llama-cloud 0.0.14__py3-none-any.whl → 0.0.16__py3-none-any.whl

llama_cloud/resources/pipelines/client.py

@@ -1040,6 +1040,52 @@ class PipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def update_pipeline_data_source(
+        self, pipeline_id: str, data_source_id: str, *, sync_interval: typing.Optional[float] = OMIT
+    ) -> PipelineDataSource:
+        """
+        Update the configuration of a data source in a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - data_source_id: str.
+
+            - sync_interval: typing.Optional[float]. The interval at which the data source should be synced.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.pipelines.update_pipeline_data_source(
+            pipeline_id="string",
+            data_source_id="string",
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {}
+        if sync_interval is not OMIT:
+            _request["sync_interval"] = sync_interval
+        _response = self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/",
+                f"api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}",
+            ),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(PipelineDataSource, _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 delete_pipeline_data_source(self, pipeline_id: str, data_source_id: str) -> None:
         """
         Delete a data source from a pipeline.
@@ -1116,6 +1162,44 @@ 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_data_source_status(self, pipeline_id: str, data_source_id: str) -> ManagedIngestionStatusResponse:
+        """
+        Get the status of a data source for a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - data_source_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.pipelines.get_pipeline_data_source_status(
+            pipeline_id="string",
+            data_source_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}/data-sources/{data_source_id}/status",
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ManagedIngestionStatusResponse, _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 run_search(
         self,
         pipeline_id: str,
@@ -1128,6 +1212,7 @@ class PipelinesClient:
         search_filters: typing.Optional[MetadataFilters] = OMIT,
         files_top_k: typing.Optional[int] = OMIT,
         retrieval_mode: typing.Optional[RetrievalMode] = OMIT,
+        retrieve_image_nodes: typing.Optional[bool] = OMIT,
         query: str,
     ) -> RetrieveResults:
         """
@@ -1152,6 +1237,8 @@ class PipelinesClient:
 
             - retrieval_mode: typing.Optional[RetrievalMode]. The retrieval mode for the query.
 
+            - retrieve_image_nodes: typing.Optional[bool]. Whether to retrieve image nodes.
+
             - query: str. The query to retrieve against.
         ---
         from llama_cloud import FilterCondition, MetadataFilters, RetrievalMode
@@ -1187,6 +1274,8 @@ class PipelinesClient:
             _request["files_top_k"] = files_top_k
         if retrieval_mode is not OMIT:
             _request["retrieval_mode"] = retrieval_mode
+        if retrieve_image_nodes is not OMIT:
+            _request["retrieve_image_nodes"] = retrieve_image_nodes
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/retrieve"),
@@ -1334,6 +1423,7 @@ class PipelinesClient:
             MetadataFilters,
             PresetRetrievalParams,
             RetrievalMode,
+            SupportedLlmModelNames,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -1350,7 +1440,9 @@ class PipelinesClient:
                     ),
                     retrieval_mode=RetrievalMode.CHUNKS,
                 ),
-                llm_parameters=LlmParameters(),
+                llm_parameters=LlmParameters(
+                    model_name=SupportedLlmModelNames.GPT_3_5_TURBO,
+                ),
             ),
         )
         """
@@ -2652,6 +2744,52 @@ class AsyncPipelinesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def update_pipeline_data_source(
+        self, pipeline_id: str, data_source_id: str, *, sync_interval: typing.Optional[float] = OMIT
+    ) -> PipelineDataSource:
+        """
+        Update the configuration of a data source in a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - data_source_id: str.
+
+            - sync_interval: typing.Optional[float]. The interval at which the data source should be synced.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.pipelines.update_pipeline_data_source(
+            pipeline_id="string",
+            data_source_id="string",
+        )
+        """
+        _request: typing.Dict[str, typing.Any] = {}
+        if sync_interval is not OMIT:
+            _request["sync_interval"] = sync_interval
+        _response = await self._client_wrapper.httpx_client.request(
+            "PUT",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/",
+                f"api/v1/pipelines/{pipeline_id}/data-sources/{data_source_id}",
+            ),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(PipelineDataSource, _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 delete_pipeline_data_source(self, pipeline_id: str, data_source_id: str) -> None:
         """
         Delete a data source from a pipeline.
@@ -2728,6 +2866,46 @@ 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_data_source_status(
+        self, pipeline_id: str, data_source_id: str
+    ) -> ManagedIngestionStatusResponse:
+        """
+        Get the status of a data source for a pipeline.
+
+        Parameters:
+            - pipeline_id: str.
+
+            - data_source_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.pipelines.get_pipeline_data_source_status(
+            pipeline_id="string",
+            data_source_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}/data-sources/{data_source_id}/status",
+            ),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ManagedIngestionStatusResponse, _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 run_search(
         self,
         pipeline_id: str,
@@ -2740,6 +2918,7 @@ class AsyncPipelinesClient:
         search_filters: typing.Optional[MetadataFilters] = OMIT,
         files_top_k: typing.Optional[int] = OMIT,
         retrieval_mode: typing.Optional[RetrievalMode] = OMIT,
+        retrieve_image_nodes: typing.Optional[bool] = OMIT,
         query: str,
     ) -> RetrieveResults:
         """
@@ -2764,6 +2943,8 @@ class AsyncPipelinesClient:
 
