llama-cloud 0.1.41__py3-none-any.whl → 1.0.0b4__py3-none-any.whl

llama_cloud/types/beta/batch_create_params.py

@@ -0,0 +1,399 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, List, Union, Iterable, Optional
+from typing_extensions import Literal, Required, Annotated, TypeAlias, TypedDict
+
+from ..._types import SequenceNotStr
+from ..._utils import PropertyInfo
+from ..parsing_mode import ParsingMode
+from ..fail_page_mode import FailPageMode
+from ..parsing_languages import ParsingLanguages
+from ..classifier.classify_job_param import ClassifyJobParam
+from ..extraction.webhook_configuration_param import WebhookConfigurationParam
+
+__all__ = [
+    "BatchCreateParams",
+    "JobConfig",
+    "JobConfigBatchParseJobRecordCreate",
+    "JobConfigBatchParseJobRecordCreateParameters",
+]
+
+
+class BatchCreateParams(TypedDict, total=False):
+    job_config: Required[JobConfig]
+    """Job configuration for batch processing.
+
+    Can be BatchParseJobRecordCreate or ClassifyJob.
+    """
+
+    organization_id: Optional[str]
+
+    project_id: Optional[str]
+
+    continue_as_new_threshold: Optional[int]
+    """Maximum number of files to process before calling continue-as-new.
+
+    If None, continue-as-new is called after every batch. (only used in directory
+    mode)
+    """
+
+    directory_id: Optional[str]
+    """ID of the directory containing files to process"""
+
+    item_ids: Optional[SequenceNotStr[str]]
+    """List of specific item IDs to process.
+
+    Either this or directory_id must be provided.
+    """
+
+    page_size: int
+    """
+    Number of files to fetch per batch from the directory (only used in directory
+    mode)
+    """
+
+    temporal_namespace: Annotated[str, PropertyInfo(alias="temporal-namespace")]
+
+
+class JobConfigBatchParseJobRecordCreateParameters(TypedDict, total=False):
+    """Generic parse job configuration for batch processing.
+
+    This model contains the parsing configuration that applies to all files
+    in a batch, but excludes file-specific fields like file_name, file_id, etc.
+    Those file-specific fields are populated from DirectoryFile data when
+    creating individual ParseJobRecordCreate instances for each file.
+
+    The fields in this model should be generic settings that apply uniformly
+    to all files being processed in the batch.
+    """
+
+    adaptive_long_table: Optional[bool]
+
+    aggressive_table_extraction: Optional[bool]
+
+    annotate_links: Optional[bool]
+
+    auto_mode: Optional[bool]
+
+    auto_mode_configuration_json: Optional[str]
+
+    auto_mode_trigger_on_image_in_page: Optional[bool]
+
+    auto_mode_trigger_on_regexp_in_page: Optional[str]
+
+    auto_mode_trigger_on_table_in_page: Optional[bool]
+
+    auto_mode_trigger_on_text_in_page: Optional[str]
+
+    azure_openai_api_version: Optional[str]
+
+    azure_openai_deployment_name: Optional[str]
+
+    azure_openai_endpoint: Optional[str]
+
+    azure_openai_key: Optional[str]
+
+    bbox_bottom: Optional[float]
+
+    bbox_left: Optional[float]
+
+    bbox_right: Optional[float]
+
+    bbox_top: Optional[float]
+
+    bounding_box: Optional[str]
+
+    compact_markdown_table: Optional[bool]
+
+    complemental_formatting_instruction: Optional[str]
+
+    content_guideline_instruction: Optional[str]
+
+    continuous_mode: Optional[bool]
+
+    custom_metadata: Optional[Dict[str, object]]
+    """The custom metadata to attach to the documents."""
+
+    disable_image_extraction: Optional[bool]
+
+    disable_ocr: Optional[bool]
+
+    disable_reconstruction: Optional[bool]
+
+    do_not_cache: Optional[bool]
+
+    do_not_unroll_columns: Optional[bool]
+
+    extract_charts: Optional[bool]
+
+    extract_layout: Optional[bool]
