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

llama_cloud/types/extraction/__init__.py

@@ -0,0 +1,25 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .extract_job import ExtractJob as ExtractJob
+from .extract_run import ExtractRun as ExtractRun
+from .extract_agent import ExtractAgent as ExtractAgent
+from .extract_config import ExtractConfig as ExtractConfig
+from .run_get_params import RunGetParams as RunGetParams
+from .job_file_params import JobFileParams as JobFileParams
+from .job_list_params import JobListParams as JobListParams
+from .run_list_params import RunListParams as RunListParams
+from .job_create_params import JobCreateParams as JobCreateParams
+from .job_list_response import JobListResponse as JobListResponse
+from .run_delete_params import RunDeleteParams as RunDeleteParams
+from .extract_config_param import ExtractConfigParam as ExtractConfigParam
+from .job_get_result_params import JobGetResultParams as JobGetResultParams
+from .run_get_by_job_params import RunGetByJobParams as RunGetByJobParams
+from .webhook_configuration import WebhookConfiguration as WebhookConfiguration
+from .job_get_result_response import JobGetResultResponse as JobGetResultResponse
+from .webhook_configuration_param import WebhookConfigurationParam as WebhookConfigurationParam
+from .extraction_agent_list_params import ExtractionAgentListParams as ExtractionAgentListParams
+from .extraction_agent_create_params import ExtractionAgentCreateParams as ExtractionAgentCreateParams
+from .extraction_agent_list_response import ExtractionAgentListResponse as ExtractionAgentListResponse
+from .extraction_agent_update_params import ExtractionAgentUpdateParams as ExtractionAgentUpdateParams

llama_cloud/types/extraction/extract_agent.py

@@ -0,0 +1,41 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Union, Optional
+from datetime import datetime
+from typing_extensions import Literal
+
+from ..._models import BaseModel
+from .extract_config import ExtractConfig
+
+__all__ = ["ExtractAgent"]
+
+
+class ExtractAgent(BaseModel):
+    """Schema and configuration for an extraction agent."""
+
+    id: str
+    """The id of the extraction agent."""
+
+    config: ExtractConfig
+    """The configuration parameters for the extraction agent."""
+
+    data_schema: Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]
+    """The schema of the data."""
+
+    name: str
+    """The name of the extraction agent."""
+
+    project_id: str
+    """The ID of the project that the extraction agent belongs to."""
+
+    created_at: Optional[datetime] = None
+    """The creation time of the extraction agent."""
+
+    custom_configuration: Optional[Literal["default"]] = None
+    """Custom configuration type for the extraction agent.
+
+    Currently supports 'default'.
+    """
+
+    updated_at: Optional[datetime] = None
+    """The last update time of the extraction agent."""

