llama-cloud 0.1.38__py3-none-any.whl → 0.1.40__py3-none-any.whl

llama_cloud/resources/organizations/client.py

@@ -657,12 +657,7 @@ class OrganizationsClient:
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
     def add_user_to_project(
-        self,
-        organization_id: typing.Optional[str],
-        user_id: str,
-        *,
-        project_id: typing.Optional[str] = None,
-        project_id: typing.Optional[str] = None,
+        self, organization_id: typing.Optional[str], user_id: str, *, project_id: typing.Optional[str] = None
     ) -> typing.Any:
         """
         Add a user to a project.
@@ -673,8 +668,6 @@ class OrganizationsClient:
             - user_id: str.
 
             - project_id: typing.Optional[str].
-
-            - project_id: typing.Optional[str].
         ---
         from llama_cloud.client import LlamaCloud
 
@@ -692,7 +685,7 @@ class OrganizationsClient:
                 f"api/v1/organizations/{organization_id}/users/{user_id}/projects",
             ),
             params=remove_none_from_dict({"project_id": project_id}),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -1372,12 +1365,7 @@ class AsyncOrganizationsClient:
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
     async def add_user_to_project(
-        self,
-        organization_id: typing.Optional[str],
-        user_id: str,
-        *,
-        project_id: typing.Optional[str] = None,
-        project_id: typing.Optional[str] = None,
+        self, organization_id: typing.Optional[str], user_id: str, *, project_id: typing.Optional[str] = None
     ) -> typing.Any:
         """
         Add a user to a project.
@@ -1388,8 +1376,6 @@ class AsyncOrganizationsClient:
             - user_id: str.
 
             - project_id: typing.Optional[str].
-
-            - project_id: typing.Optional[str].
         ---
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1407,7 +1393,7 @@ class AsyncOrganizationsClient:
                 f"api/v1/organizations/{organization_id}/users/{user_id}/projects",
             ),
             params=remove_none_from_dict({"project_id": project_id}),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:

llama_cloud/resources/parsing/client.py

@@ -121,7 +121,6 @@ class ParsingClient:
         webhook_configurations: str,
         job_timeout_in_seconds: float,
         job_timeout_extra_time_per_page_in_seconds: float,
-        project_id: typing.Optional[str] = None,
     ) -> ParsingJob:
         """
         Parameters:
@@ -158,8 +157,6 @@ class ParsingClient:
             - job_timeout_in_seconds: float.
 
             - job_timeout_extra_time_per_page_in_seconds: float.
-
-            - project_id: typing.Optional[str].
         """
         _request: typing.Dict[str, typing.Any] = {
             "do_not_cache": do_not_cache,
@@ -185,7 +182,7 @@ class ParsingClient:
             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=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -230,6 +227,7 @@ class ParsingClient:
         guess_xlsx_sheet_name: bool,
         high_res_ocr: bool,
         html_make_all_elements_visible: bool,
+        layout_aware: bool,
         html_remove_fixed_elements: bool,
         html_remove_navigation_elements: bool,
         http_proxy: str,
@@ -299,7 +297,6 @@ class ParsingClient:
         page_header_suffix: str,
         page_footer_prefix: str,
         page_footer_suffix: str,
-        project_id: typing.Optional[str] = None,
     ) -> ParsingJob:
         """
         Parameters:
@@ -361,6 +358,8 @@ class ParsingClient:
 
             - html_make_all_elements_visible: bool.
 
+            - layout_aware: bool.
+
             - html_remove_fixed_elements: bool.
 
             - html_remove_navigation_elements: bool.
@@ -498,8 +497,6 @@ class ParsingClient:
             - page_footer_prefix: str.
 
             - page_footer_suffix: str.
-
-            - project_id: typing.Optional[str].
         """
         _request: typing.Dict[str, typing.Any] = {
             "adaptive_long_table": adaptive_long_table,
@@ -528,6 +525,7 @@ class ParsingClient:
             "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
             "high_res_ocr": high_res_ocr,
             "html_make_all_elements_visible": html_make_all_elements_visible,
+            "layout_aware": layout_aware,
             "html_remove_fixed_elements": html_remove_fixed_elements,
             "html_remove_navigation_elements": html_remove_navigation_elements,
             "http_proxy": http_proxy,
@@ -608,7 +606,7 @@ class ParsingClient:
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
             params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}),
             json=jsonable_encoder(_request),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -1299,7 +1297,6 @@ class AsyncParsingClient:
         webhook_configurations: str,
         job_timeout_in_seconds: float,
         job_timeout_extra_time_per_page_in_seconds: float,
-        project_id: typing.Optional[str] = None,
     ) -> ParsingJob:
         """
         Parameters:
@@ -1336,8 +1333,6 @@ class AsyncParsingClient:
             - job_timeout_in_seconds: float.
 