             - retrieval_mode: typing.Optional[RetrievalMode]. The retrieval mode for the query.
 
+            - retrieve_image_nodes: typing.Optional[bool]. Whether to retrieve image nodes.
+
             - query: str. The query to retrieve against.
         ---
         from llama_cloud import FilterCondition, MetadataFilters, RetrievalMode
@@ -2799,6 +2980,8 @@ class AsyncPipelinesClient:
             _request["files_top_k"] = files_top_k
         if retrieval_mode is not OMIT:
             _request["retrieval_mode"] = retrieval_mode
+        if retrieve_image_nodes is not OMIT:
+            _request["retrieve_image_nodes"] = retrieve_image_nodes
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/retrieve"),
@@ -2946,6 +3129,7 @@ class AsyncPipelinesClient:
             MetadataFilters,
             PresetRetrievalParams,
             RetrievalMode,
+            SupportedLlmModelNames,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -2962,7 +3146,9 @@ class AsyncPipelinesClient:
                     ),
                     retrieval_mode=RetrievalMode.CHUNKS,
                 ),
-                llm_parameters=LlmParameters(),
+                llm_parameters=LlmParameters(
+                    model_name=SupportedLlmModelNames.GPT_3_5_TURBO,
+                ),
             ),
         )
         """

llama_cloud/resources/pipelines/types/__init__.py

@@ -9,6 +9,7 @@ from .pipeline_update_embedding_config import (
     PipelineUpdateEmbeddingConfig_GeminiEmbedding,
     PipelineUpdateEmbeddingConfig_HuggingfaceApiEmbedding,
     PipelineUpdateEmbeddingConfig_OpenaiEmbedding,
+    PipelineUpdateEmbeddingConfig_VertexaiEmbedding,
 )
 from .pipeline_update_transform_config import (
     PipelineUpdateTransformConfig,
@@ -25,6 +26,7 @@ __all__ = [
     "PipelineUpdateEmbeddingConfig_GeminiEmbedding",
     "PipelineUpdateEmbeddingConfig_HuggingfaceApiEmbedding",
     "PipelineUpdateEmbeddingConfig_OpenaiEmbedding",
+    "PipelineUpdateEmbeddingConfig_VertexaiEmbedding",
     "PipelineUpdateTransformConfig",
     "PipelineUpdateTransformConfig_Advanced",
     "PipelineUpdateTransformConfig_Auto",

llama_cloud/resources/pipelines/types/pipeline_update_embedding_config.py

@@ -12,6 +12,7 @@ from ....types.cohere_embedding_config import CohereEmbeddingConfig
 from ....types.gemini_embedding_config import GeminiEmbeddingConfig
 from ....types.hugging_face_inference_api_embedding_config import HuggingFaceInferenceApiEmbeddingConfig
 from ....types.open_ai_embedding_config import OpenAiEmbeddingConfig
+from ....types.vertex_ai_embedding_config import VertexAiEmbeddingConfig
 
 
 class PipelineUpdateEmbeddingConfig_OpenaiEmbedding(OpenAiEmbeddingConfig):
@@ -68,6 +69,15 @@ class PipelineUpdateEmbeddingConfig_CohereEmbedding(CohereEmbeddingConfig):
         allow_population_by_field_name = True
 
