llama-cloud 0.1.14__tar.gz → 0.1.15__tar.gz

{llama_cloud-0.1.14 → llama_cloud-0.1.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-cloud
-Version: 0.1.14
+Version: 0.1.15
 Summary: 
 License: MIT
 Author: Logan Markewich

{llama_cloud-0.1.14 → llama_cloud-0.1.15}/llama_cloud/__init__.py

@@ -116,6 +116,9 @@ from .types import (
     ExtractConfig,
     ExtractJob,
     ExtractJobCreate,
+    ExtractJobCreateBatch,
+    ExtractJobCreateBatchDataSchemaOverride,
+    ExtractJobCreateBatchDataSchemaOverrideZeroValue,
     ExtractJobCreateDataSchemaOverride,
     ExtractJobCreateDataSchemaOverrideZeroValue,
     ExtractMode,
@@ -194,6 +197,7 @@ from .types import (
     PageScreenshotNodeWithScore,
     PageSegmentationConfig,
     PageSplitterNodeParser,
+    PaginatedExtractRunsResponse,
     PaginatedJobsHistoryWithMetrics,
     PaginatedListCloudDocumentsResponse,
     PaginatedListPipelineFilesResponse,
@@ -490,6 +494,9 @@ __all__ = [
     "ExtractConfig",
     "ExtractJob",
     "ExtractJobCreate",
+    "ExtractJobCreateBatch",
+    "ExtractJobCreateBatchDataSchemaOverride",
+    "ExtractJobCreateBatchDataSchemaOverrideZeroValue",
     "ExtractJobCreateDataSchemaOverride",
     "ExtractJobCreateDataSchemaOverrideZeroValue",
     "ExtractMode",
@@ -572,6 +579,7 @@ __all__ = [
     "PageScreenshotNodeWithScore",
     "PageSegmentationConfig",
     "PageSplitterNodeParser",
+    "PaginatedExtractRunsResponse",
     "PaginatedJobsHistoryWithMetrics",
     "PaginatedListCloudDocumentsResponse",
     "PaginatedListPipelineFilesResponse",

{llama_cloud-0.1.14 → llama_cloud-0.1.15}/llama_cloud/resources/llama_extract/client.py

@@ -14,12 +14,14 @@ from ...types.extract_agent_create import ExtractAgentCreate
 from ...types.extract_agent_update import ExtractAgentUpdate
 from ...types.extract_job import ExtractJob
 from ...types.extract_job_create import ExtractJobCreate
+from ...types.extract_job_create_batch import ExtractJobCreateBatch
 from ...types.extract_resultset import ExtractResultset
 from ...types.extract_run import ExtractRun
 from ...types.extract_schema_validate_request import ExtractSchemaValidateRequest
 from ...types.extract_schema_validate_response import ExtractSchemaValidateResponse
 from ...types.http_validation_error import HttpValidationError
 from ...types.llama_extract_settings import LlamaExtractSettings
+from ...types.paginated_extract_runs_response import PaginatedExtractRunsResponse
 