llama_cloud/types/extraction/extract_config.py

@@ -0,0 +1,118 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Union, Optional
+from typing_extensions import Literal
+
+from ..._models import BaseModel
+
+__all__ = ["ExtractConfig"]
+
+
+class ExtractConfig(BaseModel):
+    """Configuration parameters for the extraction agent."""
+
+    chunk_mode: Optional[Literal["PAGE", "SECTION"]] = None
+    """The mode to use for chunking the document."""
+
+    citation_bbox: Optional[bool] = None
+    """Whether to fetch citation bounding boxes for the extraction.
+
+    Only available in PREMIUM mode. Deprecated: this is now synonymous with
+    cite_sources.
+    """
+
+    cite_sources: Optional[bool] = None
+    """Whether to cite sources for the extraction."""
+
+    confidence_scores: Optional[bool] = None
+    """Whether to fetch confidence scores for the extraction."""
+
+    extract_model: Union[
+        Literal[
+            "openai-gpt-4-1",
+            "openai-gpt-4-1-mini",
+            "openai-gpt-4-1-nano",
+            "openai-gpt-5",
+            "openai-gpt-5-mini",
+            "gemini-2.0-flash",
+            "gemini-2.5-flash",
+            "gemini-2.5-flash-lite",
+            "gemini-2.5-pro",
+            "openai-gpt-4o",
+            "openai-gpt-4o-mini",
+        ],
+        str,
+        None,
+    ] = None
+    """The extract model to use for data extraction.
+
+    If not provided, uses the default for the extraction mode.
+    """
+
+    extraction_mode: Optional[Literal["FAST", "BALANCED", "PREMIUM", "MULTIMODAL"]] = None
+    """The extraction mode specified (FAST, BALANCED, MULTIMODAL, PREMIUM)."""
+
+    extraction_target: Optional[Literal["PER_DOC", "PER_PAGE", "PER_TABLE_ROW"]] = None
+    """The extraction target specified."""
+
+    high_resolution_mode: Optional[bool] = None
+    """Whether to use high resolution mode for the extraction."""
+
+    invalidate_cache: Optional[bool] = None
+    """Whether to invalidate the cache for the extraction."""
+
+    multimodal_fast_mode: Optional[bool] = None
+    """DEPRECATED: Whether to use fast mode for multimodal extraction."""
+
+    num_pages_context: Optional[int] = None
+    """Number of pages to pass as context on long document extraction."""
+
+    page_range: Optional[str] = None
+    """
+    Comma-separated list of page numbers or ranges to extract from (1-based, e.g.,
+    '1,3,5-7,9' or '1-3,8-10').
+    """
+
+    parse_model: Optional[
+        Literal[
+            "openai-gpt-4o",
+            "openai-gpt-4o-mini",
+            "openai-gpt-4-1",
+            "openai-gpt-4-1-mini",
+            "openai-gpt-4-1-nano",
+            "openai-gpt-5",
+            "openai-gpt-5-mini",
+            "openai-gpt-5-nano",
+            "openai-text-embedding-3-large",
+            "openai-text-embedding-3-small",
+            "openai-whisper-1",
+            "anthropic-sonnet-3.5",
+            "anthropic-sonnet-3.5-v2",
+            "anthropic-sonnet-3.7",
+            "anthropic-sonnet-4.0",
+            "anthropic-sonnet-4.5",
+            "anthropic-haiku-3.5",
+            "anthropic-haiku-4.5",
+            "gemini-2.5-flash",
+            "gemini-3.0-pro",
+            "gemini-2.5-pro",
+            "gemini-2.0-flash",
+            "gemini-2.0-flash-lite",
+            "gemini-2.5-flash-lite",
+            "gemini-1.5-flash",
+            "gemini-1.5-pro",
+        ]
+    ] = None
+    """Public model names."""
+
+    priority: Optional[Literal["low", "medium", "high", "critical"]] = None
+    """The priority for the request.
+
+    This field may be ignored or overwritten depending on the organization tier.
+    """
+
+    system_prompt: Optional[str] = None
+    """The system prompt to use for the extraction."""
+
+    use_reasoning: Optional[bool] = None
+    """Whether to use reasoning for the extraction."""