 
+class PipelineUpdateEmbeddingConfig_VertexaiEmbedding(VertexAiEmbeddingConfig):
+    type: typing_extensions.Literal["VERTEXAI_EMBEDDING"]
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+
+
 PipelineUpdateEmbeddingConfig = typing.Union[
     PipelineUpdateEmbeddingConfig_OpenaiEmbedding,
     PipelineUpdateEmbeddingConfig_AzureEmbedding,
@@ -75,4 +85,5 @@ PipelineUpdateEmbeddingConfig = typing.Union[
     PipelineUpdateEmbeddingConfig_BedrockEmbedding,
     PipelineUpdateEmbeddingConfig_GeminiEmbedding,
     PipelineUpdateEmbeddingConfig_CohereEmbedding,
+    PipelineUpdateEmbeddingConfig_VertexaiEmbedding,
 ]

llama_cloud/types/__init__.py

@@ -82,6 +82,7 @@ from .eval_execution_params_override import EvalExecutionParamsOverride
 from .eval_question import EvalQuestion
 from .eval_question_create import EvalQuestionCreate
 from .eval_question_result import EvalQuestionResult
+from .extend_vertex_text_embedding import ExtendVertexTextEmbedding
 from .extraction_job import ExtractionJob
 from .extraction_result import ExtractionResult
 from .extraction_result_data_value import ExtractionResultDataValue
@@ -127,6 +128,8 @@ from .open_ai_embedding import OpenAiEmbedding
 from .open_ai_embedding_config import OpenAiEmbeddingConfig
 from .organization import Organization
 from .organization_create import OrganizationCreate
+from .page_screenshot_metadata import PageScreenshotMetadata
+from .page_screenshot_node_with_score import PageScreenshotNodeWithScore
 from .page_segmentation_config import PageSegmentationConfig
 from .page_splitter_node_parser import PageSplitterNodeParser
 from .parser_languages import ParserLanguages
@@ -137,6 +140,7 @@ from .parsing_job_markdown_result import ParsingJobMarkdownResult
 from .parsing_job_text_result import ParsingJobTextResult
 from .parsing_usage import ParsingUsage
 from .pipeline import Pipeline
+from .pipeline_configuration_hashes import PipelineConfigurationHashes
 from .pipeline_create import PipelineCreate
 from .pipeline_create_embedding_config import (
     PipelineCreateEmbeddingConfig,
@@ -146,6 +150,7 @@ from .pipeline_create_embedding_config import (
     PipelineCreateEmbeddingConfig_GeminiEmbedding,
     PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding,
     PipelineCreateEmbeddingConfig_OpenaiEmbedding,
+    PipelineCreateEmbeddingConfig_VertexaiEmbedding,
 )
 from .pipeline_create_transform_config import (
     PipelineCreateTransformConfig,
@@ -166,8 +171,10 @@ from .pipeline_embedding_config import (
     PipelineEmbeddingConfig_GeminiEmbedding,
     PipelineEmbeddingConfig_HuggingfaceApiEmbedding,
     PipelineEmbeddingConfig_OpenaiEmbedding,
+    PipelineEmbeddingConfig_VertexaiEmbedding,
 )
 from .pipeline_file import PipelineFile
+from .pipeline_file_config_hash_value import PipelineFileConfigHashValue
 from .pipeline_file_create import PipelineFileCreate
 from .pipeline_file_create_custom_metadata_value import PipelineFileCreateCustomMetadataValue
 from .pipeline_file_custom_metadata_value import PipelineFileCustomMetadataValue
@@ -208,6 +215,8 @@ from .user_organization_create import UserOrganizationCreate
 from .user_organization_delete import UserOrganizationDelete
 from .validation_error import ValidationError
 from .validation_error_loc_item import ValidationErrorLocItem
+from .vertex_ai_embedding_config import VertexAiEmbeddingConfig
+from .vertex_embedding_mode import VertexEmbeddingMode
 
 __all__ = [
     "AdvancedModeTransformConfig",
@@ -288,6 +297,7 @@ __all__ = [
     "EvalQuestion",
     "EvalQuestionCreate",
     "EvalQuestionResult",
+    "ExtendVertexTextEmbedding",
     "ExtractionJob",
     "ExtractionResult",
     "ExtractionResultDataValue",
@@ -333,6 +343,8 @@ __all__ = [
     "OpenAiEmbeddingConfig",
     "Organization",
     "OrganizationCreate",
+    "PageScreenshotMetadata",
+    "PageScreenshotNodeWithScore",
     "PageSegmentationConfig",
     "PageSplitterNodeParser",
     "ParserLanguages",
@@ -343,6 +355,7 @@ __all__ = [
     "ParsingJobTextResult",
     "ParsingUsage",
     "Pipeline",
+    "PipelineConfigurationHashes",
     "PipelineCreate",
     "PipelineCreateEmbeddingConfig",
     "PipelineCreateEmbeddingConfig_AzureEmbedding",
@@ -351,6 +364,7 @@ __all__ = [
     "PipelineCreateEmbeddingConfig_GeminiEmbedding",
     "PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding",
     "PipelineCreateEmbeddingConfig_OpenaiEmbedding",
+    "PipelineCreateEmbeddingConfig_VertexaiEmbedding",
     "PipelineCreateTransformConfig",
     "PipelineCreateTransformConfig_Advanced",
     "PipelineCreateTransformConfig_Auto",
@@ -367,7 +381,9 @@ __all__ = [
     "PipelineEmbeddingConfig_GeminiEmbedding",
     "PipelineEmbeddingConfig_HuggingfaceApiEmbedding",
     "PipelineEmbeddingConfig_OpenaiEmbedding",
+    "PipelineEmbeddingConfig_VertexaiEmbedding",
     "PipelineFile",
+    "PipelineFileConfigHashValue",
     "PipelineFileCreate",
     "PipelineFileCreateCustomMetadataValue",
     "PipelineFileCustomMetadataValue",
@@ -406,4 +422,6 @@ __all__ = [
     "UserOrganizationDelete",
     "ValidationError",
     "ValidationErrorLocItem",
+    "VertexAiEmbeddingConfig",
+    "VertexEmbeddingMode",
 ]