+
+    extract_printed_page_number: Optional[bool]
+
+    fast_mode: Optional[bool]
+
+    formatting_instruction: Optional[str]
+
+    gpt4o_api_key: Optional[str]
+
+    gpt4o_mode: Optional[bool]
+
+    guess_xlsx_sheet_name: Optional[bool]
+
+    hide_footers: Optional[bool]
+
+    hide_headers: Optional[bool]
+
+    high_res_ocr: Optional[bool]
+
+    html_make_all_elements_visible: Optional[bool]
+
+    html_remove_fixed_elements: Optional[bool]
+
+    html_remove_navigation_elements: Optional[bool]
+
+    http_proxy: Optional[str]
+
+    ignore_document_elements_for_layout_detection: Optional[bool]
+
+    images_to_save: Optional[List[Literal["screenshot", "embedded", "layout"]]]
+
+    inline_images_in_markdown: Optional[bool]
+
+    input_s3_path: Optional[str]
+
+    input_s3_region: Optional[str]
+    """The region for the input S3 bucket."""
+
+    input_url: Optional[str]
+
+    internal_is_screenshot_job: Optional[bool]
+
+    invalidate_cache: Optional[bool]
+
+    is_formatting_instruction: Optional[bool]
+
+    job_timeout_extra_time_per_page_in_seconds: Optional[float]
+
+    job_timeout_in_seconds: Optional[float]
+
+    keep_page_separator_when_merging_tables: Optional[bool]
+
+    lang: str
+    """The language."""
+
+    languages: List[ParsingLanguages]
+
+    layout_aware: Optional[bool]
+
+    line_level_bounding_box: Optional[bool]
+
+    markdown_table_multiline_header_separator: Optional[str]
+
+    max_pages: Optional[int]
+
+    max_pages_enforced: Optional[int]
+
+    merge_tables_across_pages_in_markdown: Optional[bool]
+
+    model: Optional[str]
+
+    outlined_table_extraction: Optional[bool]
+
+    output_pdf_of_document: Optional[bool]
+
+    output_s3_path_prefix: Optional[str]
+    """If specified, llamaParse will save the output to the specified path.
+
+    All output file will use this 'prefix' should be a valid s3:// url
+    """
+
+    output_s3_region: Optional[str]
+    """The region for the output S3 bucket."""
+
+    output_tables_as_html: Annotated[Optional[bool], PropertyInfo(alias="output_tables_as_HTML")]
+
+    output_bucket: Annotated[Optional[str], PropertyInfo(alias="outputBucket")]
+    """The output bucket."""
+
+    page_error_tolerance: Optional[float]
+
+    page_footer_prefix: Optional[str]
+
+    page_footer_suffix: Optional[str]
+
+    page_header_prefix: Optional[str]
+
+    page_header_suffix: Optional[str]
+
+    page_prefix: Optional[str]
+
+    page_separator: Optional[str]
+
+    page_suffix: Optional[str]
+
+    parse_mode: Optional[ParsingMode]
+    """Enum for representing the mode of parsing to be used."""
+
+    parsing_instruction: Optional[str]
+
+    pipeline_id: Optional[str]
+    """The pipeline ID."""
+
+    precise_bounding_box: Optional[bool]
+
+    premium_mode: Optional[bool]
+
+    presentation_out_of_bounds_content: Optional[bool]
+
+    presentation_skip_embedded_data: Optional[bool]
+
+    preserve_layout_alignment_across_pages: Optional[bool]
+
+    preserve_very_small_text: Optional[bool]
+
+    preset: Optional[str]
+
+    priority: Optional[Literal["low", "medium", "high", "critical"]]
+    """The priority for the request.
+
+    This field may be ignored or overwritten depending on the organization tier.
+    """
+
+    project_id: Optional[str]
+
+    remove_hidden_text: Optional[bool]
+
+    replace_failed_page_mode: Optional[FailPageMode]
+    """Enum for representing the different available page error handling modes."""
+
+    replace_failed_page_with_error_message_prefix: Optional[str]
+
+    replace_failed_page_with_error_message_suffix: Optional[str]
+
+    resource_info: Optional[Dict[str, object]]
+    """The resource info about the file"""
+
+    save_images: Optional[bool]
+
