llama-cloud 0.1.18__py3-none-any.whl → 0.1.19__py3-none-any.whl

llama_cloud/resources/parsing/client.py

@@ -9,6 +9,7 @@ from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from ...core.jsonable_encoder import jsonable_encoder
 from ...core.remove_none_from_dict import remove_none_from_dict
 from ...errors.unprocessable_entity_error import UnprocessableEntityError
+from ...types.fail_page_mode import FailPageMode
 from ...types.http_validation_error import HttpValidationError
 from ...types.llama_parse_supported_file_extensions import LlamaParseSupportedFileExtensions
 from ...types.parser_languages import ParserLanguages
@@ -250,6 +251,10 @@ class ParsingClient:
         webhook_url: str,
         preset: str,
         parse_mode: typing.Optional[ParsingMode] = OMIT,
+        page_error_tolerance: float,
+        replace_failed_page_mode: typing.Optional[FailPageMode] = OMIT,
+        replace_failed_page_with_error_message_prefix: str,
+        replace_failed_page_with_error_message_suffix: str,
         system_prompt: str,
         system_prompt_append: str,
         user_prompt: str,
@@ -259,8 +264,10 @@ class ParsingClient:
         strict_mode_image_ocr: bool,
         strict_mode_reconstruction: bool,
         strict_mode_buggy_font: bool,
+        save_images: bool,
         ignore_document_elements_for_layout_detection: bool,
         output_tables_as_html: bool,
+        markdown_table_multiline_header_separator: str,
         use_vendor_multimodal_model: bool,
         bounding_box: str,
         gpt_4_o_mode: bool,
@@ -275,8 +282,6 @@ class ParsingClient:
         formatting_instruction: str,
     ) -> ParsingJob:
         """
-        Upload a file to s3 and create a job. return a job id
-
         Parameters:
             - organization_id: typing.Optional[str].
 
@@ -392,6 +397,14 @@ class ParsingClient:
 
             - parse_mode: typing.Optional[ParsingMode].
 
+            - page_error_tolerance: float.
+
+            - replace_failed_page_mode: typing.Optional[FailPageMode].
+
+            - replace_failed_page_with_error_message_prefix: str.
+
+            - replace_failed_page_with_error_message_suffix: str.
+
             - system_prompt: str.
 
             - system_prompt_append: str.
@@ -410,10 +423,14 @@ class ParsingClient:
 
             - strict_mode_buggy_font: bool.
 
+            - save_images: bool.
+
             - ignore_document_elements_for_layout_detection: bool.
 
             - output_tables_as_html: bool.
 
+            - markdown_table_multiline_header_separator: str.
+
             - use_vendor_multimodal_model: bool.
 
