llama-cloud 0.1.12__py3-none-any.whl → 0.1.13__py3-none-any.whl

llama_cloud/__init__.py

@@ -16,7 +16,6 @@ from .types import (
     AutoTransformConfig,
     AzureOpenAiEmbedding,
     AzureOpenAiEmbeddingConfig,
-    Base,
     BasePromptTemplate,
     BedrockEmbedding,
     BedrockEmbeddingConfig,
@@ -191,6 +190,7 @@ from .types import (
     ParsingJobMarkdownResult,
     ParsingJobStructuredResult,
     ParsingJobTextResult,
+    ParsingMode,
     ParsingUsage,
     PartitionNames,
     Permission,
@@ -366,7 +366,6 @@ __all__ = [
     "AutoTransformConfig",
     "AzureOpenAiEmbedding",
     "AzureOpenAiEmbeddingConfig",
-    "Base",
     "BasePromptTemplate",
     "BedrockEmbedding",
     "BedrockEmbeddingConfig",
@@ -562,6 +561,7 @@ __all__ = [
     "ParsingJobMarkdownResult",
     "ParsingJobStructuredResult",
     "ParsingJobTextResult",
+    "ParsingMode",
     "ParsingUsage",
     "PartitionNames",
     "Permission",

llama_cloud/resources/llama_extract/client.py

@@ -424,6 +424,7 @@ class LlamaExtractClient:
             ExtractTarget,
             LlamaExtractSettings,
             LlamaParseParameters,
+            ParsingMode,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -441,7 +442,9 @@ class LlamaExtractClient:
             ),
             extract_settings=LlamaExtractSettings(
                 chunk_mode=ChunkMode.PAGE,
-                llama_parse_params=LlamaParseParameters(),
+                llama_parse_params=LlamaParseParameters(
+                    parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM,
+                ),
             ),
         )
         """
@@ -526,6 +529,7 @@ class LlamaExtractClient:
             ExtractTarget,
             LlamaExtractSettings,
             LlamaParseParameters,
+            ParsingMode,
         )
         from llama_cloud.client import LlamaCloud
 
@@ -543,7 +547,9 @@ class LlamaExtractClient:
             ),
             extract_settings=LlamaExtractSettings(
                 chunk_mode=ChunkMode.PAGE,
-                llama_parse_params=LlamaParseParameters(),
+                llama_parse_params=LlamaParseParameters(
+                    parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM,
+                ),
             ),
         )
         """
@@ -1083,6 +1089,7 @@ class AsyncLlamaExtractClient:
             ExtractTarget,
             LlamaExtractSettings,
             LlamaParseParameters,
+            ParsingMode,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1100,7 +1107,9 @@ class AsyncLlamaExtractClient:
             ),
             extract_settings=LlamaExtractSettings(
                 chunk_mode=ChunkMode.PAGE,
-                llama_parse_params=LlamaParseParameters(),
+                llama_parse_params=LlamaParseParameters(
+                    parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM,
+                ),
             ),
         )
         """
@@ -1185,6 +1194,7 @@ class AsyncLlamaExtractClient:
             ExtractTarget,
             LlamaExtractSettings,
             LlamaParseParameters,
+            ParsingMode,
         )
         from llama_cloud.client import AsyncLlamaCloud
 
@@ -1202,7 +1212,9 @@ class AsyncLlamaExtractClient:
             ),
             extract_settings=LlamaExtractSettings(
                 chunk_mode=ChunkMode.PAGE,
-                llama_parse_params=LlamaParseParameters(),
+                llama_parse_params=LlamaParseParameters(
+                    parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM,
+                ),
             ),
         )
         """

llama_cloud/resources/parsing/client.py

@@ -18,6 +18,7 @@ from ...types.parsing_job_json_result import ParsingJobJsonResult
 from ...types.parsing_job_markdown_result import ParsingJobMarkdownResult
 from ...types.parsing_job_structured_result import ParsingJobStructuredResult
 from ...types.parsing_job_text_result import ParsingJobTextResult
+from ...types.parsing_mode import ParsingMode
 from ...types.parsing_usage import ParsingUsage
 from ...types.presigned_url import PresignedUrl
 
@@ -210,17 +211,12 @@ class ParsingClient:
         bbox_left: float,
         bbox_right: float,
         bbox_top: float,
-        complemental_formatting_instruction: str,
-        content_guideline_instruction: str,
-        continuous_mode: bool,
         disable_ocr: bool,
         disable_reconstruction: bool,
         disable_image_extraction: bool,
         do_not_cache: bool,
         do_not_unroll_columns: bool,
         extract_charts: bool,
-        fast_mode: bool,
-        formatting_instruction: str,
         guess_xlsx_sheet_name: bool,
         html_make_all_elements_visible: bool,
         html_remove_fixed_elements: bool,
@@ -230,7 +226,6 @@ class ParsingClient:
         input_s_3_region: str,
         input_url: str,
         invalidate_cache: bool,
-        is_formatting_instruction: bool,
         language: typing.List[ParserLanguages],
         extract_layout: bool,
         max_pages: typing.Optional[int] = OMIT,
@@ -240,8 +235,7 @@ class ParsingClient:
         page_prefix: str,
         page_separator: str,
         page_suffix: str,
-        parsing_instruction: str,
-        premium_mode: bool,
+        preserve_layout_alignment_across_pages: bool,
         skip_diagonal_text: bool,
         spreadsheet_extract_sub_tables: bool,
         structured_output: bool,
@@ -249,13 +243,13 @@ class ParsingClient:
         structured_output_json_schema_name: str,
         take_screenshot: bool,
         target_pages: str,
-        use_vendor_multimodal_model: bool,
         vendor_multimodal_api_key: str,
         vendor_multimodal_model_name: str,
         webhook_url: str,
-        bounding_box: str,
-        gpt_4_o_mode: bool,
-        gpt_4_o_api_key: str,
+        parse_mode: typing.Optional[ParsingMode] = OMIT,
+        system_prompt: str,
+        system_prompt_append: str,
+        user_prompt: str,
         job_timeout_in_seconds: float,
         job_timeout_extra_time_per_page_in_seconds: float,
         strict_mode_image_extraction: bool,
@@ -264,6 +258,18 @@ class ParsingClient:
         strict_mode_buggy_font: bool,
         ignore_document_elements_for_layout_detection: bool,
         output_tables_as_html: bool,
+        use_vendor_multimodal_model: bool,
+        bounding_box: str,
+        gpt_4_o_mode: bool,
+        gpt_4_o_api_key: str,
+        complemental_formatting_instruction: str,
+        content_guideline_instruction: str,
+        premium_mode: bool,
+        is_formatting_instruction: bool,
+        continuous_mode: bool,
+        parsing_instruction: str,
+        fast_mode: bool,
+        formatting_instruction: str,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
@@ -303,12 +309,6 @@ class ParsingClient:
 