+    skip_diagonal_text: Optional[bool]
+
+    specialized_chart_parsing_agentic: Optional[bool]
+
+    specialized_chart_parsing_efficient: Optional[bool]
+
+    specialized_chart_parsing_plus: Optional[bool]
+
+    specialized_image_parsing: Optional[bool]
+
+    spreadsheet_extract_sub_tables: Optional[bool]
+
+    spreadsheet_force_formula_computation: Optional[bool]
+
+    strict_mode_buggy_font: Optional[bool]
+
+    strict_mode_image_extraction: Optional[bool]
+
+    strict_mode_image_ocr: Optional[bool]
+
+    strict_mode_reconstruction: Optional[bool]
+
+    structured_output: Optional[bool]
+
+    structured_output_json_schema: Optional[str]
+
+    structured_output_json_schema_name: Optional[str]
+
+    system_prompt: Optional[str]
+
+    system_prompt_append: Optional[str]
+
+    take_screenshot: Optional[bool]
+
+    target_pages: Optional[str]
+
+    tier: Optional[str]
+
+    type: Literal["parse"]
+
+    use_vendor_multimodal_model: Optional[bool]
+
+    user_prompt: Optional[str]
+
+    vendor_multimodal_api_key: Optional[str]
+
+    vendor_multimodal_model_name: Optional[str]
+
+    version: Optional[str]
+
+    webhook_configurations: Optional[Iterable[WebhookConfigurationParam]]
+    """The outbound webhook configurations"""
+
+    webhook_url: Optional[str]
+
+
+class JobConfigBatchParseJobRecordCreate(TypedDict, total=False):
+    """Batch-specific parse job record for batch processing.
+
+    This model contains the metadata and configuration for a batch parse job,
+    but excludes file-specific information. It's used as input to the batch
+    parent workflow and combined with DirectoryFile data to create full
+    ParseJobRecordCreate instances for each file.
+
+    Attributes:
+        job_name: Must be PARSE_RAW_FILE
+        partitions: Partitions for job output location
+        parameters: Generic parse configuration (BatchParseJobConfig)
+        session_id: Upstream request ID for tracking
+        correlation_id: Correlation ID for cross-service tracking
+        parent_job_execution_id: Parent job execution ID if nested
+        user_id: User who created the job
+        project_id: Project this job belongs to
+        webhook_url: Optional webhook URL for job completion notifications
+    """
+
+    correlation_id: Optional[str]
+    """The correlation ID for this job. Used for tracking the job across services."""
+
+    job_name: Literal["parse_raw_file_job"]
+
+    parameters: Optional[JobConfigBatchParseJobRecordCreateParameters]
+    """Generic parse job configuration for batch processing.
+
+    This model contains the parsing configuration that applies to all files in a
+    batch, but excludes file-specific fields like file_name, file_id, etc. Those
+    file-specific fields are populated from DirectoryFile data when creating
+    individual ParseJobRecordCreate instances for each file.
+
+    The fields in this model should be generic settings that apply uniformly to all
+    files being processed in the batch.
+    """
+
+    parent_job_execution_id: Optional[str]
+    """The ID of the parent job execution."""
+
+    partitions: Dict[str, str]
+    """The partitions for this execution.
+
+    Used for determining where to save job output.
+    """
+
+    project_id: Optional[str]
+    """The ID of the project this job belongs to."""
+
+    session_id: Optional[str]
+    """The upstream request ID that created this job.
+
+    Used for tracking the job across services.
+    """
+
+    user_id: Optional[str]
+    """The ID of the user that created this job"""
+
+    webhook_url: Optional[str]
+    """The URL that needs to be called at the end of the parsing job."""
+
+
+JobConfig: TypeAlias = Union[JobConfigBatchParseJobRecordCreate, ClassifyJobParam]