 try:
     import pydantic
@@ -469,6 +471,50 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def run_batch_jobs(self, *, request: ExtractJobCreateBatch) -> typing.List[ExtractJob]:
+        """
+        Parameters:
+            - request: ExtractJobCreateBatch.
+        ---
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreateBatch,
+            ExtractMode,
+            ExtractTarget,
+        )
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.llama_extract.run_batch_jobs(
+            request=ExtractJobCreateBatch(
+                extraction_agent_id="string",
+                file_ids=[],
+                config_override=ExtractConfig(
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
+                ),
+            ),
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"),
+            json=jsonable_encoder(request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[ExtractJob], _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_job_result(self, job_id: str) -> ExtractResultset:
         """
         Parameters:
@@ -499,10 +545,16 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    def list_extract_runs(self, *, extraction_agent_id: str) -> typing.List[ExtractRun]:
+    def list_extract_runs(
+        self, *, extraction_agent_id: str, skip: typing.Optional[int] = None, limit: typing.Optional[int] = None
+    ) -> PaginatedExtractRunsResponse:
         """
         Parameters:
             - extraction_agent_id: str.
+
+            - skip: typing.Optional[int].
+
+            - limit: typing.Optional[int].
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -516,12 +568,12 @@ class LlamaExtractClient:
         _response = self._client_wrapper.httpx_client.request(
             "GET",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"),
-            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
+            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id, "skip": skip, "limit": limit}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.List[ExtractRun], _response.json())  # type: ignore
+            return pydantic.parse_obj_as(PaginatedExtractRunsResponse, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -590,6 +642,36 @@ class LlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def delete_extraction_run(self, run_id: str) -> typing.Any:
+        """
+        Parameters:
+            - run_id: str.
+        ---
+        from llama_cloud.client import LlamaCloud
+
+        client = LlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        client.llama_extract.delete_extraction_run(
+            run_id="string",
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            "DELETE",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_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 AsyncLlamaExtractClient:
     def __init__(self, *, client_wrapper: AsyncClientWrapper):
@@ -1029,6 +1111,50 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def run_batch_jobs(self, *, request: ExtractJobCreateBatch) -> typing.List[ExtractJob]:
+        """
+        Parameters:
+            - request: ExtractJobCreateBatch.
+        ---
+        from llama_cloud import (
+            ExtractConfig,
+            ExtractJobCreateBatch,
+            ExtractMode,
+            ExtractTarget,
+        )
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.llama_extract.run_batch_jobs(
+            request=ExtractJobCreateBatch(
+                extraction_agent_id="string",
+                file_ids=[],
+                config_override=ExtractConfig(
+                    extraction_target=ExtractTarget.PER_DOC,
+                    extraction_mode=ExtractMode.FAST,
+                ),
+            ),
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "POST",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/batch"),
+            json=jsonable_encoder(request),
+            headers=self._client_wrapper.get_headers(),
+            timeout=60,
+        )
+        if 200 <= _response.status_code < 300:
+            return pydantic.parse_obj_as(typing.List[ExtractJob], _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_job_result(self, job_id: str) -> ExtractResultset:
         """
         Parameters:
@@ -1059,10 +1185,16 @@ class AsyncLlamaExtractClient:
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
-    async def list_extract_runs(self, *, extraction_agent_id: str) -> typing.List[ExtractRun]:
+    async def list_extract_runs(
+        self, *, extraction_agent_id: str, skip: typing.Optional[int] = None, limit: typing.Optional[int] = None
+    ) -> PaginatedExtractRunsResponse:
         """
         Parameters:
             - extraction_agent_id: str.
+
+            - skip: typing.Optional[int].
+
+            - limit: typing.Optional[int].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1076,12 +1208,12 @@ class AsyncLlamaExtractClient:
         _response = await self._client_wrapper.httpx_client.request(
             "GET",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"),
-            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
+            params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id, "skip": skip, "limit": limit}),
             headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
-            return pydantic.parse_obj_as(typing.List[ExtractRun], _response.json())  # type: ignore
+            return pydantic.parse_obj_as(PaginatedExtractRunsResponse, _response.json())  # type: ignore
         if _response.status_code == 422:
             raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json()))  # type: ignore
         try:
@@ -1149,3 +1281,33 @@ class AsyncLlamaExtractClient:
         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_extraction_run(self, run_id: str) -> typing.Any:
+        """
+        Parameters:
+            - run_id: str.
+        ---
+        from llama_cloud.client import AsyncLlamaCloud
+
+        client = AsyncLlamaCloud(
+            token="YOUR_TOKEN",
+        )
+        await client.llama_extract.delete_extraction_run(
+            run_id="string",
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            "DELETE",
+            urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_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-0.1.14 → llama_cloud-0.1.15}/llama_cloud/resources/parsing/client.py

@@ -212,7 +212,6 @@ class ParsingClient:
         bbox_left: float,
         bbox_right: float,
         bbox_top: float,
-        compact_markdown_table: bool,
         disable_ocr: bool,
         disable_reconstruction: bool,
         disable_image_extraction: bool,
@@ -314,8 +313,6 @@ class ParsingClient:
 
             - bbox_top: float.
 
