llama-cloud 0.1.10__tar.gz → 0.1.12__tar.gz

{llama_cloud-0.1.10 → llama_cloud-0.1.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-cloud
-Version: 0.1.10
+Version: 0.1.12
 Summary: 
 License: MIT
 Author: Logan Markewich
@@ -13,8 +13,7 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: certifi (>=2024.7.4,<2025.0.0)
+Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: httpx (>=0.20.0)
 Requires-Dist: pydantic (>=1.10)
 Description-Content-Type: text/markdown

{llama_cloud-0.1.10 → llama_cloud-0.1.12}/llama_cloud/__init__.py

@@ -26,6 +26,7 @@ from .types import (
     ChatApp,
     ChatAppResponse,
     ChatData,
+    ChunkMode,
     CloudAzStorageBlobDataSource,
     CloudAzureAiSearchVectorStore,
     CloudBoxDataSource,
@@ -70,6 +71,7 @@ from .types import (
     DataSourceCustomMetadataValue,
     DataSourceDefinition,
     EditSuggestion,
+    EditSuggestionBlocksItem,
     ElementSegmentationConfig,
     EmbeddingModelConfig,
     EmbeddingModelConfigEmbeddingConfig,
@@ -120,6 +122,7 @@ from .types import (
     ExtractSchemaValidateResponse,
     ExtractSchemaValidateResponseDataSchemaValue,
     ExtractState,
+    ExtractTarget,
     File,
     FilePermissionInfoValue,
     FileResourceInfoValue,
@@ -237,6 +240,7 @@ from .types import (
     ProgressEventStatus,
     Project,
     ProjectCreate,
+    PromptConf,
     PromptMixinPrompts,
     PromptSpec,
     PydanticProgramMode,
@@ -252,7 +256,6 @@ from .types import (
     ReportEventItemEventData_ReportBlockUpdate,
     ReportEventItemEventData_ReportStateUpdate,
     ReportEventType,
-    ReportFileInfo,
     ReportMetadata,
     ReportPlan,
     ReportPlanBlock,
@@ -267,10 +270,13 @@ from .types import (
     RetrieverCreate,
     RetrieverPipeline,
     Role,
+    SchemaRelaxMode,
     SemanticChunkingConfig,
     SentenceChunkingConfig,
     SentenceSplitter,
     StatusEnum,
+    StructMode,
+    StructParseConf,
     SupportedLlmModel,
     SupportedLlmModelNames,
     TextBlock,
@@ -370,6 +376,7 @@ __all__ = [
     "ChatApp",
     "ChatAppResponse",
     "ChatData",
+    "ChunkMode",
     "CloudAzStorageBlobDataSource",
     "CloudAzureAiSearchVectorStore",
     "CloudBoxDataSource",
@@ -417,6 +424,7 @@ __all__ = [
     "DataSourceUpdateComponent",
     "DataSourceUpdateCustomMetadataValue",
     "EditSuggestion",
+    "EditSuggestionBlocksItem",
     "ElementSegmentationConfig",
     "EmbeddingModelConfig",
     "EmbeddingModelConfigCreateEmbeddingConfig",
@@ -481,6 +489,7 @@ __all__ = [
     "ExtractSchemaValidateResponse",
     "ExtractSchemaValidateResponseDataSchemaValue",
     "ExtractState",
+    "ExtractTarget",
     "File",
     "FileCreateFromUrlResourceInfoValue",
     "FileCreatePermissionInfoValue",
@@ -612,6 +621,7 @@ __all__ = [
     "ProgressEventStatus",
     "Project",
     "ProjectCreate",
+    "PromptConf",
     "PromptMixinPrompts",
     "PromptSpec",
     "PydanticProgramMode",
@@ -627,7 +637,6 @@ __all__ = [
     "ReportEventItemEventData_ReportBlockUpdate",
     "ReportEventItemEventData_ReportStateUpdate",
     "ReportEventType",
-    "ReportFileInfo",
     "ReportMetadata",
     "ReportPlan",
     "ReportPlanBlock",
@@ -642,10 +651,13 @@ __all__ = [
     "RetrieverCreate",
     "RetrieverPipeline",
     "Role",
+    "SchemaRelaxMode",
     "SemanticChunkingConfig",
     "SentenceChunkingConfig",
     "SentenceSplitter",
     "StatusEnum",
+    "StructMode",
+    "StructParseConf",
     "SupportedLlmModel",
     "SupportedLlmModelNames",
     "TextBlock",

{llama_cloud-0.1.10 → llama_cloud-0.1.12}/llama_cloud/resources/files/client.py

@@ -151,6 +151,7 @@ class FilesClient:
     def upload_file(
         self,
         *,
+        external_file_id: typing.Optional[str] = None,
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
         upload_file: typing.IO,
@@ -159,6 +160,8 @@ class FilesClient:
         Upload a file to S3.
 
