LlamaParse Pipeline Data Sources API

openapi: 3.2.0
info:
  title: Llama Platform Agent Data Pipeline Data Sources API
  version: 0.1.0
servers:
- url: https://api.cloud.llamaindex.ai
  description: Base URL declared by the provider in apis.yml (roadmap#122).
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:
    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'
    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
    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
    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
    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
    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."
    ElementSegmentationConfig:
      properties:
        mode:
          type: string
          const: element
          title: Mode
          default: element
      type: object
      title: ElementSegmentationConfig
    NoneChunkingConfig:
      properties:
        mode:
          type: string
          const: none
          title: Mode
          default: none
      type: object
      title: NoneChunkingConfig
    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.
    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.
    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.
    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.
    ConfigurableDataSourceNames:
      type: string
      enum:
      - S3
      - AZURE_STORAGE_BLOB
      - GOOGLE_DRIVE
      - MICROSOFT_ONEDRIVE
      - MICROSOFT_SHAREPOINT
      - SLACK
      - NOTION_PAGE
      - CONFLUENCE
      - JIRA
      - JIRA_V2
      - BOX
      title: ConfigurableDataSourceNames
    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.
    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.
    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.
    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.
    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'"
    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
    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
    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
    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"
    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'
    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.
    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
    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 f

# --- truncated at 32 KB (113 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/llamaparse/refs/heads/main/openapi/llamaparse-pipeline-data-sources-api-openapi.yml