-            - compact_markdown_table: bool.
-
             - disable_ocr: bool.
 
             - disable_reconstruction: bool.
@@ -452,7 +449,6 @@ class ParsingClient:
             "bbox_left": bbox_left,
             "bbox_right": bbox_right,
             "bbox_top": bbox_top,
-            "compact_markdown_table": compact_markdown_table,
             "disable_ocr": disable_ocr,
             "disable_reconstruction": disable_reconstruction,
             "disable_image_extraction": disable_image_extraction,
@@ -1192,7 +1188,6 @@ class AsyncParsingClient:
         bbox_left: float,
         bbox_right: float,
         bbox_top: float,
-        compact_markdown_table: bool,
         disable_ocr: bool,
         disable_reconstruction: bool,
         disable_image_extraction: bool,
@@ -1294,8 +1289,6 @@ class AsyncParsingClient:
 
             - bbox_top: float.
 
-            - compact_markdown_table: bool.
-
             - disable_ocr: bool.
 
             - disable_reconstruction: bool.
@@ -1432,7 +1425,6 @@ class AsyncParsingClient:
             "bbox_left": bbox_left,
             "bbox_right": bbox_right,
             "bbox_top": bbox_top,
-            "compact_markdown_table": compact_markdown_table,
             "disable_ocr": disable_ocr,
             "disable_reconstruction": disable_reconstruction,
             "disable_image_extraction": disable_image_extraction,

{llama_cloud-0.1.14 → llama_cloud-0.1.15}/llama_cloud/types/__init__.py

@@ -123,6 +123,9 @@ from .extract_agent_update_data_schema_zero_value import ExtractAgentUpdateDataS
 from .extract_config import ExtractConfig
 from .extract_job import ExtractJob
 from .extract_job_create import ExtractJobCreate
+from .extract_job_create_batch import ExtractJobCreateBatch
+from .extract_job_create_batch_data_schema_override import ExtractJobCreateBatchDataSchemaOverride
+from .extract_job_create_batch_data_schema_override_zero_value import ExtractJobCreateBatchDataSchemaOverrideZeroValue
 from .extract_job_create_data_schema_override import ExtractJobCreateDataSchemaOverride
 from .extract_job_create_data_schema_override_zero_value import ExtractJobCreateDataSchemaOverrideZeroValue
 from .extract_mode import ExtractMode
@@ -203,6 +206,7 @@ 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 .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
@@ -451,6 +455,9 @@ __all__ = [
     "ExtractConfig",
     "ExtractJob",
     "ExtractJobCreate",
+    "ExtractJobCreateBatch",
+    "ExtractJobCreateBatchDataSchemaOverride",
+    "ExtractJobCreateBatchDataSchemaOverrideZeroValue",
     "ExtractJobCreateDataSchemaOverride",
     "ExtractJobCreateDataSchemaOverrideZeroValue",
     "ExtractMode",
@@ -529,6 +536,7 @@ __all__ = [
     "PageScreenshotNodeWithScore",
     "PageSegmentationConfig",
     "PageSplitterNodeParser",
+    "PaginatedExtractRunsResponse",
     "PaginatedJobsHistoryWithMetrics",
     "PaginatedListCloudDocumentsResponse",
     "PaginatedListPipelineFilesResponse",

{llama_cloud-0.1.14 → llama_cloud-0.1.15}/llama_cloud/types/chunk_mode.py

@@ -10,12 +10,14 @@ class ChunkMode(str, enum.Enum):
     PAGE = "PAGE"
     DOCUMENT = "DOCUMENT"
     SECTION = "SECTION"
+    GROUPED_PAGES = "GROUPED_PAGES"
 
     def visit(
         self,
         page: typing.Callable[[], T_Result],
         document: typing.Callable[[], T_Result],
         section: typing.Callable[[], T_Result],
+        grouped_pages: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is ChunkMode.PAGE:
             return page()
@@ -23,3 +25,5 @@ class ChunkMode(str, enum.Enum):
             return document()
         if self is ChunkMode.SECTION:
             return section()
+        if self is ChunkMode.GROUPED_PAGES:
+            return grouped_pages()

llama_cloud-0.1.15/llama_cloud/types/extract_job_create_batch.py

@@ -0,0 +1,42 @@
+# 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 .extract_config import ExtractConfig
+from .extract_job_create_batch_data_schema_override import ExtractJobCreateBatchDataSchemaOverride
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class ExtractJobCreateBatch(pydantic.BaseModel):
+    """
+    Schema for creating extraction jobs in batch.
+    """
+
+    extraction_agent_id: str = pydantic.Field(description="The id of the extraction agent")
+    file_ids: typing.List[str] = pydantic.Field(description="The ids of the files")
+    data_schema_override: typing.Optional[ExtractJobCreateBatchDataSchemaOverride] = pydantic.Field(
+        description="The data schema to override the extraction agent's data schema with"
+    )
+    config_override: typing.Optional[ExtractConfig]
+
+    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-0.1.15/llama_cloud/types/extract_job_create_batch_data_schema_override.py

@@ -0,0 +1,9 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+from .extract_job_create_batch_data_schema_override_zero_value import ExtractJobCreateBatchDataSchemaOverrideZeroValue
+
+ExtractJobCreateBatchDataSchemaOverride = typing.Union[
+    typing.Dict[str, typing.Optional[ExtractJobCreateBatchDataSchemaOverrideZeroValue]], str
+]

llama_cloud-0.1.15/llama_cloud/types/extract_job_create_batch_data_schema_override_zero_value.py

@@ -0,0 +1,7 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+ExtractJobCreateBatchDataSchemaOverrideZeroValue = typing.Union[
+    typing.Dict[str, typing.Any], typing.List[typing.Any], str, int, float, bool
+]

{llama_cloud-0.1.14 → llama_cloud-0.1.15}/llama_cloud/types/llama_parse_parameters.py

@@ -26,7 +26,6 @@ class LlamaParseParameters(pydantic.BaseModel):
     disable_ocr: typing.Optional[bool]
     annotate_links: typing.Optional[bool]
     adaptive_long_table: typing.Optional[bool]
-    compact_markdown_table: typing.Optional[bool]
     disable_reconstruction: typing.Optional[bool]
     disable_image_extraction: typing.Optional[bool]
     invalidate_cache: typing.Optional[bool]

llama_cloud-0.1.15/llama_cloud/types/paginated_extract_runs_response.py

@@ -0,0 +1,39 @@
+# 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 .extract_run import ExtractRun
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class PaginatedExtractRunsResponse(pydantic.BaseModel):
+    """
+    Schema for paginated extraction runs response.
+    """
+
+    items: typing.List[ExtractRun] = pydantic.Field(description="The list of extraction runs")
+    total: int = pydantic.Field(description="The total number of extraction runs")
+    skip: int = pydantic.Field(description="The number of extraction runs skipped")
+    limit: int = pydantic.Field(description="The maximum number of extraction runs returned")
+
+    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-0.1.14 → llama_cloud-0.1.15}/llama_cloud/types/usage.py

@@ -18,7 +18,7 @@ except ImportError:
 
 class Usage(pydantic.BaseModel):
     """
-    Response model; use UsageSubmission for tracking
+    Response model
     """
 
     active_free_credits_usage: typing.Optional[typing.List[FreeCreditsUsage]]
@@ -27,6 +27,7 @@ class Usage(pydantic.BaseModel):
     total_indexed_pages: typing.Optional[int]
     active_alerts: typing.Optional[typing.List[UsageActiveAlertsItem]]
     current_invoice_total_usd_cents: typing.Optional[int]
+    total_extraction_agents: typing.Optional[int]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

{llama_cloud-0.1.14 → llama_cloud-0.1.15}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "llama-cloud"
-version = "0.1.14"
+version = "0.1.15"
 description = ""
 authors = ["Logan Markewich <logan@runllama.ai>"]
 readme = "README.md"