llama_cloud/types/cloud_az_storage_blob_data_source.py

@@ -21,9 +21,8 @@ class CloudAzStorageBlobDataSource(pydantic.BaseModel):
 
     container_name: str = pydantic.Field(description="The name of the Azure Storage Blob container to read from.")
     account_url: str = pydantic.Field(description="The Azure Storage Blob account URL to use for authentication.")
-    blob: typing.Optional[str] = pydantic.Field(description="The blob name to read from.")
     prefix: typing.Optional[str] = pydantic.Field(
-        description="The prefix of the Azure Storage Blob objects to read from."
+        description="The prefix of the Azure Storage Blob objects to read from. Use this to filter files at the subdirectory level"
     )
     account_name: typing.Optional[str] = pydantic.Field(
         description="The Azure Storage Blob account name to use for authentication."

llama_cloud/types/cloud_postgres_vector_store.py

@@ -20,17 +20,15 @@ class CloudPostgresVectorStore(pydantic.BaseModel):
     """
 
     supports_nested_metadata_filters: typing.Optional[bool]
-    connection_string: str
-    async_connection_string: str
+    database: str
+    host: str
+    password: str
+    port: str
+    user: str
     table_name: str
     schema_name: str
     embed_dim: int
-    hybrid_search: bool
-    text_search_config: str
-    cache_ok: bool
-    perform_setup: bool
-    debug: bool
-    use_jsonb: bool
+    hybrid_search: typing.Optional[bool]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/configurable_transformation_names.py

@@ -24,6 +24,7 @@ class ConfigurableTransformationNames(str, enum.Enum):
     BEDROCK_EMBEDDING = "BEDROCK_EMBEDDING"
     HUGGINGFACE_API_EMBEDDING = "HUGGINGFACE_API_EMBEDDING"
     GEMINI_EMBEDDING = "GEMINI_EMBEDDING"
+    VERTEXAI_EMBEDDING = "VERTEXAI_EMBEDDING"
 
     def visit(
         self,
@@ -40,6 +41,7 @@ class ConfigurableTransformationNames(str, enum.Enum):
         bedrock_embedding: typing.Callable[[], T_Result],
         huggingface_api_embedding: typing.Callable[[], T_Result],
         gemini_embedding: typing.Callable[[], T_Result],
+        vertexai_embedding: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is ConfigurableTransformationNames.CHARACTER_SPLITTER:
             return character_splitter()
@@ -67,3 +69,5 @@ class ConfigurableTransformationNames(str, enum.Enum):
             return huggingface_api_embedding()
         if self is ConfigurableTransformationNames.GEMINI_EMBEDDING:
             return gemini_embedding()
+        if self is ConfigurableTransformationNames.VERTEXAI_EMBEDDING:
+            return vertexai_embedding()

llama_cloud/types/configured_transformation_item_component_one.py

@@ -7,6 +7,7 @@ from .bedrock_embedding import BedrockEmbedding
 from .character_splitter import CharacterSplitter
 from .code_splitter import CodeSplitter
 from .cohere_embedding import CohereEmbedding
+from .extend_vertex_text_embedding import ExtendVertexTextEmbedding
 from .gemini_embedding import GeminiEmbedding
 from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
 from .markdown_element_node_parser import MarkdownElementNodeParser
@@ -30,4 +31,5 @@ ConfiguredTransformationItemComponentOne = typing.Union[
     BedrockEmbedding,
     HuggingFaceInferenceApiEmbedding,
     GeminiEmbedding,
+    ExtendVertexTextEmbedding,
 ]