             - bbox_top: float.
 
-            - complemental_formatting_instruction: str.
-
-            - content_guideline_instruction: str.
-
-            - continuous_mode: bool.
-
             - disable_ocr: bool.
 
             - disable_reconstruction: bool.
@@ -321,10 +321,6 @@ class ParsingClient:
 
             - extract_charts: bool.
 
-            - fast_mode: bool.
-
-            - formatting_instruction: str.
-
             - guess_xlsx_sheet_name: bool.
 
             - html_make_all_elements_visible: bool.
@@ -343,8 +339,6 @@ class ParsingClient:
 
             - invalidate_cache: bool.
 
-            - is_formatting_instruction: bool.
-
             - language: typing.List[ParserLanguages].
 
             - extract_layout: bool.
@@ -363,9 +357,7 @@ class ParsingClient:
 
             - page_suffix: str.
 
-            - parsing_instruction: str.
-
-            - premium_mode: bool.
+            - preserve_layout_alignment_across_pages: bool.
 
             - skip_diagonal_text: bool.
 
@@ -381,19 +373,19 @@ class ParsingClient:
 
             - target_pages: str.
 
-            - use_vendor_multimodal_model: bool.
-
             - vendor_multimodal_api_key: str.
 
             - vendor_multimodal_model_name: str.
 
             - webhook_url: str.
 
-            - bounding_box: str.
+            - parse_mode: typing.Optional[ParsingMode].
 
-            - gpt_4_o_mode: bool.
+            - system_prompt: str.
 
-            - gpt_4_o_api_key: str.
+            - system_prompt_append: str.
+
+            - user_prompt: str.
 
             - job_timeout_in_seconds: float.
 
@@ -410,6 +402,30 @@ class ParsingClient:
             - ignore_document_elements_for_layout_detection: bool.
 