         Parameters:
+            - external_file_id: typing.Optional[str].
+
             - project_id: typing.Optional[str].
 
             - organization_id: typing.Optional[str].
@@ -168,7 +171,9 @@ class FilesClient:
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/files"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            params=remove_none_from_dict(
+                {"external_file_id": external_file_id, "project_id": project_id, "organization_id": organization_id}
+            ),
             data=jsonable_encoder({}),
             files={"upload_file": upload_file},
             headers=self._client_wrapper.get_headers(),
@@ -766,6 +771,7 @@ class AsyncFilesClient:
     async def upload_file(
         self,
         *,
+        external_file_id: typing.Optional[str] = None,
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
         upload_file: typing.IO,
@@ -774,6 +780,8 @@ class AsyncFilesClient:
         Upload a file to S3.
 
         Parameters:
+            - external_file_id: typing.Optional[str].
+
             - project_id: typing.Optional[str].
 
             - organization_id: typing.Optional[str].
@@ -783,7 +791,9 @@ class AsyncFilesClient:
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/files"),
-            params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
+            params=remove_none_from_dict(
+                {"external_file_id": external_file_id, "project_id": project_id, "organization_id": organization_id}
+            ),
             data=jsonable_encoder({}),
             files={"upload_file": upload_file},
             headers=self._client_wrapper.get_headers(),

{llama_cloud-0.1.10 → llama_cloud-0.1.12}/llama_cloud/resources/llama_extract/client.py

@@ -88,7 +88,7 @@ class LlamaExtractClient:
 
             - config: ExtractConfig. The configuration parameters for the extraction agent.
         ---
-        from llama_cloud import ExtractConfig, ExtractMode
+        from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
@@ -97,7 +97,8 @@ class LlamaExtractClient:
         client.llama_extract.create_extraction_agent(
             name="string",
             config=ExtractConfig(
-                extraction_mode=ExtractMode.PER_DOC,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
             ),
         )
         """
@@ -234,7 +235,7 @@ class LlamaExtractClient:
 
             - config: ExtractConfig. The configuration parameters for the extraction agent.
         ---
-        from llama_cloud import ExtractConfig, ExtractMode
+        from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
@@ -243,7 +244,8 @@ class LlamaExtractClient:
         client.llama_extract.update_extraction_agent(
             extraction_agent_id="string",
             config=ExtractConfig(
-                extraction_mode=ExtractMode.PER_DOC,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
             ),
         )
         """
@@ -336,7 +338,12 @@ class LlamaExtractClient:
         Parameters:
             - request: ExtractJobCreate.
         ---
-        from llama_cloud import ExtractConfig, ExtractJobCreate, ExtractMode
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreate,
+            ExtractMode,
+            ExtractTarget,
+        )
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
@@ -347,7 +354,8 @@ class LlamaExtractClient:
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
-                    extraction_mode=ExtractMode.PER_DOC,
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
                 ),
             ),
         )
@@ -409,9 +417,11 @@ class LlamaExtractClient:
             - extract_settings: typing.Optional[LlamaExtractSettings].
         ---
         from llama_cloud import (
+            ChunkMode,
             ExtractConfig,
             ExtractJobCreate,
             ExtractMode,
+            ExtractTarget,
             LlamaExtractSettings,
             LlamaParseParameters,
         )
@@ -425,10 +435,12 @@ class LlamaExtractClient:
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
-                    extraction_mode=ExtractMode.PER_DOC,
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
                 ),
             ),
             extract_settings=LlamaExtractSettings(
+                chunk_mode=ChunkMode.PAGE,
                 llama_parse_params=LlamaParseParameters(),
             ),
         )
@@ -458,7 +470,12 @@ class LlamaExtractClient:
         Parameters:
             - request: ExtractJobCreate.
         ---
-        from llama_cloud import ExtractConfig, ExtractJobCreate, ExtractMode
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreate,
+            ExtractMode,
+            ExtractTarget,
+        )
         from llama_cloud.client import LlamaCloud
 
         client = LlamaCloud(
@@ -469,7 +486,8 @@ class LlamaExtractClient:
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
-                    extraction_mode=ExtractMode.PER_DOC,
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
                 ),
             ),
         )
@@ -501,9 +519,11 @@ class LlamaExtractClient:
             - extract_settings: typing.Optional[LlamaExtractSettings].
         ---
         from llama_cloud import (
+            ChunkMode,
             ExtractConfig,
             ExtractJobCreate,
             ExtractMode,
+            ExtractTarget,
             LlamaExtractSettings,
             LlamaParseParameters,
         )
@@ -517,10 +537,12 @@ class LlamaExtractClient:
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
-                    extraction_mode=ExtractMode.PER_DOC,
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
                 ),
             ),
             extract_settings=LlamaExtractSettings(
+                chunk_mode=ChunkMode.PAGE,
                 llama_parse_params=LlamaParseParameters(),
             ),
         )
@@ -725,7 +747,7 @@ class AsyncLlamaExtractClient:
 
