3 objects. Must be a valid regex pattern.
        aws_access_id:
          anyOf:
          - type: string
          - type: 'null'
          title: Aws Access Id
          description: The AWS access ID to use for authentication.
        aws_access_secret:
          anyOf:
          - type: string
            format: password
            writeOnly: true
          - type: 'null'
          title: Aws Access Secret
          description: The AWS access secret to use for authentication.
        s3_endpoint_url:
          anyOf:
          - type: string
          - type: 'null'
          title: S3 Endpoint Url
          description: The S3 endpoint URL to use for authentication.
        class_name:
          type: string
          title: Class Name
          default: CloudS3DataSource
      type: object
      required:
      - bucket
      title: CloudS3DataSource
    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
    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