llama-cloud 0.1.40__py3-none-any.whl → 0.1.41__py3-none-any.whl

llama_cloud/resources/llama_extract/client.py

@@ -111,7 +111,9 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -124,6 +126,8 @@ class LlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -359,7 +363,9 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -372,6 +378,8 @@ class LlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -472,7 +480,9 @@ class LlamaExtractClient:
             ExtractJobCreate,
             ExtractJobCreatePriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -488,6 +498,8 @@ class LlamaExtractClient:
                     priority=ExtractConfigPriority.LOW,
                     extraction_target=ExtractTarget.PER_DOC,
                     extraction_mode=ExtractMode.FAST,
+                    parse_model=PublicModelName.OPENAI_GPT_4_O,
+                    extract_model=ExtractModels.OPENAI_GPT_4_1,
                     chunk_mode=DocumentChunkMode.PAGE,
                 ),
             ),
@@ -564,6 +576,7 @@ class LlamaExtractClient:
             ExtractJobCreate,
             ExtractJobCreatePriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
             FailPageMode,
             LlamaExtractSettings,
@@ -571,6 +584,7 @@ class LlamaExtractClient:
             LlamaParseParametersPriority,
             MultimodalParseResolution,
             ParsingMode,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -586,6 +600,8 @@ class LlamaExtractClient:
                     priority=ExtractConfigPriority.LOW,
                     extraction_target=ExtractTarget.PER_DOC,
                     extraction_mode=ExtractMode.FAST,
+                    parse_model=PublicModelName.OPENAI_GPT_4_O,
+                    extract_model=ExtractModels.OPENAI_GPT_4_1,
                     chunk_mode=DocumentChunkMode.PAGE,
                 ),
             ),
@@ -693,7 +709,9 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -707,6 +725,8 @@ class LlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -988,8 +1008,10 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
             FileData,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -1001,6 +1023,8 @@ class LlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
             file=FileData(
@@ -1108,7 +1132,9 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1121,6 +1147,8 @@ class AsyncLlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -1356,7 +1384,9 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1369,6 +1399,8 @@ class AsyncLlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -1469,7 +1501,9 @@ class AsyncLlamaExtractClient:
             ExtractJobCreate,
             ExtractJobCreatePriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1485,6 +1519,8 @@ class AsyncLlamaExtractClient:
                     priority=ExtractConfigPriority.LOW,
                     extraction_target=ExtractTarget.PER_DOC,
                     extraction_mode=ExtractMode.FAST,
+                    parse_model=PublicModelName.OPENAI_GPT_4_O,
+                    extract_model=ExtractModels.OPENAI_GPT_4_1,
                     chunk_mode=DocumentChunkMode.PAGE,
                 ),
             ),
@@ -1561,6 +1597,7 @@ class AsyncLlamaExtractClient:
             ExtractJobCreate,
             ExtractJobCreatePriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
             FailPageMode,
             LlamaExtractSettings,
@@ -1568,6 +1605,7 @@ class AsyncLlamaExtractClient:
             LlamaParseParametersPriority,
             MultimodalParseResolution,
             ParsingMode,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1583,6 +1621,8 @@ class AsyncLlamaExtractClient:
                     priority=ExtractConfigPriority.LOW,
                     extraction_target=ExtractTarget.PER_DOC,
                     extraction_mode=ExtractMode.FAST,
+                    parse_model=PublicModelName.OPENAI_GPT_4_O,
+                    extract_model=ExtractModels.OPENAI_GPT_4_1,
                     chunk_mode=DocumentChunkMode.PAGE,
                 ),
             ),
@@ -1690,7 +1730,9 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1704,6 +1746,8 @@ class AsyncLlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -1985,8 +2029,10 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
             FileData,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1998,6 +2044,8 @@ class AsyncLlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
             file=FileData(