llama_cloud/types/extraction/extract_config_param.py

@@ -0,0 +1,118 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Union, Optional
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["ExtractConfigParam"]
+
+
+class ExtractConfigParam(TypedDict, total=False):
+    """Configuration parameters for the extraction agent."""
+
+    chunk_mode: Literal["PAGE", "SECTION"]
+    """The mode to use for chunking the document."""
+
+    citation_bbox: bool
+    """Whether to fetch citation bounding boxes for the extraction.
+
+    Only available in PREMIUM mode. Deprecated: this is now synonymous with
+    cite_sources.
+    """
+
+    cite_sources: bool
+    """Whether to cite sources for the extraction."""
+
+    confidence_scores: bool
+    """Whether to fetch confidence scores for the extraction."""
+
+    extract_model: Union[
+        Literal[
+            "openai-gpt-4-1",
+            "openai-gpt-4-1-mini",
+            "openai-gpt-4-1-nano",
+            "openai-gpt-5",
+            "openai-gpt-5-mini",
+            "gemini-2.0-flash",
+            "gemini-2.5-flash",
+            "gemini-2.5-flash-lite",
+            "gemini-2.5-pro",
+            "openai-gpt-4o",
+            "openai-gpt-4o-mini",
+        ],
+        str,
+        None,
+    ]
+    """The extract model to use for data extraction.
+
+    If not provided, uses the default for the extraction mode.
+    """
+
+    extraction_mode: Literal["FAST", "BALANCED", "PREMIUM", "MULTIMODAL"]
+    """The extraction mode specified (FAST, BALANCED, MULTIMODAL, PREMIUM)."""
+
+    extraction_target: Literal["PER_DOC", "PER_PAGE", "PER_TABLE_ROW"]
+    """The extraction target specified."""
+
+    high_resolution_mode: bool
+    """Whether to use high resolution mode for the extraction."""
+
+    invalidate_cache: bool
+    """Whether to invalidate the cache for the extraction."""
+
+    multimodal_fast_mode: bool
+    """DEPRECATED: Whether to use fast mode for multimodal extraction."""
+
+    num_pages_context: Optional[int]
+    """Number of pages to pass as context on long document extraction."""
+
+    page_range: Optional[str]
+    """
+    Comma-separated list of page numbers or ranges to extract from (1-based, e.g.,
+    '1,3,5-7,9' or '1-3,8-10').
+    """
+
+    parse_model: Optional[
+        Literal[
+            "openai-gpt-4o",
+            "openai-gpt-4o-mini",
+            "openai-gpt-4-1",
+            "openai-gpt-4-1-mini",
+            "openai-gpt-4-1-nano",
+            "openai-gpt-5",
+            "openai-gpt-5-mini",
+            "openai-gpt-5-nano",
+            "openai-text-embedding-3-large",
+            "openai-text-embedding-3-small",
+            "openai-whisper-1",
+            "anthropic-sonnet-3.5",
+            "anthropic-sonnet-3.5-v2",
+            "anthropic-sonnet-3.7",
+            "anthropic-sonnet-4.0",
+            "anthropic-sonnet-4.5",
+            "anthropic-haiku-3.5",
+            "anthropic-haiku-4.5",
+            "gemini-2.5-flash",
+            "gemini-3.0-pro",
+            "gemini-2.5-pro",
+            "gemini-2.0-flash",
+            "gemini-2.0-flash-lite",
+            "gemini-2.5-flash-lite",
+            "gemini-1.5-flash",
+            "gemini-1.5-pro",
+        ]
+    ]
+    """Public model names."""
+
+    priority: Optional[Literal["low", "medium", "high", "critical"]]
+    """The priority for the request.
+
+    This field may be ignored or overwritten depending on the organization tier.
+    """
+
+    system_prompt: Optional[str]
+    """The system prompt to use for the extraction."""
+
+    use_reasoning: bool
+    """Whether to use reasoning for the extraction."""

llama_cloud/types/extraction/extract_job.py

@@ -0,0 +1,32 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Optional
+from typing_extensions import Literal
+
+from ..file import File
+from ..._models import BaseModel
+from .extract_agent import ExtractAgent
+
+__all__ = ["ExtractJob"]
+
+
+class ExtractJob(BaseModel):
+    """Schema for an extraction job."""
+
+    id: str
+    """The id of the extraction job"""
+
+    extraction_agent: ExtractAgent
+    """The agent that the job was run on."""
+
+    status: Literal["PENDING", "SUCCESS", "ERROR", "PARTIAL_SUCCESS", "CANCELLED"]
+    """The status of the extraction job"""
+
+    error: Optional[str] = None
+    """The error that occurred during extraction"""
+
+    file: Optional[File] = None
+    """Schema for a file."""
+
+    file_id: Optional[str] = None
+    """The id of the file that the extract was extracted from"""

