llama-cloud 0.1.39__py3-none-any.whl → 0.1.41__py3-none-any.whl

llama_cloud/resources/llama_extract/client.py

@@ -111,7 +111,9 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -124,6 +126,8 @@ class LlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -359,7 +363,9 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -372,6 +378,8 @@ class LlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -470,8 +478,11 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractJobCreate,
+            ExtractJobCreatePriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -480,12 +491,15 @@ class LlamaExtractClient:
         )
         client.llama_extract.run_job(
             request=ExtractJobCreate(
+                priority=ExtractJobCreatePriority.LOW,
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
                     priority=ExtractConfigPriority.LOW,
                     extraction_target=ExtractTarget.PER_DOC,
                     extraction_mode=ExtractMode.FAST,
+                    parse_model=PublicModelName.OPENAI_GPT_4_O,
+                    extract_model=ExtractModels.OPENAI_GPT_4_1,
                     chunk_mode=DocumentChunkMode.PAGE,
                 ),
             ),
@@ -560,7 +574,9 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractJobCreate,
+            ExtractJobCreatePriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
             FailPageMode,
             LlamaExtractSettings,
@@ -568,6 +584,7 @@ class LlamaExtractClient:
             LlamaParseParametersPriority,
             MultimodalParseResolution,
             ParsingMode,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -576,12 +593,15 @@ class LlamaExtractClient:
         )
         client.llama_extract.run_job_test_user(
             job_create=ExtractJobCreate(
+                priority=ExtractJobCreatePriority.LOW,
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
                     priority=ExtractConfigPriority.LOW,
                     extraction_target=ExtractTarget.PER_DOC,
                     extraction_mode=ExtractMode.FAST,
+                    parse_model=PublicModelName.OPENAI_GPT_4_O,
+                    extract_model=ExtractModels.OPENAI_GPT_4_1,
                     chunk_mode=DocumentChunkMode.PAGE,
                 ),
             ),
@@ -689,7 +709,9 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -703,6 +725,8 @@ class LlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -984,8 +1008,10 @@ class LlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
             FileData,
+            PublicModelName,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -997,6 +1023,8 @@ class LlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
             file=FileData(
@@ -1104,7 +1132,9 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1117,6 +1147,8 @@ class AsyncLlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -1352,7 +1384,9 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1365,6 +1399,8 @@ class AsyncLlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -1463,8 +1499,11 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractJobCreate,
+            ExtractJobCreatePriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1473,12 +1512,15 @@ class AsyncLlamaExtractClient:
         )
         await client.llama_extract.run_job(
             request=ExtractJobCreate(
+                priority=ExtractJobCreatePriority.LOW,
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
                     priority=ExtractConfigPriority.LOW,
                     extraction_target=ExtractTarget.PER_DOC,
                     extraction_mode=ExtractMode.FAST,
+                    parse_model=PublicModelName.OPENAI_GPT_4_O,
+                    extract_model=ExtractModels.OPENAI_GPT_4_1,
                     chunk_mode=DocumentChunkMode.PAGE,
                 ),
             ),
@@ -1553,7 +1595,9 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractJobCreate,
+            ExtractJobCreatePriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
             FailPageMode,
             LlamaExtractSettings,
@@ -1561,6 +1605,7 @@ class AsyncLlamaExtractClient:
             LlamaParseParametersPriority,
             MultimodalParseResolution,
             ParsingMode,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1569,12 +1614,15 @@ class AsyncLlamaExtractClient:
         )
         await client.llama_extract.run_job_test_user(
             job_create=ExtractJobCreate(
+                priority=ExtractJobCreatePriority.LOW,
                 extraction_agent_id="string",
                 file_id="string",
                 config_override=ExtractConfig(
                     priority=ExtractConfigPriority.LOW,
                     extraction_target=ExtractTarget.PER_DOC,
                     extraction_mode=ExtractMode.FAST,
+                    parse_model=PublicModelName.OPENAI_GPT_4_O,
+                    extract_model=ExtractModels.OPENAI_GPT_4_1,
                     chunk_mode=DocumentChunkMode.PAGE,
                 ),
             ),
@@ -1682,7 +1730,9 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1696,6 +1746,8 @@ class AsyncLlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
         )
@@ -1977,8 +2029,10 @@ class AsyncLlamaExtractClient:
             ExtractConfig,
             ExtractConfigPriority,
             ExtractMode,
+            ExtractModels,
             ExtractTarget,
             FileData,
+            PublicModelName,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1990,6 +2044,8 @@ class AsyncLlamaExtractClient:
                 priority=ExtractConfigPriority.LOW,
                 extraction_target=ExtractTarget.PER_DOC,
                 extraction_mode=ExtractMode.FAST,
+                parse_model=PublicModelName.OPENAI_GPT_4_O,
+                extract_model=ExtractModels.OPENAI_GPT_4_1,
                 chunk_mode=DocumentChunkMode.PAGE,
             ),
             file=FileData(

llama_cloud/resources/parsing/client.py

@@ -227,6 +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,
@@ -357,6 +358,8 @@ class ParsingClient:
 
             - html_make_all_elements_visible: bool.
 
+            - layout_aware: bool.
+
             - html_remove_fixed_elements: bool.
 
             - html_remove_navigation_elements: bool.
@@ -522,6 +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,
@@ -1399,6 +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,
@@ -1529,6 +1534,8 @@ class AsyncParsingClient:
 
             - html_make_all_elements_visible: bool.
 
+            - layout_aware: bool.
+
             - html_remove_fixed_elements: bool.
 
             - html_remove_navigation_elements: bool.
@@ -1694,6 +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,

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
@@ -217,6 +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,
@@ -238,6 +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].
@@ -263,6 +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:
@@ -554,6 +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,
@@ -561,6 +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.
 
@@ -568,6 +584,8 @@ class PipelinesClient:
 
             - only_manually_uploaded: typing.Optional[bool].
 
+            - file_name_contains: typing.Optional[str].
+
             - limit: typing.Optional[int].
 
             - offset: typing.Optional[int].
@@ -590,6 +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,
@@ -1888,6 +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,
@@ -1909,6 +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].
@@ -1934,6 +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:
@@ -2225,6 +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,
@@ -2232,6 +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.
 
@@ -2239,6 +2273,8 @@ class AsyncPipelinesClient:
 
             - only_manually_uploaded: typing.Optional[bool].
 
+            - file_name_contains: typing.Optional[str].
+
             - limit: typing.Optional[int].
 
             - offset: typing.Optional[int].
@@ -2261,6 +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,