llama_cloud/types/__init__.py

@@ -19,7 +19,6 @@ from .agent_data import AgentData
 from .agent_deployment_list import AgentDeploymentList
 from .agent_deployment_summary import AgentDeploymentSummary
 from .aggregate_group import AggregateGroup
-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
@@ -39,6 +38,7 @@ from .character_chunking_config import CharacterChunkingConfig
 from .chat_app import ChatApp
 from .chat_app_response import ChatAppResponse
 from .chat_data import ChatData
+from .chat_message import ChatMessage
 from .chunk_mode import ChunkMode
 from .classification_result import ClassificationResult
 from .classifier_rule import ClassifierRule
@@ -88,11 +88,8 @@ from .data_source_reader_version_metadata import DataSourceReaderVersionMetadata
 from .data_source_reader_version_metadata_reader_version import DataSourceReaderVersionMetadataReaderVersion
 from .data_source_update_dispatcher_config import DataSourceUpdateDispatcherConfig
 from .delete_params import DeleteParams
-from .document_block import DocumentBlock
 from .document_chunk_mode import DocumentChunkMode
 from .document_ingestion_job_params import DocumentIngestionJobParams
-from .edit_suggestion import EditSuggestion
-from .edit_suggestion_blocks_item import EditSuggestionBlocksItem
 from .element_segmentation_config import ElementSegmentationConfig
 from .embedding_model_config import EmbeddingModelConfig
 from .embedding_model_config_embedding_config import (
@@ -178,7 +175,6 @@ from .http_validation_error import HttpValidationError
 from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
 from .hugging_face_inference_api_embedding_config import HuggingFaceInferenceApiEmbeddingConfig
 from .hugging_face_inference_api_embedding_token import HuggingFaceInferenceApiEmbeddingToken
-from .image_block import ImageBlock
 from .ingestion_error_response import IngestionErrorResponse
 from .input_message import InputMessage
 from .job_name_mapping import JobNameMapping
@@ -204,14 +200,6 @@ from .llama_extract_feature_availability import LlamaExtractFeatureAvailability
 from .llama_extract_mode_availability import LlamaExtractModeAvailability
 from .llama_extract_mode_availability_status import LlamaExtractModeAvailabilityStatus
 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_Document,
-    LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image,
-    LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text,
-)
 from .llama_parse_parameters import LlamaParseParameters
 from .llama_parse_parameters_priority import LlamaParseParametersPriority
 from .llama_parse_supported_file_extensions import LlamaParseSupportedFileExtensions
@@ -246,11 +234,14 @@ from .paginated_extract_runs_response import PaginatedExtractRunsResponse
 from .paginated_jobs_history_with_metrics import PaginatedJobsHistoryWithMetrics
 from .paginated_list_cloud_documents_response import PaginatedListCloudDocumentsResponse
 from .paginated_list_pipeline_files_response import PaginatedListPipelineFilesResponse
-from .paginated_report_response import PaginatedReportResponse
 from .paginated_response_agent_data import PaginatedResponseAgentData
 from .paginated_response_aggregate_group import PaginatedResponseAggregateGroup
 from .paginated_response_classify_job import PaginatedResponseClassifyJob
 from .paginated_response_quota_configuration import PaginatedResponseQuotaConfiguration
+from .parse_configuration import ParseConfiguration
+from .parse_configuration_create import ParseConfigurationCreate
+from .parse_configuration_filter import ParseConfigurationFilter
+from .parse_configuration_query_response import ParseConfigurationQueryResponse
 from .parse_job_config import ParseJobConfig
 from .parse_job_config_priority import ParseJobConfigPriority
 from .parse_plan_level import ParsePlanLevel
@@ -326,11 +317,10 @@ from .preset_retrieval_params_search_filters_inference_schema_value import (
     PresetRetrievalParamsSearchFiltersInferenceSchemaValue,
 )
 from .presigned_url import PresignedUrl
-from .progress_event import ProgressEvent
-from .progress_event_status import ProgressEventStatus
 from .project import Project
 from .project_create import ProjectCreate
 from .prompt_conf import PromptConf
+from .public_model_name import PublicModelName
 from .quota_configuration import QuotaConfiguration
 from .quota_configuration_configuration_type import QuotaConfigurationConfigurationType
 from .quota_configuration_status import QuotaConfigurationStatus
@@ -341,26 +331,6 @@ from .re_ranker_type import ReRankerType
 from .recurring_credit_grant import RecurringCreditGrant
 from .related_node_info import RelatedNodeInfo
 from .related_node_info_node_type import RelatedNodeInfoNodeType
-from .report import Report
-from .report_block import ReportBlock
-from .report_block_dependency import ReportBlockDependency
-from .report_create_response import ReportCreateResponse
-from .report_event_item import ReportEventItem
-from .report_event_item_event_data import (
-    ReportEventItemEventData,
-    ReportEventItemEventData_Progress,