             - bounding_box: str.
@@ -491,6 +508,9 @@ class ParsingClient:
             "model": model,
             "webhook_url": webhook_url,
             "preset": preset,
+            "page_error_tolerance": page_error_tolerance,
+            "replace_failed_page_with_error_message_prefix": replace_failed_page_with_error_message_prefix,
+            "replace_failed_page_with_error_message_suffix": replace_failed_page_with_error_message_suffix,
             "system_prompt": system_prompt,
             "system_prompt_append": system_prompt_append,
             "user_prompt": user_prompt,
@@ -500,8 +520,10 @@ class ParsingClient:
             "strict_mode_image_ocr": strict_mode_image_ocr,
             "strict_mode_reconstruction": strict_mode_reconstruction,
             "strict_mode_buggy_font": strict_mode_buggy_font,
+            "save_images": save_images,
             "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
             "output_tables_as_HTML": output_tables_as_html,
+            "markdown_table_multiline_header_separator": markdown_table_multiline_header_separator,
             "use_vendor_multimodal_model": use_vendor_multimodal_model,
             "bounding_box": bounding_box,
             "gpt4o_mode": gpt_4_o_mode,
@@ -521,6 +543,8 @@ class ParsingClient:
             _request["max_pages"] = max_pages
         if parse_mode is not OMIT:
             _request["parse_mode"] = parse_mode
+        if replace_failed_page_mode is not OMIT:
+            _request["replace_failed_page_mode"] = replace_failed_page_mode
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
@@ -571,6 +595,38 @@ class ParsingClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def get_job_parameters(self, job_id: str) -> typing.Any:
+        """
+        Get a job by id
+
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.parsing.get_job_parameters(
+            job_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/parameters"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.Any, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     def get_parsing_job_details(self, job_id: str) -> typing.Any:
         """
         Get a job by id
@@ -1202,6 +1258,10 @@ class AsyncParsingClient:
         webhook_url: str,
         preset: str,
         parse_mode: typing.Optional[ParsingMode] = OMIT,
+        page_error_tolerance: float,
+        replace_failed_page_mode: typing.Optional[FailPageMode] = OMIT,
+        replace_failed_page_with_error_message_prefix: str,
+        replace_failed_page_with_error_message_suffix: str,
         system_prompt: str,
         system_prompt_append: str,
         user_prompt: str,
@@ -1211,8 +1271,10 @@ class AsyncParsingClient:
         strict_mode_image_ocr: bool,
         strict_mode_reconstruction: bool,
         strict_mode_buggy_font: bool,
+        save_images: bool,
         ignore_document_elements_for_layout_detection: bool,
         output_tables_as_html: bool,
+        markdown_table_multiline_header_separator: str,
         use_vendor_multimodal_model: bool,
         bounding_box: str,
         gpt_4_o_mode: bool,
@@ -1227,8 +1289,6 @@ class AsyncParsingClient:
         formatting_instruction: str,
     ) -> ParsingJob:
         """
-        Upload a file to s3 and create a job. return a job id
-
         Parameters:
             - organization_id: typing.Optional[str].
 
@@ -1344,6 +1404,14 @@ class AsyncParsingClient:
 
             - parse_mode: typing.Optional[ParsingMode].
 
+            - page_error_tolerance: float.
+
+            - replace_failed_page_mode: typing.Optional[FailPageMode].
+
+            - replace_failed_page_with_error_message_prefix: str.
+
+            - replace_failed_page_with_error_message_suffix: str.
+
             - system_prompt: str.
 
             - system_prompt_append: str.
@@ -1362,10 +1430,14 @@ class AsyncParsingClient:
 
             - strict_mode_buggy_font: bool.
 
+            - save_images: bool.
+
             - ignore_document_elements_for_layout_detection: bool.
 
             - output_tables_as_html: bool.
 
+            - markdown_table_multiline_header_separator: str.
+
             - use_vendor_multimodal_model: bool.
 
             - bounding_box: str.
@@ -1443,6 +1515,9 @@ class AsyncParsingClient:
             "model": model,
             "webhook_url": webhook_url,
             "preset": preset,
+            "page_error_tolerance": page_error_tolerance,
+            "replace_failed_page_with_error_message_prefix": replace_failed_page_with_error_message_prefix,
+            "replace_failed_page_with_error_message_suffix": replace_failed_page_with_error_message_suffix,
             "system_prompt": system_prompt,
             "system_prompt_append": system_prompt_append,
             "user_prompt": user_prompt,
@@ -1452,8 +1527,10 @@ class AsyncParsingClient:
             "strict_mode_image_ocr": strict_mode_image_ocr,
             "strict_mode_reconstruction": strict_mode_reconstruction,
             "strict_mode_buggy_font": strict_mode_buggy_font,
+            "save_images": save_images,
             "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
             "output_tables_as_HTML": output_tables_as_html,
+            "markdown_table_multiline_header_separator": markdown_table_multiline_header_separator,
             "use_vendor_multimodal_model": use_vendor_multimodal_model,
             "bounding_box": bounding_box,
             "gpt4o_mode": gpt_4_o_mode,
@@ -1473,6 +1550,8 @@ class AsyncParsingClient:
             _request["max_pages"] = max_pages
         if parse_mode is not OMIT:
             _request["parse_mode"] = parse_mode
+        if replace_failed_page_mode is not OMIT:
+            _request["replace_failed_page_mode"] = replace_failed_page_mode
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
@@ -1523,6 +1602,38 @@ class AsyncParsingClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def get_job_parameters(self, job_id: str) -> typing.Any:
+        """
+        Get a job by id
+
+        Parameters:
+            - job_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.parsing.get_job_parameters(
+            job_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/parsing/job/{job_id}/parameters"),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.Any, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     async def get_parsing_job_details(self, job_id: str) -> typing.Any:
         """
         Get a job by id

