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

llama_cloud/__init__.py

@@ -79,6 +79,7 @@ from .types import (
     EvalQuestion,
     EvalQuestionCreate,
     EvalQuestionResult,
+    ExtendVertexTextEmbedding,
     ExtractionJob,
     ExtractionResult,
     ExtractionResultDataValue,
@@ -124,6 +125,8 @@ from .types import (
     OpenAiEmbeddingConfig,
     Organization,
     OrganizationCreate,
+    PageScreenshotMetadata,
+    PageScreenshotNodeWithScore,
     PageSegmentationConfig,
     PageSplitterNodeParser,
     ParserLanguages,
@@ -134,6 +137,7 @@ from .types import (
     ParsingJobTextResult,
     ParsingUsage,
     Pipeline,
+    PipelineConfigurationHashes,
     PipelineCreate,
     PipelineCreateEmbeddingConfig,
     PipelineCreateEmbeddingConfig_AzureEmbedding,
@@ -142,6 +146,7 @@ from .types import (
     PipelineCreateEmbeddingConfig_GeminiEmbedding,
     PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding,
     PipelineCreateEmbeddingConfig_OpenaiEmbedding,
+    PipelineCreateEmbeddingConfig_VertexaiEmbedding,
     PipelineCreateTransformConfig,
     PipelineCreateTransformConfig_Advanced,
     PipelineCreateTransformConfig_Auto,
@@ -158,7 +163,9 @@ from .types import (
     PipelineEmbeddingConfig_GeminiEmbedding,
     PipelineEmbeddingConfig_HuggingfaceApiEmbedding,
     PipelineEmbeddingConfig_OpenaiEmbedding,
+    PipelineEmbeddingConfig_VertexaiEmbedding,
     PipelineFile,
+    PipelineFileConfigHashValue,
     PipelineFileCreate,
     PipelineFileCreateCustomMetadataValue,
     PipelineFileCustomMetadataValue,
@@ -197,6 +204,8 @@ from .types import (
     UserOrganizationDelete,
     ValidationError,
     ValidationErrorLocItem,
+    VertexAiEmbeddingConfig,
+    VertexEmbeddingMode,
 )
 from .errors import UnprocessableEntityError
 from .resources import (
@@ -216,6 +225,7 @@ from .resources import (
     PipelineUpdateEmbeddingConfig_GeminiEmbedding,
     PipelineUpdateEmbeddingConfig_HuggingfaceApiEmbedding,
     PipelineUpdateEmbeddingConfig_OpenaiEmbedding,
+    PipelineUpdateEmbeddingConfig_VertexaiEmbedding,
     PipelineUpdateTransformConfig,
     PipelineUpdateTransformConfig_Advanced,
     PipelineUpdateTransformConfig_Auto,
@@ -317,6 +327,7 @@ __all__ = [
     "EvalQuestion",
     "EvalQuestionCreate",
     "EvalQuestionResult",
+    "ExtendVertexTextEmbedding",
     "ExtractionJob",
     "ExtractionResult",
     "ExtractionResultDataValue",
@@ -366,6 +377,8 @@ __all__ = [
     "OpenAiEmbeddingConfig",
     "Organization",
     "OrganizationCreate",
+    "PageScreenshotMetadata",
+    "PageScreenshotNodeWithScore",
     "PageSegmentationConfig",
     "PageSplitterNodeParser",
     "ParserLanguages",
@@ -376,6 +389,7 @@ __all__ = [
     "ParsingJobTextResult",
     "ParsingUsage",
     "Pipeline",
+    "PipelineConfigurationHashes",
     "PipelineCreate",
     "PipelineCreateEmbeddingConfig",
     "PipelineCreateEmbeddingConfig_AzureEmbedding",
@@ -384,6 +398,7 @@ __all__ = [
     "PipelineCreateEmbeddingConfig_GeminiEmbedding",
     "PipelineCreateEmbeddingConfig_HuggingfaceApiEmbedding",
     "PipelineCreateEmbeddingConfig_OpenaiEmbedding",
+    "PipelineCreateEmbeddingConfig_VertexaiEmbedding",
     "PipelineCreateTransformConfig",
     "PipelineCreateTransformConfig_Advanced",
     "PipelineCreateTransformConfig_Auto",
@@ -400,7 +415,9 @@ __all__ = [
     "PipelineEmbeddingConfig_GeminiEmbedding",
     "PipelineEmbeddingConfig_HuggingfaceApiEmbedding",
     "PipelineEmbeddingConfig_OpenaiEmbedding",
+    "PipelineEmbeddingConfig_VertexaiEmbedding",
     "PipelineFile",
+    "PipelineFileConfigHashValue",
     "PipelineFileCreate",
     "PipelineFileCreateCustomMetadataValue",
     "PipelineFileCustomMetadataValue",
@@ -417,6 +434,7 @@ __all__ = [
     "PipelineUpdateEmbeddingConfig_GeminiEmbedding",
     "PipelineUpdateEmbeddingConfig_HuggingfaceApiEmbedding",
     "PipelineUpdateEmbeddingConfig_OpenaiEmbedding",
+    "PipelineUpdateEmbeddingConfig_VertexaiEmbedding",
     "PipelineUpdateTransformConfig",
     "PipelineUpdateTransformConfig_Advanced",
     "PipelineUpdateTransformConfig_Auto",
@@ -451,6 +469,8 @@ __all__ = [
     "UserOrganizationDelete",
     "ValidationError",
     "ValidationErrorLocItem",
+    "VertexAiEmbeddingConfig",
+    "VertexEmbeddingMode",
     "auth",
     "component_definitions",
     "data_sinks",