-    ReportEventItemEventData_ReportBlockUpdate,
-    ReportEventItemEventData_ReportStateUpdate,
-)
-from .report_event_type import ReportEventType
-from .report_metadata import ReportMetadata
-from .report_plan import ReportPlan
-from .report_plan_block import ReportPlanBlock
-from .report_query import ReportQuery
-from .report_response import ReportResponse
-from .report_state import ReportState
-from .report_state_event import ReportStateEvent
-from .report_update_event import ReportUpdateEvent
 from .retrieval_mode import RetrievalMode
 from .retrieve_results import RetrieveResults
 from .retriever import Retriever
@@ -374,13 +344,11 @@ from .semantic_chunking_config import SemanticChunkingConfig
 from .sentence_chunking_config import SentenceChunkingConfig
 from .sparse_model_config import SparseModelConfig
 from .sparse_model_type import SparseModelType
-from .src_app_schema_chat_chat_message import SrcAppSchemaChatChatMessage
 from .status_enum import StatusEnum
 from .struct_mode import StructMode
 from .struct_parse_conf import StructParseConf
 from .supported_llm_model import SupportedLlmModel
 from .supported_llm_model_names import SupportedLlmModelNames
-from .text_block import TextBlock
 from .text_node import TextNode
 from .text_node_relationships_value import TextNodeRelationshipsValue
 from .text_node_with_score import TextNodeWithScore
@@ -420,7 +388,6 @@ __all__ = [
     "AgentDeploymentList",
     "AgentDeploymentSummary",
     "AggregateGroup",
-    "AudioBlock",
     "AutoTransformConfig",
     "AzureOpenAiEmbedding",
     "AzureOpenAiEmbeddingConfig",
@@ -440,6 +407,7 @@ __all__ = [
     "ChatApp",
     "ChatAppResponse",
     "ChatData",
+    "ChatMessage",
     "ChunkMode",
     "ClassificationResult",
     "ClassifierRule",
@@ -489,11 +457,8 @@ __all__ = [
     "DataSourceReaderVersionMetadataReaderVersion",
     "DataSourceUpdateDispatcherConfig",
     "DeleteParams",
-    "DocumentBlock",
     "DocumentChunkMode",
     "DocumentIngestionJobParams",
-    "EditSuggestion",
-    "EditSuggestionBlocksItem",
     "ElementSegmentationConfig",
     "EmbeddingModelConfig",
     "EmbeddingModelConfigEmbeddingConfig",
@@ -575,7 +540,6 @@ __all__ = [
     "HuggingFaceInferenceApiEmbedding",
     "HuggingFaceInferenceApiEmbeddingConfig",
     "HuggingFaceInferenceApiEmbeddingToken",
-    "ImageBlock",
     "IngestionErrorResponse",
     "InputMessage",
     "JobNameMapping",
@@ -599,12 +563,6 @@ __all__ = [
     "LlamaExtractModeAvailability",
     "LlamaExtractModeAvailabilityStatus",
     "LlamaExtractSettings",
-    "LlamaIndexCoreBaseLlmsTypesChatMessage",
-    "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem",
-    "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Audio",
-    "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Document",
-    "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Image",
-    "LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem_Text",
     "LlamaParseParameters",
     "LlamaParseParametersPriority",
     "LlamaParseSupportedFileExtensions",
@@ -639,11 +597,14 @@ __all__ = [
     "PaginatedJobsHistoryWithMetrics",
     "PaginatedListCloudDocumentsResponse",
     "PaginatedListPipelineFilesResponse",
-    "PaginatedReportResponse",
     "PaginatedResponseAgentData",
     "PaginatedResponseAggregateGroup",
     "PaginatedResponseClassifyJob",
     "PaginatedResponseQuotaConfiguration",
+    "ParseConfiguration",
+    "ParseConfigurationCreate",
+    "ParseConfigurationFilter",
+    "ParseConfigurationQueryResponse",
     "ParseJobConfig",
     "ParseJobConfigPriority",
     "ParsePlanLevel",
@@ -711,11 +672,10 @@ __all__ = [
     "PresetRetrievalParams",
     "PresetRetrievalParamsSearchFiltersInferenceSchemaValue",
     "PresignedUrl",
-    "ProgressEvent",
-    "ProgressEventStatus",
     "Project",
     "ProjectCreate",
     "PromptConf",
+    "PublicModelName",
     "QuotaConfiguration",
     "QuotaConfigurationConfigurationType",
     "QuotaConfigurationStatus",
@@ -726,24 +686,6 @@ __all__ = [
     "RecurringCreditGrant",
     "RelatedNodeInfo",
     "RelatedNodeInfoNodeType",
-    "Report",
-    "ReportBlock",
-    "ReportBlockDependency",
-    "ReportCreateResponse",
-    "ReportEventItem",
-    "ReportEventItemEventData",
-    "ReportEventItemEventData_Progress",
-    "ReportEventItemEventData_ReportBlockUpdate",
-    "ReportEventItemEventData_ReportStateUpdate",
-    "ReportEventType",
-    "ReportMetadata",
-    "ReportPlan",
-    "ReportPlanBlock",
-    "ReportQuery",
-    "ReportResponse",
-    "ReportState",
-    "ReportStateEvent",
-    "ReportUpdateEvent",
     "RetrievalMode",
     "RetrieveResults",
     "Retriever",
@@ -757,13 +699,11 @@ __all__ = [
     "SentenceChunkingConfig",
     "SparseModelConfig",
     "SparseModelType",
-    "SrcAppSchemaChatChatMessage",
     "StatusEnum",
     "StructMode",
     "StructParseConf",
     "SupportedLlmModel",
     "SupportedLlmModelNames",
-    "TextBlock",
     "TextNode",
     "TextNodeRelationshipsValue",
     "TextNodeWithScore",