             - config: ExtractConfig. The configuration parameters for the extraction agent.
         ---
-        from llama_cloud import ExtractConfig, ExtractMode
+        from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
@@ -734,7 +756,8 @@ class AsyncLlamaExtractClient:
         await client.llama_extract.create_extraction_agent(
             name="string",
             config=ExtractConfig(
-                extraction_mode=ExtractMode.PER_DOC,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
             ),
         )
         """
@@ -871,7 +894,7 @@ class AsyncLlamaExtractClient:
 
             - config: ExtractConfig. The configuration parameters for the extraction agent.
         ---
-        from llama_cloud import ExtractConfig, ExtractMode
+        from llama_cloud import ExtractConfig, ExtractMode, ExtractTarget
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
@@ -880,7 +903,8 @@ class AsyncLlamaExtractClient:
         await client.llama_extract.update_extraction_agent(
             extraction_agent_id="string",
             config=ExtractConfig(
-                extraction_mode=ExtractMode.PER_DOC,
+                extraction_target=ExtractTarget.PER_DOC,
+                extraction_mode=ExtractMode.FAST,
             ),
         )
         """
@@ -973,7 +997,12 @@ class AsyncLlamaExtractClient:
         Parameters:
             - request: ExtractJobCreate.
         ---
-        from llama_cloud import ExtractConfig, ExtractJobCreate, ExtractMode
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreate,
+            ExtractMode,
+            ExtractTarget,
+        )
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
@@ -984,7 +1013,8 @@ class AsyncLlamaExtractClient:
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
-                    extraction_mode=ExtractMode.PER_DOC,
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
                 ),
             ),
         )
@@ -1046,9 +1076,11 @@ class AsyncLlamaExtractClient:
             - extract_settings: typing.Optional[LlamaExtractSettings].
         ---
         from llama_cloud import (
+            ChunkMode,
             ExtractConfig,
             ExtractJobCreate,
             ExtractMode,
+            ExtractTarget,
             LlamaExtractSettings,
             LlamaParseParameters,
         )
@@ -1062,10 +1094,12 @@ class AsyncLlamaExtractClient:
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
-                    extraction_mode=ExtractMode.PER_DOC,
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
                 ),
             ),
             extract_settings=LlamaExtractSettings(
+                chunk_mode=ChunkMode.PAGE,
                 llama_parse_params=LlamaParseParameters(),
             ),
         )
@@ -1095,7 +1129,12 @@ class AsyncLlamaExtractClient:
         Parameters:
             - request: ExtractJobCreate.
         ---
-        from llama_cloud import ExtractConfig, ExtractJobCreate, ExtractMode
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreate,
+            ExtractMode,
+            ExtractTarget,
+        )
         from llama_cloud.client import AsyncLlamaCloud
 
         client = AsyncLlamaCloud(
@@ -1106,7 +1145,8 @@ class AsyncLlamaExtractClient:
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
-                    extraction_mode=ExtractMode.PER_DOC,
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
                 ),
             ),
         )
@@ -1138,9 +1178,11 @@ class AsyncLlamaExtractClient:
             - extract_settings: typing.Optional[LlamaExtractSettings].
         ---
         from llama_cloud import (
+            ChunkMode,
             ExtractConfig,
             ExtractJobCreate,
             ExtractMode,
+            ExtractTarget,
             LlamaExtractSettings,
             LlamaParseParameters,
         )
@@ -1154,10 +1196,12 @@ class AsyncLlamaExtractClient:
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
-                    extraction_mode=ExtractMode.PER_DOC,
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
                 ),
             ),
             extract_settings=LlamaExtractSettings(
+                chunk_mode=ChunkMode.PAGE,
                 llama_parse_params=LlamaParseParameters(),
             ),
         )

{llama_cloud-0.1.10 → llama_cloud-0.1.12}/llama_cloud/resources/parsing/client.py