llama_cloud/resources/__init__.py

@@ -26,6 +26,7 @@ from .pipelines import (
     PipelineUpdateEmbeddingConfig_GeminiEmbedding,
     PipelineUpdateEmbeddingConfig_HuggingfaceApiEmbedding,
     PipelineUpdateEmbeddingConfig_OpenaiEmbedding,
+    PipelineUpdateEmbeddingConfig_VertexaiEmbedding,
     PipelineUpdateTransformConfig,
     PipelineUpdateTransformConfig_Advanced,
     PipelineUpdateTransformConfig_Auto,
@@ -48,6 +49,7 @@ __all__ = [
     "PipelineUpdateEmbeddingConfig_GeminiEmbedding",
     "PipelineUpdateEmbeddingConfig_HuggingfaceApiEmbedding",
     "PipelineUpdateEmbeddingConfig_OpenaiEmbedding",
+    "PipelineUpdateEmbeddingConfig_VertexaiEmbedding",
     "PipelineUpdateTransformConfig",
     "PipelineUpdateTransformConfig_Advanced",
     "PipelineUpdateTransformConfig_Auto",

llama_cloud/resources/files/client.py

@@ -12,6 +12,7 @@ from ...core.remove_none_from_dict import remove_none_from_dict
 from ...errors.unprocessable_entity_error import UnprocessableEntityError
 from ...types.file import File
 from ...types.http_validation_error import HttpValidationError
+from ...types.page_screenshot_metadata import PageScreenshotMetadata
 from ...types.presigned_url import PresignedUrl
 from .types.file_create_resource_info_value import FileCreateResourceInfoValue
 
@@ -288,6 +289,85 @@ class FilesClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def list_file_page_screenshots(
+        self, id: str, *, project_id: typing.Optional[str] = None
+    ) -> typing.List[PageScreenshotMetadata]:
+        """
+        List metadata for all screenshots of pages from a file.
+
+        Parameters:
+            - id: str.
+
+            - project_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.files.list_file_page_screenshots(
+            id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/files/{id}/page_screenshots"),
+            params=remove_none_from_dict({"project_id": project_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[PageScreenshotMetadata], _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_file_page_screenshot(
+        self, id: str, page_index: int, *, project_id: typing.Optional[str] = None
+    ) -> typing.Any:
+        """
+        Get screenshot of a page from a file.
+
+        Parameters:
+            - id: str.
+
+            - page_index: int.
+
+            - project_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.files.get_file_page_screenshot(
+            id="string",
+            page_index=1,
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/files/{id}/page_screenshots/{page_index}"
+            ),
+            params=remove_none_from_dict({"project_id": project_id}),
+            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)
+
 
 class AsyncFilesClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
@@ -549,3 +629,82 @@ class AsyncFilesClient:
         except JSONDecodeError:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
+
+    async def list_file_page_screenshots(
+        self, id: str, *, project_id: typing.Optional[str] = None
+    ) -> typing.List[PageScreenshotMetadata]:
+        """
+        List metadata for all screenshots of pages from a file.
+
+        Parameters:
+            - id: str.
+
+            - project_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.files.list_file_page_screenshots(
+            id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/files/{id}/page_screenshots"),
+            params=remove_none_from_dict({"project_id": project_id}),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[PageScreenshotMetadata], _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_file_page_screenshot(
+        self, id: str, page_index: int, *, project_id: typing.Optional[str] = None
+    ) -> typing.Any:
+        """
+        Get screenshot of a page from a file.
+
+        Parameters:
+            - id: str.
+
+            - page_index: int.
+
+            - project_id: typing.Optional[str].
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.files.get_file_page_screenshot(
+            id="string",
+            page_index=1,
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "GET",
+            urllib.parse.urljoin(
+                f"{self._client_wrapper.get_base_url()}/", f"api/v1/files/{id}/page_screenshots/{page_index}"
+            ),
+            params=remove_none_from_dict({"project_id": project_id}),
+            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)