             - output_tables_as_html: bool.
+
+            - use_vendor_multimodal_model: bool.
+
+            - bounding_box: str.
+
+            - gpt_4_o_mode: bool.
+
+            - gpt_4_o_api_key: str.
+
+            - complemental_formatting_instruction: str.
+
+            - content_guideline_instruction: str.
+
+            - premium_mode: bool.
+
+            - is_formatting_instruction: bool.
+
+            - continuous_mode: bool.
+
+            - parsing_instruction: str.
+
+            - fast_mode: bool.
+
+            - formatting_instruction: str.
         """
         _request: typing.Dict[str, typing.Any] = {
             "annotate_links": annotate_links,
@@ -426,17 +442,12 @@ class ParsingClient:
             "bbox_left": bbox_left,
             "bbox_right": bbox_right,
             "bbox_top": bbox_top,
-            "complemental_formatting_instruction": complemental_formatting_instruction,
-            "content_guideline_instruction": content_guideline_instruction,
-            "continuous_mode": continuous_mode,
             "disable_ocr": disable_ocr,
             "disable_reconstruction": disable_reconstruction,
             "disable_image_extraction": disable_image_extraction,
             "do_not_cache": do_not_cache,
             "do_not_unroll_columns": do_not_unroll_columns,
             "extract_charts": extract_charts,
-            "fast_mode": fast_mode,
-            "formatting_instruction": formatting_instruction,
             "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
             "html_make_all_elements_visible": html_make_all_elements_visible,
             "html_remove_fixed_elements": html_remove_fixed_elements,
@@ -446,7 +457,6 @@ class ParsingClient:
             "input_s3_region": input_s_3_region,
             "input_url": input_url,
             "invalidate_cache": invalidate_cache,
-            "is_formatting_instruction": is_formatting_instruction,
             "language": language,
             "extract_layout": extract_layout,
             "output_pdf_of_document": output_pdf_of_document,
@@ -455,8 +465,7 @@ class ParsingClient:
             "page_prefix": page_prefix,
             "page_separator": page_separator,
             "page_suffix": page_suffix,
-            "parsing_instruction": parsing_instruction,
-            "premium_mode": premium_mode,
+            "preserve_layout_alignment_across_pages": preserve_layout_alignment_across_pages,
             "skip_diagonal_text": skip_diagonal_text,
             "spreadsheet_extract_sub_tables": spreadsheet_extract_sub_tables,
             "structured_output": structured_output,
@@ -464,13 +473,12 @@ class ParsingClient:
             "structured_output_json_schema_name": structured_output_json_schema_name,
             "take_screenshot": take_screenshot,
             "target_pages": target_pages,
-            "use_vendor_multimodal_model": use_vendor_multimodal_model,
             "vendor_multimodal_api_key": vendor_multimodal_api_key,
             "vendor_multimodal_model_name": vendor_multimodal_model_name,
             "webhook_url": webhook_url,
-            "bounding_box": bounding_box,
-            "gpt4o_mode": gpt_4_o_mode,
-            "gpt4o_api_key": gpt_4_o_api_key,
+            "system_prompt": system_prompt,
+            "system_prompt_append": system_prompt_append,
+            "user_prompt": user_prompt,
             "job_timeout_in_seconds": job_timeout_in_seconds,
             "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds,
             "strict_mode_image_extraction": strict_mode_image_extraction,
@@ -479,11 +487,25 @@ class ParsingClient:
             "strict_mode_buggy_font": strict_mode_buggy_font,
             "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
             "output_tables_as_HTML": output_tables_as_html,
+            "use_vendor_multimodal_model": use_vendor_multimodal_model,
+            "bounding_box": bounding_box,
+            "gpt4o_mode": gpt_4_o_mode,
+            "gpt4o_api_key": gpt_4_o_api_key,
+            "complemental_formatting_instruction": complemental_formatting_instruction,
+            "content_guideline_instruction": content_guideline_instruction,
+            "premium_mode": premium_mode,
+            "is_formatting_instruction": is_formatting_instruction,
+            "continuous_mode": continuous_mode,
+            "parsing_instruction": parsing_instruction,
+            "fast_mode": fast_mode,
+            "formatting_instruction": formatting_instruction,
         }
         if file is not OMIT:
             _request["file"] = file
         if max_pages is not OMIT:
             _request["max_pages"] = max_pages
+        if parse_mode is not OMIT:
+            _request["parse_mode"] = parse_mode
         _response = self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
@@ -1157,17 +1179,12 @@ class AsyncParsingClient:
         bbox_left: float,
         bbox_right: float,
         bbox_top: float,
-        complemental_formatting_instruction: str,
-        content_guideline_instruction: str,
-        continuous_mode: bool,
         disable_ocr: bool,
         disable_reconstruction: bool,
         disable_image_extraction: bool,
         do_not_cache: bool,
         do_not_unroll_columns: bool,
         extract_charts: bool,
-        fast_mode: bool,
-        formatting_instruction: str,
         guess_xlsx_sheet_name: bool,
         html_make_all_elements_visible: bool,
         html_remove_fixed_elements: bool,
@@ -1177,7 +1194,6 @@ class AsyncParsingClient:
         input_s_3_region: str,
         input_url: str,
         invalidate_cache: bool,
-        is_formatting_instruction: bool,
         language: typing.List[ParserLanguages],
         extract_layout: bool,
         max_pages: typing.Optional[int] = OMIT,
@@ -1187,8 +1203,7 @@ class AsyncParsingClient:
         page_prefix: str,
         page_separator: str,
         page_suffix: str,
-        parsing_instruction: str,
-        premium_mode: bool,
+        preserve_layout_alignment_across_pages: bool,
         skip_diagonal_text: bool,
         spreadsheet_extract_sub_tables: bool,
         structured_output: bool,
@@ -1196,13 +1211,13 @@ class AsyncParsingClient:
         structured_output_json_schema_name: str,
         take_screenshot: bool,
         target_pages: str,
-        use_vendor_multimodal_model: bool,
         vendor_multimodal_api_key: str,
         vendor_multimodal_model_name: str,
         webhook_url: str,
-        bounding_box: str,
-        gpt_4_o_mode: bool,
-        gpt_4_o_api_key: str,
+        parse_mode: typing.Optional[ParsingMode] = OMIT,
+        system_prompt: str,
+        system_prompt_append: str,
+        user_prompt: str,
         job_timeout_in_seconds: float,
         job_timeout_extra_time_per_page_in_seconds: float,
         strict_mode_image_extraction: bool,
@@ -1211,6 +1226,18 @@ class AsyncParsingClient:
         strict_mode_buggy_font: bool,
         ignore_document_elements_for_layout_detection: bool,
         output_tables_as_html: bool,
+        use_vendor_multimodal_model: bool,
+        bounding_box: str,
+        gpt_4_o_mode: bool,
+        gpt_4_o_api_key: str,
+        complemental_formatting_instruction: str,
+        content_guideline_instruction: str,
+        premium_mode: bool,
+        is_formatting_instruction: bool,
+        continuous_mode: bool,
+        parsing_instruction: str,
+        fast_mode: bool,
+        formatting_instruction: str,
     ) -> ParsingJob:
         """
         Upload a file to s3 and create a job. return a job id
@@ -1250,12 +1277,6 @@ class AsyncParsingClient:
 
             - bbox_top: float.
 
-            - complemental_formatting_instruction: str.
-
-            - content_guideline_instruction: str.
-
-            - continuous_mode: bool.
-
             - disable_ocr: bool.
 
             - disable_reconstruction: bool.
@@ -1268,10 +1289,6 @@ class AsyncParsingClient:
 
             - extract_charts: bool.
 
-            - fast_mode: bool.
-
-            - formatting_instruction: str.
-
             - guess_xlsx_sheet_name: bool.
 
             - html_make_all_elements_visible: bool.
@@ -1290,8 +1307,6 @@ class AsyncParsingClient:
 
             - invalidate_cache: bool.
 
-            - is_formatting_instruction: bool.
-
             - language: typing.List[ParserLanguages].
 
             - extract_layout: bool.
@@ -1310,9 +1325,7 @@ class AsyncParsingClient:
 
             - page_suffix: str.
 
-            - parsing_instruction: str.
-
-            - premium_mode: bool.
+            - preserve_layout_alignment_across_pages: bool.
 
             - skip_diagonal_text: bool.
 
@@ -1328,19 +1341,19 @@ class AsyncParsingClient:
 
             - target_pages: str.
 
-            - use_vendor_multimodal_model: bool.
-
             - vendor_multimodal_api_key: str.
 
             - vendor_multimodal_model_name: str.
 
             - webhook_url: str.
 
-            - bounding_box: str.
+            - parse_mode: typing.Optional[ParsingMode].
 