llama_cloud/types/beta/batch_create_response.py

@@ -0,0 +1,63 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from datetime import datetime
+from typing_extensions import Literal
+
+from ..._models import BaseModel
+
+__all__ = ["BatchCreateResponse"]
+
+
+class BatchCreateResponse(BaseModel):
+    """Response schema for a batch processing job."""
+
+    id: str
+    """Unique identifier for the batch job"""
+
+    job_type: Literal["parse", "extract", "classify"]
+    """Type of processing operation"""
+
+    project_id: str
+    """Project this job belongs to"""
+
+    status: Literal["pending", "running", "dispatched", "completed", "failed", "cancelled"]
+    """Current status of the job"""
+
+    total_items: int
+    """Total number of items in the job"""
+
+    completed_at: Optional[datetime] = None
+    """Timestamp when job completed"""
+
+    created_at: Optional[datetime] = None
+    """Creation datetime"""
+
+    directory_id: Optional[str] = None
+    """Directory being processed"""
+
+    effective_at: Optional[datetime] = None
+
+    error_message: Optional[str] = None
+    """Error message for the latest job attempt, if any."""
+
+    failed_items: Optional[int] = None
+    """Number of items that failed processing"""
+
+    job_record_id: Optional[str] = None
+    """The job record ID associated with this status, if any."""
+
+    processed_items: Optional[int] = None
+    """Number of items processed so far"""
+
+    skipped_items: Optional[int] = None
+    """Number of items skipped (already processed or size limit)"""
+
+    started_at: Optional[datetime] = None
+    """Timestamp when job processing started"""
+
+    updated_at: Optional[datetime] = None
+    """Update datetime"""
+
+    workflow_id: Optional[str] = None
+    """Temporal workflow ID for this batch job"""

llama_cloud/types/beta/batch_get_status_params.py

@@ -0,0 +1,14 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import TypedDict
+
+__all__ = ["BatchGetStatusParams"]
+
+
+class BatchGetStatusParams(TypedDict, total=False):
+    organization_id: Optional[str]
+
+    project_id: Optional[str]

llama_cloud/types/beta/batch_get_status_response.py

@@ -0,0 +1,73 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from datetime import datetime
+from typing_extensions import Literal
+
+from ..._models import BaseModel
+
+__all__ = ["BatchGetStatusResponse", "Job"]
+
+
+class Job(BaseModel):
+    """Response schema for a batch processing job."""
+
+    id: str
+    """Unique identifier for the batch job"""
+
+    job_type: Literal["parse", "extract", "classify"]
+    """Type of processing operation"""
+
+    project_id: str
+    """Project this job belongs to"""
+
+    status: Literal["pending", "running", "dispatched", "completed", "failed", "cancelled"]
+    """Current status of the job"""
+
+    total_items: int
+    """Total number of items in the job"""
+
+    completed_at: Optional[datetime] = None
+    """Timestamp when job completed"""
+
+    created_at: Optional[datetime] = None
+    """Creation datetime"""
+
+    directory_id: Optional[str] = None
+    """Directory being processed"""
+
+    effective_at: Optional[datetime] = None
+
+    error_message: Optional[str] = None
+    """Error message for the latest job attempt, if any."""
+
+    failed_items: Optional[int] = None
+    """Number of items that failed processing"""
+
+    job_record_id: Optional[str] = None
+    """The job record ID associated with this status, if any."""
+
+    processed_items: Optional[int] = None
+    """Number of items processed so far"""
+
+    skipped_items: Optional[int] = None
+    """Number of items skipped (already processed or size limit)"""
+
+    started_at: Optional[datetime] = None
+    """Timestamp when job processing started"""
+
+    updated_at: Optional[datetime] = None
+    """Update datetime"""
+
+    workflow_id: Optional[str] = None
+    """Temporal workflow ID for this batch job"""
+
+
+class BatchGetStatusResponse(BaseModel):
+    """Detailed status response for a batch processing job."""
+
+    job: Job
+    """Response schema for a batch processing job."""
+
+    progress_percentage: float
+    """Percentage of items processed (0-100)"""