llama_cloud/types/extraction/extract_run.py

@@ -0,0 +1,64 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Union, Optional
+from datetime import datetime
+from typing_extensions import Literal
+
+from ..file import File
+from ..._models import BaseModel
+from .extract_config import ExtractConfig
+
+__all__ = ["ExtractRun"]
+
+
+class ExtractRun(BaseModel):
+    """Schema for an extraction run."""
+
+    id: str
+    """The id of the extraction run"""
+
+    config: ExtractConfig
+    """The config used for extraction"""
+
+    data_schema: Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]
+    """The schema used for extraction"""
+
+    extraction_agent_id: str
+    """The id of the extraction agent"""
+
+    from_ui: bool
+    """Whether this extraction run was triggered from the UI"""
+
+    project_id: str
+    """The id of the project that the extraction run belongs to"""
+
+    status: Literal["CREATED", "PENDING", "SUCCESS", "ERROR"]
+    """The status of the extraction run"""
+
+    created_at: Optional[datetime] = None
+    """Creation datetime"""
+
+    data: Union[
+        Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]],
+        List[Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]],
+        None,
+    ] = None
+    """The data extracted from the file"""
+
+    error: Optional[str] = None
+    """The error that occurred during extraction"""
+
+    extraction_metadata: Optional[Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]] = None
+    """The metadata extracted from the file"""
+
+    file: Optional[File] = None
+    """Schema for a file."""
+
+    file_id: Optional[str] = None
+    """The id of the file that the extract was extracted from"""
+
+    job_id: Optional[str] = None
+    """The id of the job that the extraction run belongs to"""
+
+    updated_at: Optional[datetime] = None
+    """Update datetime"""

llama_cloud/types/extraction/extraction_agent_create_params.py

@@ -0,0 +1,25 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Union, Iterable, Optional
+from typing_extensions import Required, TypedDict
+
+from .extract_config_param import ExtractConfigParam
+
+__all__ = ["ExtractionAgentCreateParams"]
+
+
+class ExtractionAgentCreateParams(TypedDict, total=False):
+    config: Required[ExtractConfigParam]
+    """The configuration parameters for the extraction agent."""
+
+    data_schema: Required[Union[Dict[str, Union[Dict[str, object], Iterable[object], str, float, bool, None]], str]]
+    """The schema of the data."""
+
+    name: Required[str]
+    """The name of the extraction schema"""
+
+    organization_id: Optional[str]
+
+    project_id: Optional[str]

llama_cloud/types/extraction/extraction_agent_list_params.py

@@ -0,0 +1,17 @@
+# 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__ = ["ExtractionAgentListParams"]
+
+
+class ExtractionAgentListParams(TypedDict, total=False):
+    include_default: bool
+    """Whether to include default agents in the results"""
+
+    organization_id: Optional[str]
+
+    project_id: Optional[str]

llama_cloud/types/extraction/extraction_agent_list_response.py

@@ -0,0 +1,10 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import List
+from typing_extensions import TypeAlias
+
+from .extract_agent import ExtractAgent
+
+__all__ = ["ExtractionAgentListResponse"]
+
+ExtractionAgentListResponse: TypeAlias = List[ExtractAgent]

llama_cloud/types/extraction/extraction_agent_update_params.py

@@ -0,0 +1,18 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Union, Iterable
+from typing_extensions import Required, TypedDict
+
+from .extract_config_param import ExtractConfigParam
+
+__all__ = ["ExtractionAgentUpdateParams"]
+
+
+class ExtractionAgentUpdateParams(TypedDict, total=False):
+    config: Required[ExtractConfigParam]
+    """The configuration parameters for the extraction agent."""
+
+    data_schema: Required[Union[Dict[str, Union[Dict[str, object], Iterable[object], str, float, bool, None]], str]]
+    """The schema of the data"""

llama_cloud/types/extraction/extraction_agents/__init__.py

@@ -0,0 +1,8 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from .schema_generate_schema_params import SchemaGenerateSchemaParams as SchemaGenerateSchemaParams
+from .schema_validate_schema_params import SchemaValidateSchemaParams as SchemaValidateSchemaParams
+from .schema_generate_schema_response import SchemaGenerateSchemaResponse as SchemaGenerateSchemaResponse
+from .schema_validate_schema_response import SchemaValidateSchemaResponse as SchemaValidateSchemaResponse

llama_cloud/types/extraction/extraction_agents/schema_generate_schema_params.py

@@ -0,0 +1,23 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Union, Iterable, Optional
+from typing_extensions import TypedDict
+
+__all__ = ["SchemaGenerateSchemaParams"]
+
+
+class SchemaGenerateSchemaParams(TypedDict, total=False):
+    organization_id: Optional[str]
+
+    project_id: Optional[str]
+
+    data_schema: Union[Dict[str, Union[Dict[str, object], Iterable[object], str, float, bool, None]], str, None]
+    """Optional schema to validate, refine, or extend during generation"""
+
+    file_id: Optional[str]
+    """Optional file ID to analyze for schema generation"""
+
+    prompt: Optional[str]
+    """Natural language description of the data structure to extract"""

llama_cloud/types/extraction/extraction_agents/schema_generate_schema_response.py