llama_cloud/types/{src_app_schema_chat_chat_message.py → chat_message.py}

@@ -16,7 +16,7 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class SrcAppSchemaChatChatMessage(pydantic.BaseModel):
+class ChatMessage(pydantic.BaseModel):
     id: str
     index: int = pydantic.Field(description="The index of the message in the chat.")
     annotations: typing.Optional[typing.List[MessageAnnotation]] = pydantic.Field(

llama_cloud/types/extract_config.py

@@ -7,7 +7,9 @@ from ..core.datetime_utils import serialize_datetime
 from .document_chunk_mode import DocumentChunkMode
 from .extract_config_priority import ExtractConfigPriority
 from .extract_mode import ExtractMode
+from .extract_models import ExtractModels
 from .extract_target import ExtractTarget
+from .public_model_name import PublicModelName
 
 try:
     import pydantic
@@ -25,9 +27,13 @@ class ExtractConfig(pydantic.BaseModel):
 
     priority: typing.Optional[ExtractConfigPriority]
     extraction_target: typing.Optional[ExtractTarget] = pydantic.Field(description="The extraction target specified.")
-    extraction_mode: typing.Optional[ExtractMode] = pydantic.Field(description="The extraction mode specified.")
+    extraction_mode: typing.Optional[ExtractMode] = pydantic.Field(
+        description="The extraction mode specified (FAST, BALANCED, MULTIMODAL, PREMIUM)."
+    )
+    parse_model: typing.Optional[PublicModelName]
+    extract_model: typing.Optional[ExtractModels]
     multimodal_fast_mode: typing.Optional[bool] = pydantic.Field(
-        description="Whether to use fast mode for multimodal extraction."
+        description="DEPRECATED: Whether to use fast mode for multimodal extraction."
     )
     system_prompt: typing.Optional[str]
     use_reasoning: typing.Optional[bool] = pydantic.Field(description="Whether to use reasoning for the extraction.")