-            - gpt_4_o_mode: bool.
+            - system_prompt: str.
 
-            - gpt_4_o_api_key: str.
+            - system_prompt_append: str.
+
+            - user_prompt: str.
 
             - job_timeout_in_seconds: float.
 
@@ -1357,6 +1370,30 @@ class AsyncParsingClient:
             - ignore_document_elements_for_layout_detection: bool.
 
             - output_tables_as_html: bool.
+
+            - use_vendor_multimodal_model: bool.
+
+            - bounding_box: str.
+
+            - gpt_4_o_mode: bool.
+
+            - gpt_4_o_api_key: str.
+
+            - complemental_formatting_instruction: str.
+
+            - content_guideline_instruction: str.
+
+            - premium_mode: bool.
+
+            - is_formatting_instruction: bool.
+
+            - continuous_mode: bool.
+
+            - parsing_instruction: str.
+
+            - fast_mode: bool.
+
+            - formatting_instruction: str.
         """
         _request: typing.Dict[str, typing.Any] = {
             "annotate_links": annotate_links,
@@ -1373,17 +1410,12 @@ class AsyncParsingClient:
             "bbox_left": bbox_left,
             "bbox_right": bbox_right,
             "bbox_top": bbox_top,
-            "complemental_formatting_instruction": complemental_formatting_instruction,
-            "content_guideline_instruction": content_guideline_instruction,
-            "continuous_mode": continuous_mode,
             "disable_ocr": disable_ocr,
             "disable_reconstruction": disable_reconstruction,
             "disable_image_extraction": disable_image_extraction,
             "do_not_cache": do_not_cache,
             "do_not_unroll_columns": do_not_unroll_columns,
             "extract_charts": extract_charts,
-            "fast_mode": fast_mode,
-            "formatting_instruction": formatting_instruction,
             "guess_xlsx_sheet_name": guess_xlsx_sheet_name,
             "html_make_all_elements_visible": html_make_all_elements_visible,
             "html_remove_fixed_elements": html_remove_fixed_elements,
@@ -1393,7 +1425,6 @@ class AsyncParsingClient:
             "input_s3_region": input_s_3_region,
             "input_url": input_url,
             "invalidate_cache": invalidate_cache,
-            "is_formatting_instruction": is_formatting_instruction,
             "language": language,
             "extract_layout": extract_layout,
             "output_pdf_of_document": output_pdf_of_document,
@@ -1402,8 +1433,7 @@ class AsyncParsingClient:
             "page_prefix": page_prefix,
             "page_separator": page_separator,
             "page_suffix": page_suffix,
-            "parsing_instruction": parsing_instruction,
-            "premium_mode": premium_mode,
+            "preserve_layout_alignment_across_pages": preserve_layout_alignment_across_pages,
             "skip_diagonal_text": skip_diagonal_text,
             "spreadsheet_extract_sub_tables": spreadsheet_extract_sub_tables,
             "structured_output": structured_output,
@@ -1411,13 +1441,12 @@ class AsyncParsingClient:
             "structured_output_json_schema_name": structured_output_json_schema_name,
             "take_screenshot": take_screenshot,
             "target_pages": target_pages,
-            "use_vendor_multimodal_model": use_vendor_multimodal_model,
             "vendor_multimodal_api_key": vendor_multimodal_api_key,
             "vendor_multimodal_model_name": vendor_multimodal_model_name,
             "webhook_url": webhook_url,
-            "bounding_box": bounding_box,
-            "gpt4o_mode": gpt_4_o_mode,
-            "gpt4o_api_key": gpt_4_o_api_key,
+            "system_prompt": system_prompt,
+            "system_prompt_append": system_prompt_append,
+            "user_prompt": user_prompt,
             "job_timeout_in_seconds": job_timeout_in_seconds,
             "job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds,
             "strict_mode_image_extraction": strict_mode_image_extraction,
@@ -1426,11 +1455,25 @@ class AsyncParsingClient:
             "strict_mode_buggy_font": strict_mode_buggy_font,
             "ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
             "output_tables_as_HTML": output_tables_as_html,
+            "use_vendor_multimodal_model": use_vendor_multimodal_model,
+            "bounding_box": bounding_box,
+            "gpt4o_mode": gpt_4_o_mode,
+            "gpt4o_api_key": gpt_4_o_api_key,
+            "complemental_formatting_instruction": complemental_formatting_instruction,
+            "content_guideline_instruction": content_guideline_instruction,
+            "premium_mode": premium_mode,
+            "is_formatting_instruction": is_formatting_instruction,
+            "continuous_mode": continuous_mode,
+            "parsing_instruction": parsing_instruction,
+            "fast_mode": fast_mode,
+            "formatting_instruction": formatting_instruction,
         }
         if file is not OMIT:
             _request["file"] = file
         if max_pages is not OMIT:
             _request["max_pages"] = max_pages
+        if parse_mode is not OMIT:
+            _request["parse_mode"] = parse_mode
         _response = await self._client_wrapper.httpx_client.request(
             "POST",
             urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),