@@ -0,0 +1,14 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Union
+
+from ...._models import BaseModel
+
+__all__ = ["SchemaGenerateSchemaResponse"]
+
+
+class SchemaGenerateSchemaResponse(BaseModel):
+    """Response schema for schema generation."""
+
+    data_schema: Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]
+    """The generated JSON schema"""

llama_cloud/types/extraction/extraction_agents/schema_validate_schema_params.py

@@ -0,0 +1,12 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Union, Iterable
+from typing_extensions import Required, TypedDict
+
+__all__ = ["SchemaValidateSchemaParams"]
+
+
+class SchemaValidateSchemaParams(TypedDict, total=False):
+    data_schema: Required[Union[Dict[str, Union[Dict[str, object], Iterable[object], str, float, bool, None]], str]]

llama_cloud/types/extraction/extraction_agents/schema_validate_schema_response.py

@@ -0,0 +1,13 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Union
+
+from ...._models import BaseModel
+
+__all__ = ["SchemaValidateSchemaResponse"]
+
+
+class SchemaValidateSchemaResponse(BaseModel):
+    """Response schema for schema validation."""
+
+    data_schema: Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]

llama_cloud/types/extraction/job_create_params.py

@@ -0,0 +1,38 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Union, Iterable, Optional
+from typing_extensions import Literal, Required, TypedDict
+
+from .extract_config_param import ExtractConfigParam
+from .webhook_configuration_param import WebhookConfigurationParam
+
+__all__ = ["JobCreateParams"]
+
+
+class JobCreateParams(TypedDict, total=False):
+    extraction_agent_id: Required[str]
+    """The id of the extraction agent"""
+
+    file_id: Required[str]
+    """The id of the file"""
+
+    from_ui: bool
+
+    config_override: Optional[ExtractConfigParam]
+    """Configuration parameters for the extraction agent."""
+
+    data_schema_override: Union[
+        Dict[str, Union[Dict[str, object], Iterable[object], str, float, bool, None]], str, None
+    ]
+    """The data schema to override the extraction agent's data schema with"""
+
+    priority: Optional[Literal["low", "medium", "high", "critical"]]
+    """The priority for the request.
+
+    This field may be ignored or overwritten depending on the organization tier.
+    """
+
+    webhook_configurations: Optional[Iterable[WebhookConfigurationParam]]
+    """The outbound webhook configurations"""

llama_cloud/types/extraction/job_file_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 Required, TypedDict
+
+from ..._types import FileTypes
+
+__all__ = ["JobFileParams"]
+
+
+class JobFileParams(TypedDict, total=False):
+    extraction_agent_id: Required[str]
+    """The id of the extraction agent"""
+
+    file: Required[FileTypes]
+    """The file to run the job on"""
+
+    from_ui: bool
+
+    config_override: Optional[str]
+    """The config to override the extraction agent's config with as a JSON string"""
+
+    data_schema_override: Optional[str]
+    """
+    The data schema to override the extraction agent's data schema with as a JSON
+    string
+    """

llama_cloud/types/extraction/job_get_result_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__ = ["JobGetResultParams"]
+
+
+class JobGetResultParams(TypedDict, total=False):
+    organization_id: Optional[str]
+
+    project_id: Optional[str]

llama_cloud/types/extraction/job_get_result_response.py

@@ -0,0 +1,27 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from typing import Dict, List, Union
+
+from ..._models import BaseModel
+
+__all__ = ["JobGetResultResponse"]
+
+
+class JobGetResultResponse(BaseModel):
+    """Schema for an extraction resultset."""
+
+    data: Union[
+        Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]],
+        List[Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]],
+        None,
+    ] = None
+    """The data extracted from the file"""
+
+    extraction_agent_id: str
+    """The id of the extraction agent"""
+
+    extraction_metadata: Dict[str, Union[Dict[str, object], List[object], str, float, bool, None]]
+    """The metadata extracted from the file"""
+
+    run_id: str
+    """The id of the extraction run"""