             - job_timeout_extra_time_per_page_in_seconds: float.
-
-            - project_id: typing.Optional[str].
         """
         _request: typing.Dict[str, typing.Any] = {
             "do_not_cache": do_not_cache,
@@ -1363,7 +1358,7 @@ class AsyncParsingClient:
             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=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -1408,6 +1403,7 @@ class AsyncParsingClient:
         guess_xlsx_sheet_name: bool,
         high_res_ocr: bool,
         html_make_all_elements_visible: bool,
+        layout_aware: bool,
         html_remove_fixed_elements: bool,
         html_remove_navigation_elements: bool,
         http_proxy: str,
@@ -1477,7 +1473,6 @@ class AsyncParsingClient:
         page_header_suffix: str,
         page_footer_prefix: str,
         page_footer_suffix: str,
-        project_id: typing.Optional[str] = None,
     ) -> ParsingJob:
         """
         Parameters:
@@ -1539,6 +1534,8 @@ class AsyncParsingClient:
 
             - html_make_all_elements_visible: bool.
 
+            - layout_aware: bool.
+
             - html_remove_fixed_elements: bool.
 
             - html_remove_navigation_elements: bool.
@@ -1676,8 +1673,6 @@ class AsyncParsingClient:
             - page_footer_prefix: str.
 
             - page_footer_suffix: str.
-
-            - project_id: typing.Optional[str].
         """
         _request: typing.Dict[str, typing.Any] = {
             "adaptive_long_table": adaptive_long_table,
@@ -1706,6 +1701,7 @@ class AsyncParsingClient:
             "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
             "high_res_ocr": high_res_ocr,
             "html_make_all_elements_visible": html_make_all_elements_visible,
+            "layout_aware": layout_aware,
             "html_remove_fixed_elements": html_remove_fixed_elements,
             "html_remove_navigation_elements": html_remove_navigation_elements,
             "http_proxy": http_proxy,
@@ -1786,7 +1782,7 @@ class AsyncParsingClient:
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
             params=remove_none_from_dict({"organization_id": organization_id, "project_id": project_id}),
             json=jsonable_encoder(_request),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:

llama_cloud/resources/pipelines/client.py

@@ -35,6 +35,7 @@ from ...types.playground_session import PlaygroundSession
 from ...types.preset_retrieval_params import PresetRetrievalParams
 from ...types.retrieval_mode import RetrievalMode
 from ...types.retrieve_results import RetrieveResults
+from ...types.sparse_model_config import SparseModelConfig
 from ...types.text_node import TextNode
 from .types.pipeline_file_update_custom_metadata_value import PipelineFileUpdateCustomMetadataValue
 from .types.pipeline_update_embedding_config import PipelineUpdateEmbeddingConfig
@@ -67,7 +68,6 @@ class PipelinesClient:
         pipeline_name: typing.Optional[str] = None,
         pipeline_type: typing.Optional[PipelineType] = None,
         organization_id: typing.Optional[str] = None,
-        project_id: typing.Optional[str] = None,
     ) -> typing.List[Pipeline]:
         """
         Search for pipelines by various parameters.
@@ -82,8 +82,6 @@ class PipelinesClient:
             - pipeline_type: typing.Optional[PipelineType].
 
             - organization_id: typing.Optional[str].
-
-            - project_id: typing.Optional[str].
         ---
         from llama_cloud import PipelineType
         from llama_cloud.client import LlamaCloud
@@ -107,7 +105,7 @@ class PipelinesClient:
                     "organization_id": organization_id,
                 }
             ),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -126,7 +124,6 @@ class PipelinesClient:
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
         request: PipelineCreate,
-        project_id: typing.Optional[str] = None,
     ) -> Pipeline:
         """
         Create a new pipeline for a project.
@@ -137,15 +134,13 @@ class PipelinesClient:
             - organization_id: typing.Optional[str].
 
             - request: PipelineCreate.
-
-            - project_id: typing.Optional[str].
         """
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/pipelines"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             json=jsonable_encoder(request),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -164,7 +159,6 @@ class PipelinesClient:
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
         request: PipelineCreate,
-        project_id: typing.Optional[str] = None,
     ) -> Pipeline:
         """
         Upsert a pipeline for a project.
@@ -176,15 +170,13 @@ class PipelinesClient:
             - organization_id: typing.Optional[str].
 