llama_cloud/resources/pipelines/client.py

@@ -15,6 +15,7 @@ from ...types.cloud_document_create import CloudDocumentCreate
 from ...types.configured_transformation_item import ConfiguredTransformationItem
 from ...types.data_sink_create import DataSinkCreate
 from ...types.eval_execution_params import EvalExecutionParams
+from ...types.file_count_by_status_response import FileCountByStatusResponse
 from ...types.http_validation_error import HttpValidationError
 from ...types.input_message import InputMessage
 from ...types.llama_parse_parameters import LlamaParseParameters
@@ -216,6 +217,7 @@ class PipelinesClient:
         preset_retrieval_parameters: typing.Optional[PresetRetrievalParams] = OMIT,
         eval_parameters: typing.Optional[EvalExecutionParams] = OMIT,
         llama_parse_parameters: typing.Optional[LlamaParseParameters] = OMIT,
+        status: typing.Optional[str] = OMIT,
         name: typing.Optional[str] = OMIT,
         managed_pipeline_id: typing.Optional[str] = OMIT,
     ) -> Pipeline:
@@ -243,6 +245,8 @@ class PipelinesClient:
 
             - llama_parse_parameters: typing.Optional[LlamaParseParameters].
 
+            - status: typing.Optional[str].
+
             - name: typing.Optional[str].
 
             - managed_pipeline_id: typing.Optional[str].
@@ -266,6 +270,8 @@ class PipelinesClient:
             _request["eval_parameters"] = eval_parameters
         if llama_parse_parameters is not OMIT:
             _request["llama_parse_parameters"] = llama_parse_parameters
+        if status is not OMIT:
+            _request["status"] = status
         if name is not OMIT:
             _request["name"] = name
         if managed_pipeline_id is not OMIT:
@@ -559,6 +565,53 @@ class PipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def get_pipeline_file_status_counts(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: typing.Optional[str] = None,
+        only_manually_uploaded: typing.Optional[bool] = None,
+    ) -> FileCountByStatusResponse:
+        """
+        Get files for a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - data_source_id: typing.Optional[str].
+
+            - only_manually_uploaded: typing.Optional[bool].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.pipelines.get_pipeline_file_status_counts(
+            pipeline_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/files/status-counts"
+            ),
+            params=remove_none_from_dict(
+                {"data_source_id": data_source_id, "only_manually_uploaded": only_manually_uploaded}
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(FileCountByStatusResponse, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     def get_pipeline_file_status(self, file_id: str, pipeline_id: str) -> ManagedIngestionStatusResponse:
         """
         Get status of a file for a pipeline.
@@ -1771,6 +1824,7 @@ class AsyncPipelinesClient:
         preset_retrieval_parameters: typing.Optional[PresetRetrievalParams] = OMIT,
         eval_parameters: typing.Optional[EvalExecutionParams] = OMIT,
         llama_parse_parameters: typing.Optional[LlamaParseParameters] = OMIT,
+        status: typing.Optional[str] = OMIT,
         name: typing.Optional[str] = OMIT,
         managed_pipeline_id: typing.Optional[str] = OMIT,
     ) -> Pipeline:
@@ -1798,6 +1852,8 @@ class AsyncPipelinesClient:
 
             - llama_parse_parameters: typing.Optional[LlamaParseParameters].
 
+            - status: typing.Optional[str].
+
             - name: typing.Optional[str].
 