@@ -100,6 +100,96 @@ class ParsingClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def screenshot(
+        self,
+        *,
+        organization_id: typing.Optional[str] = None,
+        project_id: typing.Optional[str] = None,
+        file: typing.Optional[str] = OMIT,
+        do_not_cache: bool,
+        http_proxy: str,
+        input_s_3_path: str,
+        input_s_3_region: str,
+        input_url: str,
+        invalidate_cache: bool,
+        max_pages: typing.Optional[int] = OMIT,
+        output_s_3_path_prefix: str,
+        output_s_3_region: str,
+        target_pages: str,
+        webhook_url: str,
+        job_timeout_in_seconds: float,
+        job_timeout_extra_time_per_page_in_seconds: float,
+    ) -> ParsingJob:
+        """
+        Parameters:
+            - organization_id: typing.Optional[str].
+
+            - project_id: typing.Optional[str].
+
+            - file: typing.Optional[str].
+
+            - do_not_cache: bool.
+
+            - http_proxy: str.
+
+            - input_s_3_path: str.
+
+            - input_s_3_region: str.
+
+            - input_url: str.
+
+            - invalidate_cache: bool.
+
+            - max_pages: typing.Optional[int].
+
+            - output_s_3_path_prefix: str.
+
+            - output_s_3_region: str.
+
+            - target_pages: str.
+
+            - webhook_url: str.
+
+            - job_timeout_in_seconds: float.
+
+            - job_timeout_extra_time_per_page_in_seconds: float.
+        """
+        _request: typing.Dict[str, typing.Any] = {
+            "do_not_cache": do_not_cache,
+            "http_proxy": http_proxy,
+            "input_s3_path": input_s_3_path,
+            "input_s3_region": input_s_3_region,
+            "input_url": input_url,
+            "invalidate_cache": invalidate_cache,
+            "output_s3_path_prefix": output_s_3_path_prefix,
+            "output_s3_region": output_s_3_region,
+            "target_pages": target_pages,
+            "webhook_url": webhook_url,
+            "job_timeout_in_seconds": job_timeout_in_seconds,
+            "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds,
+        }
+        if file is not OMIT:
+            _request["file"] = file
+        if max_pages is not OMIT:
+            _request["max_pages"] = max_pages
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/screenshot"),
+            params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ParsingJob, _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 upload_file(
         self,
         *,
@@ -957,6 +1047,96 @@ class AsyncParsingClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def screenshot(
+        self,
+        *,
+        organization_id: typing.Optional[str] = None,
+        project_id: typing.Optional[str] = None,
+        file: typing.Optional[str] = OMIT,
+        do_not_cache: bool,
+        http_proxy: str,
+        input_s_3_path: str,
+        input_s_3_region: str,
+        input_url: str,
+        invalidate_cache: bool,
+        max_pages: typing.Optional[int] = OMIT,
+        output_s_3_path_prefix: str,
+        output_s_3_region: str,
+        target_pages: str,
+        webhook_url: str,
+        job_timeout_in_seconds: float,
+        job_timeout_extra_time_per_page_in_seconds: float,
+    ) -> ParsingJob:
+        """
+        Parameters:
+            - organization_id: typing.Optional[str].
+
+            - project_id: typing.Optional[str].
+
+            - file: typing.Optional[str].
+
+            - do_not_cache: bool.
+
+            - http_proxy: str.
+
+            - input_s_3_path: str.
+
+            - input_s_3_region: str.
+
+            - input_url: str.
+
+            - invalidate_cache: bool.
+
+            - max_pages: typing.Optional[int].
+
+            - output_s_3_path_prefix: str.
+
+            - output_s_3_region: str.
+
+            - target_pages: str.
+
+            - webhook_url: str.
+
+            - job_timeout_in_seconds: float.
+
+            - job_timeout_extra_time_per_page_in_seconds: float.
+        """
+        _request: typing.Dict[str, typing.Any] = {
+            "do_not_cache": do_not_cache,
+            "http_proxy": http_proxy,
+            "input_s3_path": input_s_3_path,
+            "input_s3_region": input_s_3_region,
+            "input_url": input_url,
+            "invalidate_cache": invalidate_cache,
+            "output_s3_path_prefix": output_s_3_path_prefix,
+            "output_s3_region": output_s_3_region,
+            "target_pages": target_pages,
+            "webhook_url": webhook_url,
+            "job_timeout_in_seconds": job_timeout_in_seconds,
+            "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds,
+        }
+        if file is not OMIT:
+            _request["file"] = file
+        if max_pages is not OMIT:
+            _request["max_pages"] = max_pages
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/screenshot"),
+            params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}),
+            json=jsonable_encoder(_request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(ParsingJob, _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 upload_file(
         self,
         *,