llama_cloud/types/beta/batch_list_params.py

@@ -0,0 +1,29 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["BatchListParams"]
+
+
+class BatchListParams(TypedDict, total=False):
+    directory_id: Optional[str]
+    """Filter by directory ID"""
+
+    job_type: Optional[Literal["parse", "extract", "classify"]]
+    """Type of batch processing operation."""
+
+    limit: int
+    """Maximum number of jobs to return"""
+
+    offset: int
+    """Number of jobs to skip for pagination"""
+
+    organization_id: Optional[str]
+
+    project_id: Optional[str]
+
+    status: Optional[Literal["pending", "running", "dispatched", "completed", "failed", "cancelled"]]
+    """Status of a batch processing job."""

llama_cloud/types/beta/batch_list_response.py

@@ -0,0 +1,63 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from datetime import datetime
+from typing_extensions import Literal
+
+from ..._models import BaseModel
+
+__all__ = ["BatchListResponse"]
+
+
+class BatchListResponse(BaseModel):
+    """Response schema for a batch processing job."""
+
+    id: str
+    """Unique identifier for the batch job"""
+
+    job_type: Literal["parse", "extract", "classify"]
+    """Type of processing operation"""
+
+    project_id: str
+    """Project this job belongs to"""
+
+    status: Literal["pending", "running", "dispatched", "completed", "failed", "cancelled"]
+    """Current status of the job"""
+
+    total_items: int
+    """Total number of items in the job"""
+
+    completed_at: Optional[datetime] = None
+    """Timestamp when job completed"""
+
+    created_at: Optional[datetime] = None
+    """Creation datetime"""
+
+    directory_id: Optional[str] = None
+    """Directory being processed"""
+
+    effective_at: Optional[datetime] = None
+
+    error_message: Optional[str] = None
+    """Error message for the latest job attempt, if any."""
+
+    failed_items: Optional[int] = None
+    """Number of items that failed processing"""
+
+    job_record_id: Optional[str] = None
+    """The job record ID associated with this status, if any."""
+
+    processed_items: Optional[int] = None
+    """Number of items processed so far"""
+
+    skipped_items: Optional[int] = None
+    """Number of items skipped (already processed or size limit)"""
+
+    started_at: Optional[datetime] = None
+    """Timestamp when job processing started"""
+
+    updated_at: Optional[datetime] = None
+    """Update datetime"""
+
+    workflow_id: Optional[str] = None
+    """Temporal workflow ID for this batch job"""

llama_cloud/types/beta/directories/__init__.py

@@ -0,0 +1,15 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .file_add_params import FileAddParams as FileAddParams
+from .file_get_params import FileGetParams as FileGetParams
+from .file_list_params import FileListParams as FileListParams
+from .file_add_response import FileAddResponse as FileAddResponse
+from .file_get_response import FileGetResponse as FileGetResponse
+from .file_delete_params import FileDeleteParams as FileDeleteParams
+from .file_list_response import FileListResponse as FileListResponse
+from .file_update_params import FileUpdateParams as FileUpdateParams
+from .file_upload_params import FileUploadParams as FileUploadParams
+from .file_update_response import FileUpdateResponse as FileUpdateResponse
+from .file_upload_response import FileUploadResponse as FileUploadResponse

llama_cloud/types/beta/directories/file_add_params.py

@@ -0,0 +1,26 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+__all__ = ["FileAddParams"]
+
+
+class FileAddParams(TypedDict, total=False):
+    file_id: Required[str]
+    """File ID for the storage location (required)."""
+
+    organization_id: Optional[str]
+
+    project_id: Optional[str]
+
+    display_name: Optional[str]
+    """Display name for the file. If not provided, will use the file's name."""
+
+    unique_id: Optional[str]
+    """Unique identifier for the file in the directory.
+
+    If not provided, will use the file's external_file_id or name.
+    """