llama_cloud/types/extract_models.py

@@ -7,47 +7,47 @@ T_Result = typing.TypeVar("T_Result")
 
 
 class ExtractModels(str, enum.Enum):
-    GPT_41 = "gpt-4.1"
-    GPT_41_MINI = "gpt-4.1-mini"
-    GPT_41_NANO = "gpt-4.1-nano"
+    OPENAI_GPT_41 = "openai-gpt-4-1"
+    OPENAI_GPT_41_MINI = "openai-gpt-4-1-mini"
+    OPENAI_GPT_41_NANO = "openai-gpt-4-1-nano"
+    OPENAI_GPT_5 = "openai-gpt-5"
+    OPENAI_GPT_5_MINI = "openai-gpt-5-mini"
     GEMINI_20_FLASH = "gemini-2.0-flash"
-    O_3_MINI = "o3-mini"
     GEMINI_25_FLASH = "gemini-2.5-flash"
     GEMINI_25_PRO = "gemini-2.5-pro"
-    GEMINI_25_FLASH_LITE_PREVIEW_0617 = "gemini-2.5-flash-lite-preview-06-17"
-    GPT_4_O = "gpt-4o"
-    GPT_4_O_MINI = "gpt-4o-mini"
+    OPENAI_GPT_4_O = "openai-gpt-4o"
+    OPENAI_GPT_4_O_MINI = "openai-gpt-4o-mini"
 
     def visit(
         self,
-        gpt_41: typing.Callable[[], T_Result],
-        gpt_41_mini: typing.Callable[[], T_Result],
-        gpt_41_nano: typing.Callable[[], T_Result],
+        openai_gpt_41: typing.Callable[[], T_Result],
+        openai_gpt_41_mini: typing.Callable[[], T_Result],
+        openai_gpt_41_nano: typing.Callable[[], T_Result],
+        openai_gpt_5: typing.Callable[[], T_Result],
+        openai_gpt_5_mini: typing.Callable[[], T_Result],
         gemini_20_flash: typing.Callable[[], T_Result],
-        o_3_mini: typing.Callable[[], T_Result],
         gemini_25_flash: typing.Callable[[], T_Result],
         gemini_25_pro: typing.Callable[[], T_Result],
-        gemini_25_flash_lite_preview_0617: typing.Callable[[], T_Result],
-        gpt_4_o: typing.Callable[[], T_Result],
-        gpt_4_o_mini: typing.Callable[[], T_Result],
+        openai_gpt_4_o: typing.Callable[[], T_Result],
+        openai_gpt_4_o_mini: typing.Callable[[], T_Result],
     ) -> T_Result:
-        if self is ExtractModels.GPT_41:
-            return gpt_41()
-        if self is ExtractModels.GPT_41_MINI:
-            return gpt_41_mini()
-        if self is ExtractModels.GPT_41_NANO:
-            return gpt_41_nano()
+        if self is ExtractModels.OPENAI_GPT_41:
+            return openai_gpt_41()
+        if self is ExtractModels.OPENAI_GPT_41_MINI:
+            return openai_gpt_41_mini()
+        if self is ExtractModels.OPENAI_GPT_41_NANO:
+            return openai_gpt_41_nano()
+        if self is ExtractModels.OPENAI_GPT_5:
+            return openai_gpt_5()
+        if self is ExtractModels.OPENAI_GPT_5_MINI:
+            return openai_gpt_5_mini()
         if self is ExtractModels.GEMINI_20_FLASH:
             return gemini_20_flash()
-        if self is ExtractModels.O_3_MINI:
-            return o_3_mini()
         if self is ExtractModels.GEMINI_25_FLASH:
             return gemini_25_flash()
         if self is ExtractModels.GEMINI_25_PRO:
             return gemini_25_pro()
-        if self is ExtractModels.GEMINI_25_FLASH_LITE_PREVIEW_0617:
-            return gemini_25_flash_lite_preview_0617()
-        if self is ExtractModels.GPT_4_O:
-            return gpt_4_o()
-        if self is ExtractModels.GPT_4_O_MINI:
-            return gpt_4_o_mini()
+        if self is ExtractModels.OPENAI_GPT_4_O:
+            return openai_gpt_4_o()
+        if self is ExtractModels.OPENAI_GPT_4_O_MINI:
+            return openai_gpt_4_o_mini()