llama_cloud/resources/parsing/client.py

@@ -118,7 +118,12 @@ class ParsingClient:
         vendor_multimodal_api_key: str,
         page_prefix: str,
         page_suffix: str,
+        webhook_url: str,
         take_screenshot: bool,
+        disable_ocr: bool,
+        disable_reconstruction: bool,
+        input_s_3_path: str,
+        output_s_3_path_prefix: str,
         file: typing.IO,
     ) -> ParsingJob:
         """
@@ -159,8 +164,18 @@ class ParsingClient:
 
             - page_suffix: str.
 
+            - webhook_url: str.
+
             - take_screenshot: bool.
 
+            - disable_ocr: bool.
+
+            - disable_reconstruction: bool.
+
+            - input_s_3_path: str.
+
+            - output_s_3_path_prefix: str.
+
             - file: typing.IO.
         """
         _response = self._client_wrapper.httpx_client.request(
@@ -185,7 +200,12 @@ class ParsingClient:
                     "vendor_multimodal_api_key": vendor_multimodal_api_key,
                     "page_prefix": page_prefix,
                     "page_suffix": page_suffix,
+                    "webhook_url": webhook_url,
                     "take_screenshot": take_screenshot,
+                    "disable_ocr": disable_ocr,
+                    "disable_reconstruction": disable_reconstruction,
+                    "input_s3_path": input_s_3_path,
+                    "output_s3_path_prefix": output_s_3_path_prefix,
                 }
             ),
             files={"file": file},
@@ -647,7 +667,12 @@ class AsyncParsingClient:
         vendor_multimodal_api_key: str,
         page_prefix: str,
         page_suffix: str,
+        webhook_url: str,
         take_screenshot: bool,
+        disable_ocr: bool,
+        disable_reconstruction: bool,
+        input_s_3_path: str,
+        output_s_3_path_prefix: str,
         file: typing.IO,
     ) -> ParsingJob:
         """
@@ -688,8 +713,18 @@ class AsyncParsingClient:
 
             - page_suffix: str.
 
+            - webhook_url: str.
+
             - take_screenshot: bool.
 
+            - disable_ocr: bool.
+
+            - disable_reconstruction: bool.
+
+            - input_s_3_path: str.
+
+            - output_s_3_path_prefix: str.
+
             - file: typing.IO.
         """
         _response = await self._client_wrapper.httpx_client.request(
@@ -714,7 +749,12 @@ class AsyncParsingClient:
                     "vendor_multimodal_api_key": vendor_multimodal_api_key,
                     "page_prefix": page_prefix,
                     "page_suffix": page_suffix,
+                    "webhook_url": webhook_url,
                     "take_screenshot": take_screenshot,
+                    "disable_ocr": disable_ocr,
+                    "disable_reconstruction": disable_reconstruction,
+                    "input_s3_path": input_s_3_path,
+                    "output_s3_path_prefix": output_s_3_path_prefix,
                 }
             ),
             files={"file": file},

llama_cloud/resources/pipelines/__init__.py

@@ -9,6 +9,7 @@ from .types import (
     PipelineUpdateEmbeddingConfig_GeminiEmbedding,
     PipelineUpdateEmbeddingConfig_HuggingfaceApiEmbedding,
     PipelineUpdateEmbeddingConfig_OpenaiEmbedding,
+    PipelineUpdateEmbeddingConfig_VertexaiEmbedding,
     PipelineUpdateTransformConfig,
     PipelineUpdateTransformConfig_Advanced,
     PipelineUpdateTransformConfig_Auto,
@@ -23,6 +24,7 @@ __all__ = [
     "PipelineUpdateEmbeddingConfig_GeminiEmbedding",
     "PipelineUpdateEmbeddingConfig_HuggingfaceApiEmbedding",
     "PipelineUpdateEmbeddingConfig_OpenaiEmbedding",
+    "PipelineUpdateEmbeddingConfig_VertexaiEmbedding",
     "PipelineUpdateTransformConfig",
     "PipelineUpdateTransformConfig_Advanced",
     "PipelineUpdateTransformConfig_Auto",