llama_cloud/types/__init__.py

@@ -19,7 +19,6 @@ from .app_schema_chat_chat_message import AppSchemaChatChatMessage
 from .auto_transform_config import AutoTransformConfig
 from .azure_open_ai_embedding import AzureOpenAiEmbedding
 from .azure_open_ai_embedding_config import AzureOpenAiEmbeddingConfig
-from .base import Base
 from .base_prompt_template import BasePromptTemplate
 from .bedrock_embedding import BedrockEmbedding
 from .bedrock_embedding_config import BedrockEmbeddingConfig
@@ -200,6 +199,7 @@ from .parsing_job_json_result import ParsingJobJsonResult
 from .parsing_job_markdown_result import ParsingJobMarkdownResult
 from .parsing_job_structured_result import ParsingJobStructuredResult
 from .parsing_job_text_result import ParsingJobTextResult
+from .parsing_mode import ParsingMode
 from .parsing_usage import ParsingUsage
 from .partition_names import PartitionNames
 from .permission import Permission
@@ -332,7 +332,6 @@ __all__ = [
     "AutoTransformConfig",
     "AzureOpenAiEmbedding",
     "AzureOpenAiEmbeddingConfig",
-    "Base",
     "BasePromptTemplate",
     "BedrockEmbedding",
     "BedrockEmbeddingConfig",
@@ -507,6 +506,7 @@ __all__ = [
     "ParsingJobMarkdownResult",
     "ParsingJobStructuredResult",
     "ParsingJobTextResult",
+    "ParsingMode",
     "ParsingUsage",
     "PartitionNames",
     "Permission",

llama_cloud/types/eval_dataset_job_record.py

@@ -6,7 +6,6 @@ import typing
 import typing_extensions
 
 from ..core.datetime_utils import serialize_datetime
-from .base import Base
 from .eval_dataset_job_params import EvalDatasetJobParams
 from .status_enum import StatusEnum
 
@@ -43,7 +42,7 @@ class EvalDatasetJobRecord(pydantic.BaseModel):
     started_at: typing.Optional[dt.datetime]
     ended_at: typing.Optional[dt.datetime]
     updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
-    data: typing.Optional[Base]
+    data: typing.Optional[typing.Any]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/job_record.py

@@ -4,7 +4,6 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .base import Base
 from .job_names import JobNames
 from .status_enum import StatusEnum
 
@@ -26,7 +25,7 @@ class JobRecord(pydantic.BaseModel):
     partitions: typing.Dict[str, str] = pydantic.Field(
         description="The partitions for this execution. Used for determining where to save job output."
     )
-    parameters: typing.Optional[Base]
+    parameters: typing.Optional[typing.Any]
     session_id: typing.Optional[str]
     correlation_id: typing.Optional[str]
     parent_job_execution_id: typing.Optional[str]
@@ -41,7 +40,7 @@ class JobRecord(pydantic.BaseModel):
     started_at: typing.Optional[dt.datetime]
     ended_at: typing.Optional[dt.datetime]
     updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
-    data: typing.Optional[Base]
+    data: typing.Optional[typing.Any]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/llama_parse_parameters.py

@@ -5,6 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from .parser_languages import ParserLanguages
+from .parsing_mode import ParsingMode
 
 try:
     import pydantic
@@ -31,6 +32,7 @@ class LlamaParseParameters(pydantic.BaseModel):
     do_not_cache: typing.Optional[bool]
     fast_mode: typing.Optional[bool]
     skip_diagonal_text: typing.Optional[bool]
+    preserve_layout_alignment_across_pages: typing.Optional[bool]
     gpt_4_o_mode: typing.Optional[bool] = pydantic.Field(alias="gpt4o_mode")
     gpt_4_o_api_key: typing.Optional[str] = pydantic.Field(alias="gpt4o_api_key")
     do_not_unroll_columns: typing.Optional[bool]
@@ -91,6 +93,10 @@ class LlamaParseParameters(pydantic.BaseModel):
     ignore_document_elements_for_layout_detection: typing.Optional[bool]
     output_tables_as_html: typing.Optional[bool] = pydantic.Field(alias="output_tables_as_HTML")
     internal_is_screenshot_job: typing.Optional[bool]
+    parse_mode: typing.Optional[ParsingMode]
+    system_prompt: typing.Optional[str]
+    system_prompt_append: typing.Optional[str]
+    user_prompt: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/llm_parameters.py

@@ -22,6 +22,7 @@ class LlmParameters(pydantic.BaseModel):
     system_prompt: typing.Optional[str]
     temperature: typing.Optional[float]
     use_chain_of_thought_reasoning: typing.Optional[bool]
+    use_citation: typing.Optional[bool]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/page_screenshot_metadata.py

@@ -18,6 +18,7 @@ class PageScreenshotMetadata(pydantic.BaseModel):
     page_index: int = pydantic.Field(description="The index of the page for which the screenshot is taken (0-indexed)")
     file_id: str = pydantic.Field(description="The ID of the file that the page screenshot was taken from")
     image_size: int = pydantic.Field(description="The size of the image in bytes")
+    metadata: typing.Optional[typing.Dict[str, typing.Any]]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/parsing_mode.py

@@ -0,0 +1,37 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import enum
+import typing
+
+T_Result = typing.TypeVar("T_Result")
+
+
+class ParsingMode(str, enum.Enum):
+    """
+    Enum for representing the mode of parsing to be used
+    """
+
+    PARSE_PAGE_WITHOUT_LLM = "parse_page_without_llm"
+    PARSE_PAGE_WITH_LLM = "parse_page_with_llm"
+    PARSE_PAGE_WITH_LVM = "parse_page_with_lvm"
+    PARSE_PAGE_WITH_AGENT = "parse_page_with_agent"
+    PARSE_DOCUMENT_WITH_LLM = "parse_document_with_llm"
+
+    def visit(
+        self,
+        parse_page_without_llm: typing.Callable[[], T_Result],
+        parse_page_with_llm: typing.Callable[[], T_Result],
+        parse_page_with_lvm: typing.Callable[[], T_Result],
+        parse_page_with_agent: typing.Callable[[], T_Result],
+        parse_document_with_llm: typing.Callable[[], T_Result],
+    ) -> T_Result:
+        if self is ParsingMode.PARSE_PAGE_WITHOUT_LLM:
+            return parse_page_without_llm()
+        if self is ParsingMode.PARSE_PAGE_WITH_LLM:
+            return parse_page_with_llm()
+        if self is ParsingMode.PARSE_PAGE_WITH_LVM:
+            return parse_page_with_lvm()
+        if self is ParsingMode.PARSE_PAGE_WITH_AGENT:
+            return parse_page_with_agent()
+        if self is ParsingMode.PARSE_DOCUMENT_WITH_LLM:
+            return parse_document_with_llm()