llama_cloud/types/extend_vertex_text_embedding.py

@@ -0,0 +1,58 @@
+# 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 .vertex_embedding_mode import VertexEmbeddingMode
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExtendVertexTextEmbedding(pydantic.BaseModel):
+    """
+    Base class for embeddings.
+    """
+
+    model_name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model.")
+    embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
+    callback_manager: typing.Optional[typing.Dict[str, typing.Any]]
+    num_workers: typing.Optional[int] = pydantic.Field(
+        description="The number of workers to use for async embedding calls."
+    )
+    embed_mode: VertexEmbeddingMode = pydantic.Field(description="The embedding mode to use.")
+    additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
+        description="Additional kwargs for the Vertex."
+    )
+    client_email: typing.Optional[str] = pydantic.Field(
+        description="The client email to use when making Vertex API calls."
+    )
+    token_uri: typing.Optional[str] = pydantic.Field(description="The token uri to use when making Vertex API calls.")
+    private_key_id: typing.Optional[str] = pydantic.Field(
+        description="The private key id to use when making Vertex API calls."
+    )
+    private_key: typing.Optional[str] = pydantic.Field(
+        description="The private key to use when making Vertex API calls."
+    )
+    project: str = pydantic.Field(description="The default GCP project to use when making Vertex API calls.")
+    location: str = pydantic.Field(description="The default location to use when making API calls.")
+    class_name: typing.Optional[str]
+
+    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}

llama_cloud/types/llama_parse_parameters.py

@@ -23,6 +23,7 @@ class LlamaParseParameters(pydantic.BaseModel):
     languages: typing.Optional[typing.List[ParserLanguages]]
     parsing_instruction: typing.Optional[str]
     disable_ocr: typing.Optional[bool]
+    disable_reconstruction: typing.Optional[bool]
     invalidate_cache: typing.Optional[bool]
     do_not_cache: typing.Optional[bool]
     fast_mode: typing.Optional[bool]
@@ -33,11 +34,12 @@ class LlamaParseParameters(pydantic.BaseModel):
     page_separator: typing.Optional[str]
     bounding_box: typing.Optional[str]
     target_pages: typing.Optional[str]
-    use_vendor_multimodal_model: typing.Optional[str]
+    use_vendor_multimodal_model: typing.Optional[bool]
     vendor_multimodal_model_name: typing.Optional[str]
     vendor_multimodal_api_key: typing.Optional[str]
     page_prefix: typing.Optional[str]
     page_suffix: typing.Optional[str]
+    webhook_url: typing.Optional[str]
     take_screenshot: typing.Optional[bool]
     s_3_input_path: typing.Optional[str] = pydantic.Field(alias="s3_input_path")
     s_3_output_path_prefix: typing.Optional[str] = pydantic.Field(alias="s3_output_path_prefix")

llama_cloud/types/llm_model_data.py

@@ -21,6 +21,7 @@ class LlmModelData(pydantic.BaseModel):
 
     name: str = pydantic.Field(description="The name of the LLM model.")
     description: str = pydantic.Field(description="The description of the LLM model.")
+    multi_modal: bool = pydantic.Field(description="Whether the model supports multi-modal image input")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/llm_parameters.py

@@ -4,6 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
+from .supported_llm_model_names import SupportedLlmModelNames
 
 try:
     import pydantic
@@ -20,7 +21,9 @@ class LlmParameters(pydantic.BaseModel):
     Comes with special serialization logic for types used commonly in platform codebase.
     """
 
-    model_name: typing.Optional[str] = pydantic.Field(description="The name of the model to use for LLM completions.")
+    model_name: typing.Optional[SupportedLlmModelNames] = pydantic.Field(
+        description="The name of the model to use for LLM completions."
+    )
     system_prompt: typing.Optional[str] = pydantic.Field(description="The system prompt to use for the completion.")
     temperature: typing.Optional[float] = pydantic.Field(description="The temperature value for the model.")
     class_name: typing.Optional[str]

llama_cloud/types/page_screenshot_metadata.py

@@ -0,0 +1,33 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PageScreenshotMetadata(pydantic.BaseModel):
+    page_index: int = pydantic.Field(description="The index of the page for which the screenshot is taken (0-indexed)")
+    file_id: str = pydantic.Field(description="The ID of the file that the page screenshot was taken from")
+    image_size: int = pydantic.Field(description="The size of the image in bytes")
+
+    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}