             - managed_pipeline_id: typing.Optional[str].
@@ -1821,6 +1877,8 @@ class AsyncPipelinesClient:
             _request["eval_parameters"] = eval_parameters
         if llama_parse_parameters is not OMIT:
             _request["llama_parse_parameters"] = llama_parse_parameters
+        if status is not OMIT:
+            _request["status"] = status
         if name is not OMIT:
             _request["name"] = name
         if managed_pipeline_id is not OMIT:
@@ -2114,6 +2172,53 @@ class AsyncPipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def get_pipeline_file_status_counts(
+        self,
+        pipeline_id: str,
+        *,
+        data_source_id: typing.Optional[str] = None,
+        only_manually_uploaded: typing.Optional[bool] = None,
+    ) -> FileCountByStatusResponse:
+        """
+        Get files for a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - data_source_id: typing.Optional[str].
+
+            - only_manually_uploaded: typing.Optional[bool].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.pipelines.get_pipeline_file_status_counts(
+            pipeline_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/files/status-counts"
+            ),
+            params=remove_none_from_dict(
+                {"data_source_id": data_source_id, "only_manually_uploaded": only_manually_uploaded}
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(FileCountByStatusResponse, _response.json())  # type: ignore
+        if _response.status_code == 422:
+            raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
+        try:
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     async def get_pipeline_file_status(self, file_id: str, pipeline_id: str) -> ManagedIngestionStatusResponse:
         """
         Get status of a file for a pipeline.