             - request: PipelineCreate.
-
-            - project_id: typing.Optional[str].
         """
         _response = self._client_wrapper.httpx_client.request(
             "PUT",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/pipelines"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             json=jsonable_encoder(request),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -226,6 +218,7 @@ class PipelinesClient:
         *,
         embedding_config: typing.Optional[PipelineUpdateEmbeddingConfig] = OMIT,
         transform_config: typing.Optional[PipelineUpdateTransformConfig] = OMIT,
+        sparse_model_config: typing.Optional[SparseModelConfig] = OMIT,
         data_sink_id: typing.Optional[str] = OMIT,
         embedding_model_config_id: typing.Optional[str] = OMIT,
         data_sink: typing.Optional[DataSinkCreate] = OMIT,
@@ -247,6 +240,8 @@ class PipelinesClient:
 
             - transform_config: typing.Optional[PipelineUpdateTransformConfig]. Configuration for the transformation.
 
+            - sparse_model_config: typing.Optional[SparseModelConfig].
+
             - data_sink_id: typing.Optional[str].
 
             - embedding_model_config_id: typing.Optional[str].
@@ -272,6 +267,8 @@ class PipelinesClient:
             _request["embedding_config"] = embedding_config
         if transform_config is not OMIT:
             _request["transform_config"] = transform_config
+        if sparse_model_config is not OMIT:
+            _request["sparse_model_config"] = sparse_model_config
         if data_sink_id is not OMIT:
             _request["data_sink_id"] = data_sink_id
         if embedding_model_config_id is not OMIT:
@@ -563,6 +560,7 @@ class PipelinesClient:
         *,
         data_source_id: typing.Optional[str] = None,
         only_manually_uploaded: typing.Optional[bool] = None,
+        file_name_contains: typing.Optional[str] = None,
         limit: typing.Optional[int] = None,
         offset: typing.Optional[int] = None,
         order_by: typing.Optional[str] = None,
@@ -570,6 +568,15 @@ class PipelinesClient:
         """
         Get files for a pipeline.
 
+        Args:
+        pipeline_id: ID of the pipeline
+        data_source_id: Optional filter by data source ID
+        only_manually_uploaded: Filter for only manually uploaded files
+        file_name_contains: Optional filter by file name (substring match)
+        limit: Limit number of results
+        offset: Offset for pagination
+        order_by: Field to order by
+
         Parameters:
             - pipeline_id: str.
 
@@ -577,6 +584,8 @@ class PipelinesClient:
 
             - only_manually_uploaded: typing.Optional[bool].
 
+            - file_name_contains: typing.Optional[str].
+
             - limit: typing.Optional[int].
 
             - offset: typing.Optional[int].
@@ -599,6 +608,7 @@ class PipelinesClient:
                 {
                     "data_source_id": data_source_id,
                     "only_manually_uploaded": only_manually_uploaded,
+                    "file_name_contains": file_name_contains,
                     "limit": limit,
                     "offset": offset,
                     "order_by": order_by,
@@ -1095,7 +1105,6 @@ class PipelinesClient:
         retrieve_page_figure_nodes: typing.Optional[bool] = OMIT,
         query: str,
         class_name: typing.Optional[str] = OMIT,
-        project_id: typing.Optional[str] = None,
     ) -> RetrieveResults:
         """
         Get retrieval results for a managed pipeline and a query
@@ -1136,8 +1145,6 @@ class PipelinesClient:
             - query: str. The query to retrieve against.
 
             - class_name: typing.Optional[str].
-
-            - project_id: typing.Optional[str].
         ---
         from llama_cloud import FilterCondition, MetadataFilters, RetrievalMode
         from llama_cloud.client import LlamaCloud
@@ -1189,7 +1196,7 @@ class PipelinesClient:
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/retrieve"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             json=jsonable_encoder(_request),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -1750,7 +1757,6 @@ class AsyncPipelinesClient:
         pipeline_name: typing.Optional[str] = None,
         pipeline_type: typing.Optional[PipelineType] = None,
         organization_id: typing.Optional[str] = None,
-        project_id: typing.Optional[str] = None,
     ) -> typing.List[Pipeline]:
         """
         Search for pipelines by various parameters.
@@ -1765,8 +1771,6 @@ class AsyncPipelinesClient:
             - pipeline_type: typing.Optional[PipelineType].
 
             - organization_id: typing.Optional[str].
-
-            - project_id: typing.Optional[str].
         ---
         from llama_cloud import PipelineType
         from llama_cloud.client import AsyncLlamaCloud
@@ -1790,7 +1794,7 @@ class AsyncPipelinesClient:
                     "organization_id": organization_id,
                 }
             ),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -1809,7 +1813,6 @@ class AsyncPipelinesClient:
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
         request: PipelineCreate,
-        project_id: typing.Optional[str] = None,
     ) -> Pipeline:
         """
         Create a new pipeline for a project.
@@ -1820,15 +1823,13 @@ class AsyncPipelinesClient:
             - organization_id: typing.Optional[str].
 