{llama_cloud-0.1.12.dist-info → llama_cloud-0.1.13.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-cloud
-Version: 0.1.12
+Version: 0.1.13
 Summary: 
 License: MIT
 Author: Logan Markewich
@@ -12,7 +12,6 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: httpx (>=0.20.0)
 Requires-Dist: pydantic (>=1.10)

{llama_cloud-0.1.12.dist-info → llama_cloud-0.1.13.dist-info}/RECORD

@@ -1,4 +1,4 @@
-llama_cloud/__init__.py,sha256=X4Q_rgTHOWZ4unIpgBwbg6xxbHL7C_NDfae-yHhM12k,22183
+llama_cloud/__init__.py,sha256=Gj7v4ih6fClpdnFDcbyebawJILfPIlnr4PrS2JhhEWA,22197
 llama_cloud/client.py,sha256=0fK6iRBCA77eSs0zFrYQj-zD0BLy6Dr2Ss0ETJ4WaOY,5555
 llama_cloud/core/__init__.py,sha256=QJS3CJ2TYP2E1Tge0CS6Z7r8LTNzJHQVX1hD3558eP0,519
 llama_cloud/core/api_error.py,sha256=RE8LELok2QCjABadECTvtDp7qejA1VmINCh6TbqPwSE,426
@@ -38,7 +38,7 @@ llama_cloud/resources/files/types/file_create_resource_info_value.py,sha256=R7Y-
 llama_cloud/resources/jobs/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 llama_cloud/resources/jobs/client.py,sha256=mN9uOzys9aZkhOJkApUy0yhfNeK8X09xQxT34ZPptNY,5386
 llama_cloud/resources/llama_extract/__init__.py,sha256=MgOA61chV7LogriUoyswOT627LaVt3UIb-imM3BvHdQ,617
-llama_cloud/resources/llama_extract/client.py,sha256=V8rmOzmyL3oRdvYbHQFZE77dFvUzzjsnEA1ep2_zLuM,55218
+llama_cloud/resources/llama_extract/client.py,sha256=SLUG01nPtdLhAXn0nMYUqkYSVrRtPQgq155fPn82KiM,55654
 llama_cloud/resources/llama_extract/types/__init__.py,sha256=yY34YD-MI4SnSbyJY5JwCGBBfqRr0dNh2zibRUt8mt4,895
 llama_cloud/resources/llama_extract/types/extract_agent_create_data_schema.py,sha256=zB31hJQ8hKaIsPkfTWiX5hqsPVFMyyeWEDZ_Aq237jo,305
 llama_cloud/resources/llama_extract/types/extract_agent_create_data_schema_zero_value.py,sha256=xoyXH3f0Y5beMWBxmtXSz6QoB_df_-0QBsYdjBhZnGw,217
@@ -49,7 +49,7 @@ llama_cloud/resources/llama_extract/types/extract_schema_validate_request_data_s
 llama_cloud/resources/organizations/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 llama_cloud/resources/organizations/client.py,sha256=VRqPsWYEksvysYgKIOGnfhXjC3aaf9OHK6fHsS-XHqk,55460
 llama_cloud/resources/parsing/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
-llama_cloud/resources/parsing/client.py,sha256=8WHscm_0WzNpewtjN2m01DiX3UdV4PlDlRlrEEwxjQs,72070
+llama_cloud/resources/parsing/client.py,sha256=wOGNhHFrdqkJ8xSOhUFnlmS2ZahDeKP1kUWSo9WCHbY,73610
 llama_cloud/resources/pipelines/__init__.py,sha256=Mx7p3jDZRLMltsfywSufam_4AnHvmAfsxtMHVI72e-8,1083
 llama_cloud/resources/pipelines/client.py,sha256=MORoQkrH6-8-utV41zrXjFW2BegDsa_6pJhJvFH4OMQ,134251
 llama_cloud/resources/pipelines/types/__init__.py,sha256=jjaMc0V3K1HZLMYZ6WT4ydMtBCVy-oF5koqTCovbDws,1202
@@ -64,7 +64,7 @@ llama_cloud/resources/reports/types/__init__.py,sha256=LfwDYrI4RcQu-o42iAe7HkcwH
 llama_cloud/resources/reports/types/update_report_plan_api_v_1_reports_report_id_plan_patch_request_action.py,sha256=Qh-MSeRvDBfNb5hoLELivv1pLtrYVf52WVoP7G8V34A,807
 llama_cloud/resources/retrievers/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
 llama_cloud/resources/retrievers/client.py,sha256=ASDdqnwXX4qj0sCAkWO7RKFnQ1oiLzBLIQ2bwqnMOKs,24905
-llama_cloud/types/__init__.py,sha256=X2X5A34cSJO0B2zEHZxvsSyv0SLKlCxkPcNCG4J6hxo,26343
+llama_cloud/types/__init__.py,sha256=34m42Eg8gOU0pfNnnjeEapXKArCpibp7Typwd70sRXI,26365
 llama_cloud/types/advanced_mode_transform_config.py,sha256=4xCXye0_cPmVS1F8aNTx81sIaEPjQH9kiCCAIoqUzlI,1502
 llama_cloud/types/advanced_mode_transform_config_chunking_config.py,sha256=wYbJnWLpeQDfhmDZz-wJfYzD1iGT5Jcxb9ga3mzUuvk,1983