llama_cloud/types/__init__.py

@@ -16,6 +16,7 @@ from .advanced_mode_transform_config_segmentation_config import (
     AdvancedModeTransformConfigSegmentationConfig_Page,
 )
 from .app_schema_chat_chat_message import AppSchemaChatChatMessage
+from .audio_block import AudioBlock
 from .auto_transform_config import AutoTransformConfig
 from .azure_open_ai_embedding import AzureOpenAiEmbedding
 from .azure_open_ai_embedding_config import AzureOpenAiEmbeddingConfig
@@ -24,6 +25,10 @@ from .base_plan_metronome_plan_type import BasePlanMetronomePlanType
 from .base_plan_name import BasePlanName
 from .base_plan_plan_frequency import BasePlanPlanFrequency
 from .base_prompt_template import BasePromptTemplate
+from .batch import Batch
+from .batch_item import BatchItem
+from .batch_paginated_list import BatchPaginatedList
+from .batch_public_output import BatchPublicOutput
 from .bedrock_embedding import BedrockEmbedding
 from .bedrock_embedding_config import BedrockEmbeddingConfig
 from .billing_period import BillingPeriod
@@ -105,19 +110,10 @@ from .embedding_model_config_update_embedding_config import (
 )
 from .eval_execution_params import EvalExecutionParams
 from .extract_agent import ExtractAgent
-from .extract_agent_create import ExtractAgentCreate
-from .extract_agent_create_data_schema import ExtractAgentCreateDataSchema
-from .extract_agent_create_data_schema_zero_value import ExtractAgentCreateDataSchemaZeroValue
 from .extract_agent_data_schema_value import ExtractAgentDataSchemaValue
-from .extract_agent_update import ExtractAgentUpdate
-from .extract_agent_update_data_schema import ExtractAgentUpdateDataSchema
-from .extract_agent_update_data_schema_zero_value import ExtractAgentUpdateDataSchemaZeroValue
 from .extract_config import ExtractConfig
 from .extract_job import ExtractJob
 from .extract_job_create import ExtractJobCreate
-from .extract_job_create_batch import ExtractJobCreateBatch
-from .extract_job_create_batch_data_schema_override import ExtractJobCreateBatchDataSchemaOverride
-from .extract_job_create_batch_data_schema_override_zero_value import ExtractJobCreateBatchDataSchemaOverrideZeroValue
 from .extract_job_create_data_schema_override import ExtractJobCreateDataSchemaOverride
 from .extract_job_create_data_schema_override_zero_value import ExtractJobCreateDataSchemaOverrideZeroValue
 from .extract_mode import ExtractMode
@@ -132,14 +128,14 @@ from .extract_run_data_item_value import ExtractRunDataItemValue
 from .extract_run_data_schema_value import ExtractRunDataSchemaValue
 from .extract_run_data_zero_value import ExtractRunDataZeroValue
 from .extract_run_extraction_metadata_value import ExtractRunExtractionMetadataValue
-from .extract_schema_validate_request import ExtractSchemaValidateRequest
-from .extract_schema_validate_request_data_schema import ExtractSchemaValidateRequestDataSchema
-from .extract_schema_validate_request_data_schema_zero_value import ExtractSchemaValidateRequestDataSchemaZeroValue
 from .extract_schema_validate_response import ExtractSchemaValidateResponse
 from .extract_schema_validate_response_data_schema_value import ExtractSchemaValidateResponseDataSchemaValue
 from .extract_state import ExtractState
 from .extract_target import ExtractTarget
+from .fail_page_mode import FailPageMode
 from .file import File
+from .file_count_by_status_response import FileCountByStatusResponse
+from .file_parse_public import FileParsePublic
 from .file_permission_info_value import FilePermissionInfoValue
 from .file_resource_info_value import FileResourceInfoValue
 from .filter_condition import FilterCondition
@@ -162,6 +158,7 @@ from .llama_extract_settings import LlamaExtractSettings
 from .llama_index_core_base_llms_types_chat_message import LlamaIndexCoreBaseLlmsTypesChatMessage
 from .llama_index_core_base_llms_types_chat_message_blocks_item import (
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem,
+    LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Audio,
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image,
     LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text,
 )
@@ -210,6 +207,9 @@ from .parsing_job_text_result import ParsingJobTextResult
 from .parsing_mode import ParsingMode
 from .partition_names import PartitionNames
 from .permission import Permission
+from .pg_vector_distance_method import PgVectorDistanceMethod
+from .pg_vector_hnsw_settings import PgVectorHnswSettings
+from .pg_vector_vector_type import PgVectorVectorType
 from .pipeline import Pipeline
 from .pipeline_configuration_hashes import PipelineConfigurationHashes
 from .pipeline_create import PipelineCreate
@@ -228,6 +228,7 @@ from .pipeline_data_source import PipelineDataSource
 from .pipeline_data_source_component import PipelineDataSourceComponent
 from .pipeline_data_source_create import PipelineDataSourceCreate
 from .pipeline_data_source_custom_metadata_value import PipelineDataSourceCustomMetadataValue
+from .pipeline_data_source_status import PipelineDataSourceStatus
 from .pipeline_deployment import PipelineDeployment
 from .pipeline_embedding_config import (
     PipelineEmbeddingConfig,
@@ -340,6 +341,7 @@ __all__ = [
     "AdvancedModeTransformConfigSegmentationConfig_None",
     "AdvancedModeTransformConfigSegmentationConfig_Page",
     "AppSchemaChatChatMessage",
+    "AudioBlock",
     "AutoTransformConfig",
     "AzureOpenAiEmbedding",
     "AzureOpenAiEmbeddingConfig",
@@ -348,6 +350,10 @@ __all__ = [
     "BasePlanName",
     "BasePlanPlanFrequency",
     "BasePromptTemplate",
+    "Batch",
+    "BatchItem",
+    "BatchPaginatedList",
+    "BatchPublicOutput",
     "BedrockEmbedding",
     "BedrockEmbeddingConfig",
     "BillingPeriod",
@@ -425,19 +431,10 @@ __all__ = [
     "EmbeddingModelConfigUpdateEmbeddingConfig_VertexaiEmbedding",
     "EvalExecutionParams",
     "ExtractAgent",
-    "ExtractAgentCreate",
-    "ExtractAgentCreateDataSchema",
-    "ExtractAgentCreateDataSchemaZeroValue",
     "ExtractAgentDataSchemaValue",
-    "ExtractAgentUpdate",
-    "ExtractAgentUpdateDataSchema",
-    "ExtractAgentUpdateDataSchemaZeroValue",
     "ExtractConfig",
     "ExtractJob",
     "ExtractJobCreate",
-    "ExtractJobCreateBatch",
-    "ExtractJobCreateBatchDataSchemaOverride",
-    "ExtractJobCreateBatchDataSchemaOverrideZeroValue",
     "ExtractJobCreateDataSchemaOverride",
     "ExtractJobCreateDataSchemaOverrideZeroValue",
     "ExtractMode",
@@ -452,14 +449,14 @@ __all__ = [
     "ExtractRunDataSchemaValue",
     "ExtractRunDataZeroValue",
     "ExtractRunExtractionMetadataValue",
-    "ExtractSchemaValidateRequest",
-    "ExtractSchemaValidateRequestDataSchema",
-    "ExtractSchemaValidateRequestDataSchemaZeroValue",
     "ExtractSchemaValidateResponse",
     "ExtractSchemaValidateResponseDataSchemaValue",
     "ExtractState",
     "ExtractTarget",
+    "FailPageMode",
     "File",
+    "FileCountByStatusResponse",
+    "FileParsePublic",
     "FilePermissionInfoValue",
     "FileResourceInfoValue",
     "FilterCondition",
@@ -481,6 +478,7 @@ __all__ = [
     "LlamaExtractSettings",
     "LlamaIndexCoreBaseLlmsTypesChatMessage",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem",
+    "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Audio",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image",
     "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text",
     "LlamaParseParameters",
@@ -528,6 +526,9 @@ __all__ = [
     "ParsingMode",
     "PartitionNames",
     "Permission",
+    "PgVectorDistanceMethod",
+    "PgVectorHnswSettings",
+    "PgVectorVectorType",
     "Pipeline",
     "PipelineConfigurationHashes",
     "PipelineCreate",
@@ -544,6 +545,7 @@ __all__ = [
     "PipelineDataSourceComponent",
     "PipelineDataSourceCreate",
     "PipelineDataSourceCustomMetadataValue",
+    "PipelineDataSourceStatus",
     "PipelineDeployment",
     "PipelineEmbeddingConfig",
     "PipelineEmbeddingConfig_AzureEmbedding",

llama_cloud/types/{extract_schema_validate_request.py → audio_block.py}

@@ -4,7 +4,6 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extract_schema_validate_request_data_schema import ExtractSchemaValidateRequestDataSchema
 
 try:
     import pydantic
@@ -15,8 +14,11 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ExtractSchemaValidateRequest(pydantic.BaseModel):
-    data_schema: ExtractSchemaValidateRequestDataSchema
+class AudioBlock(pydantic.BaseModel):
+    audio: typing.Optional[str]
+    path: typing.Optional[str]
+    url: typing.Optional[str]
+    format: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/batch.py

@@ -0,0 +1,47 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from .llama_parse_parameters import LlamaParseParameters
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class Batch(pydantic.BaseModel):
+    tool: str = pydantic.Field(description="The tool to be used for all requests in the batch.")
+    tool_data: typing.Optional[LlamaParseParameters]
+    input_type: str = pydantic.Field(description="The type of input file. Currently only 'datasource' is supported.")
+    input_id: str = pydantic.Field(description="The ID of the input file for the batch.")
+    output_type: typing.Optional[str]
+    output_id: typing.Optional[str]
+    id: str = pydantic.Field(description="Unique identifier for the batch")
+    project_id: str = pydantic.Field(description="The ID of the project to which the batch belongs")
+    organization_id: str = pydantic.Field(description="The ID of the organization to which the batch belongs")
+    user_id: str = pydantic.Field(description="The ID of the user who created the batch")
+    external_id: typing.Optional[str]
+    completion_window: int = pydantic.Field(description="The time frame within which the batch should be processed")
+    pipeline_id: str = pydantic.Field(description="The ID of the pipeline to which the batch belongs")
+    status: str = pydantic.Field(description="The current status of the batch")
+    created_at: typing.Optional[dt.datetime]
+    updated_at: typing.Optional[dt.datetime]
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        json_encoders = {dt.datetime: serialize_datetime}