             - request: PipelineCreate.
-
-            - project_id: typing.Optional[str].
         """
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/pipelines"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             json=jsonable_encoder(request),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -1847,7 +1848,6 @@ class AsyncPipelinesClient:
         project_id: typing.Optional[str] = None,
         organization_id: typing.Optional[str] = None,
         request: PipelineCreate,
-        project_id: typing.Optional[str] = None,
     ) -> Pipeline:
         """
         Upsert a pipeline for a project.
@@ -1859,15 +1859,13 @@ class AsyncPipelinesClient:
             - organization_id: typing.Optional[str].
 
             - request: PipelineCreate.
-
-            - project_id: typing.Optional[str].
         """
         _response = await self._client_wrapper.httpx_client.request(
             "PUT",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/pipelines"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             json=jsonable_encoder(request),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300:
@@ -1909,6 +1907,7 @@ class AsyncPipelinesClient:
         *,
         embedding_config: typing.Optional[PipelineUpdateEmbeddingConfig] = OMIT,
         transform_config: typing.Optional[PipelineUpdateTransformConfig] = OMIT,
+        sparse_model_config: typing.Optional[SparseModelConfig] = OMIT,
         data_sink_id: typing.Optional[str] = OMIT,
         embedding_model_config_id: typing.Optional[str] = OMIT,
         data_sink: typing.Optional[DataSinkCreate] = OMIT,
@@ -1930,6 +1929,8 @@ class AsyncPipelinesClient:
 
             - transform_config: typing.Optional[PipelineUpdateTransformConfig]. Configuration for the transformation.
 
+            - sparse_model_config: typing.Optional[SparseModelConfig].
+
             - data_sink_id: typing.Optional[str].
 
             - embedding_model_config_id: typing.Optional[str].
@@ -1955,6 +1956,8 @@ class AsyncPipelinesClient:
             _request["embedding_config"] = embedding_config
         if transform_config is not OMIT:
             _request["transform_config"] = transform_config
+        if sparse_model_config is not OMIT:
+            _request["sparse_model_config"] = sparse_model_config
         if data_sink_id is not OMIT:
             _request["data_sink_id"] = data_sink_id
         if embedding_model_config_id is not OMIT:
@@ -2246,6 +2249,7 @@ class AsyncPipelinesClient:
         *,
         data_source_id: typing.Optional[str] = None,
         only_manually_uploaded: typing.Optional[bool] = None,
+        file_name_contains: typing.Optional[str] = None,
         limit: typing.Optional[int] = None,
         offset: typing.Optional[int] = None,
         order_by: typing.Optional[str] = None,
@@ -2253,6 +2257,15 @@ class AsyncPipelinesClient:
         """
         Get files for a pipeline.
 
+        Args:
+        pipeline_id: ID of the pipeline
+        data_source_id: Optional filter by data source ID
+        only_manually_uploaded: Filter for only manually uploaded files
+        file_name_contains: Optional filter by file name (substring match)
+        limit: Limit number of results
+        offset: Offset for pagination
+        order_by: Field to order by
+
         Parameters:
             - pipeline_id: str.
 
@@ -2260,6 +2273,8 @@ class AsyncPipelinesClient:
 
             - only_manually_uploaded: typing.Optional[bool].
 
+            - file_name_contains: typing.Optional[str].
+
             - limit: typing.Optional[int].
 
             - offset: typing.Optional[int].
@@ -2282,6 +2297,7 @@ class AsyncPipelinesClient:
                 {
                     "data_source_id": data_source_id,
                     "only_manually_uploaded": only_manually_uploaded,
+                    "file_name_contains": file_name_contains,
                     "limit": limit,
                     "offset": offset,
                     "order_by": order_by,
@@ -2780,7 +2796,6 @@ class AsyncPipelinesClient:
         retrieve_page_figure_nodes: typing.Optional[bool] = OMIT,
         query: str,
         class_name: typing.Optional[str] = OMIT,
-        project_id: typing.Optional[str] = None,
     ) -> RetrieveResults:
         """
         Get retrieval results for a managed pipeline and a query
@@ -2821,8 +2836,6 @@ class AsyncPipelinesClient:
             - query: str. The query to retrieve against.
 
             - class_name: typing.Optional[str].
-
-            - project_id: typing.Optional[str].
         ---
         from llama_cloud import FilterCondition, MetadataFilters, RetrievalMode
         from llama_cloud.client import AsyncLlamaCloud
@@ -2874,7 +2887,7 @@ class AsyncPipelinesClient:
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/pipelines/{pipeline_id}/retrieve"),
             params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
             json=jsonable_encoder(_request),
-            headers=remove_none_from_dict({**self._client_wrapper.get_headers(), "Project-Id": project_id}),
+            headers=self._client_wrapper.get_headers(),
             timeout=60,
         )
         if 200 <= _response.status_code < 300: