Page error parameters (#691)

* skip llama-report tests in cicd

* skip llama-report tests in cicd

llama_cloud_services/parse/__init__.py

@@ -1,3 +1,8 @@
-from llama_cloud_services.parse.base import LlamaParse, ResultType
+from llama_cloud_services.parse.base import (
+    LlamaParse,
+    ResultType,
+    ParsingMode,
+    FailedPageMode,
+)
 
-__all__ = ["LlamaParse", "ResultType"]
+__all__ = ["LlamaParse", "ResultType", "ParsingMode", "FailedPageMode"]

llama_cloud_services/parse/base.py

@@ -23,6 +23,8 @@ from llama_cloud_services.parse.types import JobResult
 from llama_cloud_services.parse.utils import (
     SUPPORTED_FILE_TYPES,
     ResultType,
+    ParsingMode,
+    FailedPageMode,
     nest_asyncio_err,
     nest_asyncio_msg,
     make_api_request,
@@ -291,6 +293,10 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="If set to true, the parser will output tables as HTML in the markdown.",
     )
+    page_error_tolerance: Optional[float] = Field(
+        default=None,
+        description="The error tolerance for the number of pages with error in a doc (percentage express as 0-1). If we fail to parse a greater percentage of pages than the tolerance value we fail the job.",
+    )
     page_prefix: Optional[str] = Field(
         default=None,
         description="A templated prefix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number.",
@@ -303,7 +309,7 @@ class LlamaParse(BasePydanticReader):
         default=None,
         description="A templated suffix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number.",
     )
-    parse_mode: Optional[str] = Field(
+    parse_mode: Optional[Union[ParsingMode, str]] = Field(
         default=None,
         description="The parsing mode to use, see ParsingMode enum for possible values ",
     )
@@ -315,6 +321,18 @@ class LlamaParse(BasePydanticReader):
         default=False,
         description="Preserve grid alignment across page in text mode.",
     )
+    replace_failed_page_mode: Optional[Union[FailedPageMode, str]] = Field(
+        default=None,
+        description="The mode to use to replace the failed page, see FailedPageMode enum for possible value. If set, the parser will replace the failed page with the specified mode. If not set, the default mode (raw_text) will be used.",
+    )
+    replace_failed_page_with_error_message_prefix: Optional[str] = Field(
+        default=None,
+        description="A prefix to add before error message in failed pages. If not set, no prefix will be used.",
+    )
+    replace_failed_page_with_error_message_suffix: Optional[str] = Field(
+        default=None,
+        description="A suffix to add after error message in failed pages. If not set, no suffix will be used.",
+    )
     skip_diagonal_text: Optional[bool] = Field(
         default=False,
         description="If set to true, the parser will ignore diagonal text (when the text rotation in degrees modulo 90 is not 0).",
@@ -723,6 +741,9 @@ class LlamaParse(BasePydanticReader):
         if self.output_tables_as_HTML:
             data["output_tables_as_HTML"] = self.output_tables_as_HTML
 
+        if self.page_error_tolerance is not None:
+            data["page_error_tolerance"] = self.page_error_tolerance
+
         if self.page_prefix is not None:
             data["page_prefix"] = self.page_prefix
 
@@ -751,6 +772,18 @@ class LlamaParse(BasePydanticReader):
                 "preserve_layout_alignment_across_pages"
             ] = self.preserve_layout_alignment_across_pages
 
+        if self.replace_failed_page_mode is not None:
+            data["replace_failed_page_mode"] = self.replace_failed_page_mode
+        if self.replace_failed_page_with_error_message_prefix is not None:
+            data[
+                "replace_failed_page_with_error_message_prefix"
+            ] = self.replace_failed_page_with_error_message_prefix
+
+        if self.replace_failed_page_with_error_message_suffix is not None:
+            data[
+                "replace_failed_page_with_error_message_suffix"
+            ] = self.replace_failed_page_with_error_message_suffix
+
         if self.skip_diagonal_text:
             data["skip_diagonal_text"] = self.skip_diagonal_text
 

llama_cloud_services/parse/utils.py

@@ -34,6 +34,17 @@ class ParsingMode(str, Enum):
     parse_page_with_lvm = "parse_page_with_lvm"
     parse_page_with_agent = "parse_page_with_agent"
     parse_document_with_llm = "parse_document_with_llm"
+    parse_document_with_agent = "parse_document_with_agent"
+
+
+class FailedPageMode(str, Enum):
+    """
+    Enum for representing the different available page error handling modes
+    """
+
+    raw_text = "raw_text"
+    blank_page = "blank_page"
+    error_message = "error_message"
 
 
 class Language(str, Enum):

llama_parse/llama_parse/__init__.py

@@ -1,3 +1,8 @@
-from llama_cloud_services.parse import LlamaParse, ResultType
+from llama_cloud_services.parse import (
+    LlamaParse,
+    ResultType,
+    ParsingMode,
+    FailedPageMode,
+)
 
-__all__ = ["LlamaParse", "ResultType"]
+__all__ = ["LlamaParse", "ResultType", "ParsingMode", "FailedPageMode"]

llama_parse/llama_parse/base.py

@@ -1,6 +1,8 @@
 from llama_cloud_services.parse.base import (
     LlamaParse,
     ResultType,
+    ParsingMode,
+    FailedPageMode,
     FileInput,
     _DEFAULT_SEPARATOR,
     JOB_RESULT_URL,
@@ -12,6 +14,8 @@ __all__ = [
     "LlamaParse",
     "ResultType",
     "FileInput",
+    "ParsingMode",
+    "FailedPageMode",
     "_DEFAULT_SEPARATOR",
     "JOB_RESULT_URL",
     "JOB_STATUS_ROUTE",

llama_parse/llama_parse/utils.py

@@ -2,10 +2,14 @@ from llama_cloud_services.parse.utils import (
     SUPPORTED_FILE_TYPES,
     Language,
     ResultType,
+    ParsingMode,
+    FailedPageMode,
 )
 
 __all__ = [
     "SUPPORTED_FILE_TYPES",
     "Language",
     "ResultType",
+    "ParsingMode",
+    "FailedPageMode",
 ]

llama_parse/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.6.13"
+version = "0.6.14"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"
@@ -13,7 +13,7 @@ packages = [{include = "llama_parse"}]
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
-llama-cloud-services = ">=0.6.13"
+llama-cloud-services = ">=0.6.14"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0.0"

pyproject.toml

@@ -8,7 +8,7 @@ python_version = "3.10"
 
 [tool.poetry]
 name = "llama-cloud-services"
-version = "0.6.13"
+version = "0.6.14"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = ["Logan Markewich <logan@runllama.ai>"]
 license = "MIT"

tests/report/test_llama_report.py

@@ -7,7 +7,8 @@ from llama_cloud_services.report import LlamaReport, ReportClient
 
 # Skip tests if no API key is set
 pytestmark = pytest.mark.skipif(
-    not os.getenv("LLAMA_CLOUD_API_KEY"), reason="No API key provided"
+    not os.getenv("LLAMA_CLOUD_API_KEY") or os.getenv("CI") == "true",
+    reason="No API key provided",
 )