 llama_cloud/types/advanced_mode_transform_config_segmentation_config.py,sha256=anNGq0F5-IlbIW3kpC8OilzLJnUq5tdIcWHnRnmlYsg,1303
@@ -72,7 +72,6 @@ llama_cloud/types/app_schema_chat_chat_message.py,sha256=4Mplkc7PczuxKL7Gga3aj8Q
 llama_cloud/types/auto_transform_config.py,sha256=HVeHZM75DMRznScqLTfrMwcZwIdyWPuaEYbPewnHqwc,1168
 llama_cloud/types/azure_open_ai_embedding.py,sha256=MeDqZoPYFN7Nv_imY9cfqDU9SPlEyAY4HcQZ4PF5X3g,2264
 llama_cloud/types/azure_open_ai_embedding_config.py,sha256=o1zZhzcGElH3SeixFErrm7P_WFHQ6LvrLem_nKJWunw,1170
-llama_cloud/types/base.py,sha256=cn_Zn61yLMDCMm1iZTPvKILSRlqRzOqZtSYyYBY5dIE,938
 llama_cloud/types/base_prompt_template.py,sha256=Cw3887tnytHZ5bJBSlniyU9k5ASidv9VYR86--IbNqo,1248
 llama_cloud/types/bedrock_embedding.py,sha256=qrUoVW9Q2DLg-3nBRfGsZqUWGszfzc6ZHR8LJiXTZk4,1908
 llama_cloud/types/bedrock_embedding_config.py,sha256=32dMhoA2cLx1jeogDnCl9WPVb83Hn99nAALnt5BM208,1147
@@ -135,7 +134,7 @@ llama_cloud/types/embedding_model_config_update.py,sha256=BiA1KbFT-TSvy5OEyChd0d
 llama_cloud/types/embedding_model_config_update_embedding_config.py,sha256=mrXFxzb9GRaH4UUnOe_05-uYUuiTgDDCRadAMbPmGgc,2991
 llama_cloud/types/eval_dataset.py,sha256=FIP4uHqUXg0LxGPaq-LmW2aTcEdQk-i5AYLbGqsQSV0,1310
 llama_cloud/types/eval_dataset_job_params.py,sha256=vcXLJWO581uigNvGAurPDgMeEFtQURWucLF5pemdeS0,1343
-llama_cloud/types/eval_dataset_job_record.py,sha256=lcX6iTJDngUsuvVeiqDgWDMieuIRJFRewKqiAGgwWAw,2185
+llama_cloud/types/eval_dataset_job_record.py,sha256=vBDz7xezpE8AB6Kw7sZLYxgMcv0dxUWVC01_fI2QuUU,2168
 llama_cloud/types/eval_execution_params.py,sha256=ntVaJh5SMZMPL4QLUiihVjUlg2SKbrezvbMKGlrF66Q,1369
 llama_cloud/types/eval_execution_params_override.py,sha256=ihEFbMRYmFJ5mWmFW24JjV6D0qqeDM4p829mSxMGtOQ,1195
 llama_cloud/types/eval_metric.py,sha256=vhO_teMLiyzBdzKpOBW8Bm9qCw2h6m3unp2XotB7pDQ,499
@@ -182,16 +181,16 @@ llama_cloud/types/input_message.py,sha256=Ym6-tX6CMWKuHfxRtyM2y16kqSS3BzHged9rFR
 llama_cloud/types/interval_usage_and_plan.py,sha256=qRZs0MsbJ_X53YfgNujKnJjRYhMn2Bn6bjBUKKUZnZc,1161
 llama_cloud/types/job_name_mapping.py,sha256=2dQFQlVHoeSlkyEKSEJv0M3PzJf7hMvkuABj3vMY7ys,1617
 llama_cloud/types/job_names.py,sha256=ZapQT__pLI14SagjGi8AsEwWY949hBoplQemMgb_Aoc,4098
-llama_cloud/types/job_record.py,sha256=-tp6w7dyd5KZMMynxSrL5W5YoJSdqTRWolx_f0_Hbh0,2069
+llama_cloud/types/job_record.py,sha256=r2WzLQXSOFogNMN2rl10rAlYI9OTCmVn06QaZXxa0rQ,2058
 llama_cloud/types/job_record_with_usage_metrics.py,sha256=iNV2do5TB_0e3PoOz_DJyAaM6Cn9G8KG-dGPGgEs5SY,1198
 llama_cloud/types/llama_extract_settings.py,sha256=Yh9Ah9W0X4l-znjYm4oNIh8-LCBc99JEQmGU87bUzWs,2225
 llama_cloud/types/llama_index_core_base_llms_types_chat_message.py,sha256=NelHo-T-ebVMhRKsqE_xV8AJW4c7o6lS0uEQnPsmTwg,1365
 llama_cloud/types/llama_index_core_base_llms_types_chat_message_blocks_item.py,sha256=tTglUqrSUaVc2Wsi4uIt5MU-80_oxZzTnhf8ziilVGY,874
-llama_cloud/types/llama_parse_parameters.py,sha256=mUJwdL73Ngcy2O64xKk1lWHbnWnQpwAEjTWScM_piuc,4881
+llama_cloud/types/llama_parse_parameters.py,sha256=EQsbxUsMOpmG3RgkZ151dPlwuI7puKw1CA4YIknst4U,5155
 llama_cloud/types/llama_parse_supported_file_extensions.py,sha256=B_0N3f8Aq59W9FbsH50mGBUiyWTIXQjHFl739uAyaQw,11207
 llama_cloud/types/llm.py,sha256=7iIItVPjURp4u5xxJDAFIefUdhUKwIuA245WXilJPXE,2234
 llama_cloud/types/llm_model_data.py,sha256=6rrycqGwlK3LZ2S-WtgmeomithdLhDCgwBBZQ5KLaso,1300
-llama_cloud/types/llm_parameters.py,sha256=taefXZiK4IsuPHcWXxfEd36OefUqAJVuMG2e9vjnyUA,1337
+llama_cloud/types/llm_parameters.py,sha256=RTKYt09lm9a1MlnBfYuTP2x_Ww4byUNNc1TqIel5O1Y,1377