llama_cloud/types/llama_extract_mode_availability.py

@@ -19,9 +19,10 @@ class LlamaExtractModeAvailability(pydantic.BaseModel):
     mode: str
     status: LlamaExtractModeAvailabilityStatus
     parse_mode: str
-    parse_models: typing.List[str]
-    extract_models: typing.List[str]
-    missing_models: typing.Optional[typing.List[str]]
+    available_parse_models: typing.Optional[typing.List[str]]
+    missing_parse_models: typing.Optional[typing.List[str]]
+    available_extract_models: typing.Optional[typing.List[str]]
+    missing_extract_models: typing.Optional[typing.List[str]]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/llama_extract_settings.py

@@ -44,7 +44,7 @@ class LlamaExtractSettings(pydantic.BaseModel):
         description="Whether to use experimental multimodal parsing."
     )
     use_pixel_extraction: typing.Optional[bool] = pydantic.Field(
-        description="Whether to use extraction over pixels for multimodal mode."
+        description="DEPRECATED: Whether to use extraction over pixels for multimodal mode."
     )
     llama_parse_params: typing.Optional[LlamaParseParameters] = pydantic.Field(
         description="LlamaParse related settings."

llama_cloud/types/{progress_event.py → parse_configuration.py}

@@ -4,8 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .progress_event_status import ProgressEventStatus
-from .report_event_type import ReportEventType
+from .llama_parse_parameters import LlamaParseParameters
 
 try:
     import pydantic
@@ -16,19 +15,20 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class ProgressEvent(pydantic.BaseModel):
+class ParseConfiguration(pydantic.BaseModel):
     """
-    Event for tracking progress of operations in workflows.
+    Parse configuration schema.
     """
 
-    timestamp: typing.Optional[dt.datetime]
-    id: typing.Optional[str] = pydantic.Field(description="The ID of the event")
-    group_id: typing.Optional[str] = pydantic.Field(description="The ID of the group this event belongs to")
-    variant: ReportEventType
-    msg: str = pydantic.Field(description="The message to display to the user")
-    progress: typing.Optional[float]
-    status: typing.Optional[ProgressEventStatus] = pydantic.Field(description="Current status of the operation")
-    extra_detail: typing.Optional[typing.Dict[str, typing.Any]]
+    id: str = pydantic.Field(description="Unique identifier for the parse configuration")
+    name: str = pydantic.Field(description="Name of the parse configuration")
+    source_type: str = pydantic.Field(description="Type of the source (e.g., 'project')")
+    source_id: str = pydantic.Field(description="ID of the source")
+    creator: typing.Optional[str]
+    version: str = pydantic.Field(description="Version of the configuration")
+    parameters: LlamaParseParameters = pydantic.Field(description="LlamaParseParameters configuration")
+    created_at: dt.datetime = pydantic.Field(description="Creation timestamp")
+    updated_at: dt.datetime = pydantic.Field(description="Last update timestamp")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/{llama_index_core_base_llms_types_chat_message.py → parse_configuration_create.py}

@@ -4,8 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .llama_index_core_base_llms_types_chat_message_blocks_item import LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem
-from .message_role import MessageRole
+from .llama_parse_parameters import LlamaParseParameters
 
 try:
     import pydantic
@@ -16,14 +15,17 @@ except ImportError:
     import pydantic  # type: ignore
 
 
-class LlamaIndexCoreBaseLlmsTypesChatMessage(pydantic.BaseModel):
+class ParseConfigurationCreate(pydantic.BaseModel):
     """
-    Chat message.
+    Schema for creating a new parse configuration (API boundary).
     """
 
-    role: typing.Optional[MessageRole]
-    additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]]
-    blocks: typing.Optional[typing.List[LlamaIndexCoreBaseLlmsTypesChatMessageBlocksItem]]
+    name: str = pydantic.Field(description="Name of the parse configuration")
+    source_type: typing.Optional[str]
+    source_id: typing.Optional[str]
+    creator: typing.Optional[str]
+    version: str = pydantic.Field(description="Version of the configuration")
+    parameters: LlamaParseParameters = pydantic.Field(description="LlamaParseParameters configuration")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}