 llama_cloud/types/local_eval.py,sha256=aJ8jRG0b5EL9cLjx281bzAzPw7Ar004Jfp6mBmyjuTA,1491
 llama_cloud/types/local_eval_results.py,sha256=YfK6AhfD0gr5apQBfrfzrTHDXvrk7ynAUUjNSKu9NVk,1380
 llama_cloud/types/local_eval_sets.py,sha256=XJSSriwRvkma889pPiBQrpRakKejKOX3tWPu1TGb1ug,1181
@@ -216,7 +215,7 @@ llama_cloud/types/open_ai_embedding_config.py,sha256=Mquc0JrtCo8lVYA2WW7q0ZikS3H
 llama_cloud/types/organization.py,sha256=p8mYRqSsGxw17AmdW8x8nP7P1UbdpYkwr51WTIjTVLw,1467
 llama_cloud/types/organization_create.py,sha256=hUXRwArIx_0D_lilpL7z-B0oJJ5yEX8Sbu2xqfH_9so,1086
 llama_cloud/types/page_figure_metadata.py,sha256=iIg6_f2SwJg6UcQo9X4MoSm_ygxnIBmFjS2LuUsI6qE,1528
-llama_cloud/types/page_screenshot_metadata.py,sha256=dXwWNDS7670xvIIuB1C_gLlsvAzQH4BRR3jLOojRvGs,1268
+llama_cloud/types/page_screenshot_metadata.py,sha256=lobrq0AsOr8sDwMgA9ytop8lRmRFvJW2oiql3yLvbjM,1328
 llama_cloud/types/page_screenshot_node_with_score.py,sha256=EdqoXbmARCz1DV14E2saCPshIeII709uM4cLwxw_mkM,1232
 llama_cloud/types/page_segmentation_config.py,sha256=VH8uuxnubnJak1gSpS64OoMueHidhsDB-2eq2tVHbag,998
 llama_cloud/types/page_splitter_node_parser.py,sha256=rQgS1CDk18UKA0r9OPvjdtM570jzFArdLCTxYAtZny8,1424
@@ -231,6 +230,7 @@ llama_cloud/types/parsing_job_json_result.py,sha256=BA3_u-ChHpE5wm08WmOvgPUsMsCl
 llama_cloud/types/parsing_job_markdown_result.py,sha256=gPIUO0JwtKwvSHcRYEr995DNl7VN3EaaSaj4aPHCP4o,1077
 llama_cloud/types/parsing_job_structured_result.py,sha256=w_Z4DOHjwUPmffjc4qJiGYbniWTpkjpVcD4irL1dDj0,1017
 llama_cloud/types/parsing_job_text_result.py,sha256=TP-7IRTWZLAZz7NYLkzi4PsGnaRJuPTt40p56Mk6Rhw,1065
+llama_cloud/types/parsing_mode.py,sha256=ppsF_Mia1FF26Zk3sZBwERxuqMbhvVDuVoR2kOsKJdE,1340
 llama_cloud/types/parsing_usage.py,sha256=JLlozu-vIkcRKqWaOVJ9Z2TrY7peJRTzOpYjOThGKGQ,1012
 llama_cloud/types/partition_names.py,sha256=zZZn-sn59gwch2fa7fGMwFWUEuu5Dfen3ZqKtcPnBEM,1877
 llama_cloud/types/permission.py,sha256=LjhZdo0oLvk7ZVIF1d6Qja--AKH5Ri0naUhuJvZS6Ng,1345
@@ -319,7 +319,7 @@ llama_cloud/types/validation_error_loc_item.py,sha256=LAtjCHIllWRBFXvAZ5QZpp7CPX
 llama_cloud/types/vertex_ai_embedding_config.py,sha256=DvQk2xMJFmo54MEXTzoM4KSADyhGm_ygmFyx6wIcQdw,1159
 llama_cloud/types/vertex_embedding_mode.py,sha256=yY23FjuWU_DkXjBb3JoKV4SCMqel2BaIMltDqGnIowU,1217
 llama_cloud/types/vertex_text_embedding.py,sha256=-C4fNCYfFl36ATdBMGFVPpiHIKxjk0KB1ERA2Ec20aU,1932
-llama_cloud-0.1.12.dist-info/LICENSE,sha256=_iNqtPcw1Ue7dZKwOwgPtbegMUkWVy15hC7bffAdNmY,1067
-llama_cloud-0.1.12.dist-info/METADATA,sha256=cq17QpgehHf9h_wM1gBd636awXVxMkUkCgxlcHtiDQ4,851
-llama_cloud-0.1.12.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-llama_cloud-0.1.12.dist-info/RECORD,,
+llama_cloud-0.1.13.dist-info/LICENSE,sha256=_iNqtPcw1Ue7dZKwOwgPtbegMUkWVy15hC7bffAdNmY,1067
+llama_cloud-0.1.13.dist-info/METADATA,sha256=z7rMCV38oE2gVWpA1bfFemHvMaNa-JuQp8U_f3FYRVo,800
+llama_cloud-0.1.13.dist-info/WHEEL,sha256=d2fvjOD7sXsVzChCqf0Ty0JbHKBaLYwDbGQDwQTnJ50,88
+llama_cloud-0.1.13.dist-info/RECORD,,

{llama_cloud-0.1.12.dist-info → llama_cloud-0.1.13.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.0
+Generator: poetry-core 1.7.0
 Root-Is-Purelib: true
 Tag: py3-none-any

llama_cloud/types/base.py

@@ -1,29 +0,0 @@
-# This file was auto-generated by Fern from our API Definition.
-
-import datetime as dt
-import typing
-
-from ..core.datetime_utils import serialize_datetime
-
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
-
-
-class Base(pydantic.BaseModel):
-    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}