make original height + width optional in the parse result

Bumps [actions/setup-python](https://github.com/actions/setup-python) from 4 to 5.
- [Release notes](https://github.com/actions/setup-python/releases)
- [Commits](https://github.com/actions/setup-python/compare/v4...v5)

---
updated-dependencies:
- dependency-name: actions/setup-python
  dependency-version: '5'
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+# and
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/workflows/build_package.yml

@@ -21,9 +21,9 @@ jobs:
         os: [ubuntu-latest, windows-latest]
         python-version: ["3.9"]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Set up python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install Poetry

.github/workflows/codeql.yml

@@ -1,14 +1,3 @@
-# For most projects, this workflow file will not need changing; you simply need
-# to commit it to your repository.
-#
-# You may wish to alter this file to override the set of languages analyzed,
-# or to provide custom queries or build logic.
-#
-# ******** NOTE ********
-# We have attempted to detect the languages in your repository. Please check
-# the `language` matrix defined below to confirm you have the correct set of
-# supported CodeQL languages.
-#
 name: "CodeQL"
 
 on:
@@ -28,54 +17,25 @@ jobs:
     #   - https://gh.io/supported-runners-and-hardware-resources
     #   - https://gh.io/using-larger-runners
     # Consider using larger runners for possible analysis time improvements.
-    runs-on: ${{ (matrix.language == 'swift' && 'macos-latest') || 'ubuntu-latest' }}
-    timeout-minutes: ${{ (matrix.language == 'swift' && 120) || 360 }}
+    runs-on: "ubuntu-latest"
+    timeout-minutes: 360
     permissions:
       actions: read
       contents: read
       security-events: write
 
-    strategy:
-      fail-fast: false
-      matrix:
-        language: ["python"]
-        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby', 'swift' ]
-        # Use only 'java' to analyze code written in Java, Kotlin or both
-        # Use only 'javascript' to analyze code written in JavaScript, TypeScript or both
-        # Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
-
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       # Initializes the CodeQL tools for scanning.
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v2
+        uses: github/codeql-action/init@v3
         with:
-          languages: ${{ matrix.language }}
-          # If you wish to specify custom queries, you can do so here or in a config file.
-          # By default, queries listed here will override any specified in a config file.
-          # Prefix the list here with "+" to use these queries and those in the config file.
-
-          # For more details on CodeQL's query packs, refer to: https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
-          # queries: security-extended,security-and-quality
-
-      # Autobuild attempts to build any compiled languages (C/C++, C#, Go, Java, or Swift).
-      # If this step fails, then you should remove it and run the build manually (see below)
-      - name: Autobuild
-        uses: github/codeql-action/autobuild@v2
-
-      # ℹ️ Command-line programs to run using the OS shell.
-      # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
-
-      #   If the Autobuild fails above, remove it and uncomment the following three lines.
-      #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
-
-      # - run: |
-      #     echo "Run, Build Application using script"
-      #     ./location_of_script_within_repo/buildscript.sh
+          languages: python
+          dependency-caching: true
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v2
+        uses: github/codeql-action/analyze@v3
         with:
-          category: "/language:${{matrix.language}}"
+          category: "/language:python"

.github/workflows/lint.yml

@@ -18,11 +18,11 @@ jobs:
       matrix:
         python-version: ["3.9"]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: ${{ github.event_name == 'pull_request' && 2 || 0 }}
       - name: Set up python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install Poetry

.github/workflows/publish_release.yml

@@ -18,9 +18,9 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Set up python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ env.PYTHON_VERSION }}
 

.github/workflows/unit_test.yml

@@ -19,11 +19,11 @@ jobs:
       matrix:
         python-version: ["3.9", "3.10", "3.11", "3.12"]
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
       - name: Set up python ${{ matrix.python-version }}
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install Poetry

llama_cloud_services/extract/__init__.py

@@ -1,7 +1,17 @@
 from llama_cloud_services.extract.extract import (
     LlamaExtract,
+    ExtractConfig,
     ExtractionAgent,
     SourceText,
+    ExtractTarget,
+    ExtractMode,
 )
 
-__all__ = ["LlamaExtract", "ExtractionAgent", "SourceText"]
+__all__ = [
+    "LlamaExtract",
+    "ExtractionAgent",
+    "SourceText",
+    "ExtractConfig",
+    "ExtractTarget",
+    "ExtractMode",
+]

llama_cloud_services/extract/extract.py

@@ -10,13 +10,10 @@ import httpx
 from pydantic import BaseModel
 from llama_cloud import (
     ExtractAgent as CloudExtractAgent,
-    ExtractAgentCreate,
     ExtractConfig,
     ExtractJob,
     ExtractJobCreate,
     ExtractRun,
-    ExtractSchemaValidateRequest,
-    ExtractAgentUpdate,
     File,
     ExtractMode,
     StatusEnum,
@@ -26,7 +23,11 @@ from llama_cloud import (
     PaginatedExtractRunsResponse,
 )
 from llama_cloud.client import AsyncLlamaCloud
-from llama_cloud_services.extract.utils import JSONObjectType, augment_async_errors
+from llama_cloud_services.extract.utils import (
+    JSONObjectType,
+    augment_async_errors,
+    ExperimentalWarning,
+)
 from llama_index.core.schema import BaseComponent
 from llama_index.core.async_utils import run_jobs
 from llama_index.core.bridge.pydantic import Field, PrivateAttr
@@ -118,6 +119,25 @@ def run_in_thread(
     return thread_pool.submit(run_coro).result()
 
 
+def _extraction_config_warning(config: ExtractConfig) -> None:
+    if config.extraction_mode == ExtractMode.ACCURATE:
+        warnings.warn("ACCURATE extraction mode is deprecated. Using BALANCED instead.")
+        config.extraction_mode = ExtractMode.BALANCED
+    if config.use_reasoning:
+        warnings.warn(
+            "`use_reasoning` is an experimental feature. Results will be available in "
+            "the `extraction_metadata` field for the extraction run.",
+            ExperimentalWarning,
+        )
+    if config.cite_sources:
+        warnings.warn(
+            "`cite_sources` is an experimental feature. This may greatly increase the "
+            "size of the response, and slow down the extraction. Results will be "
+            "available in the `extraction_metadata` field for the extraction run.",
+            ExperimentalWarning,
+        )
+
+
 class ExtractionAgent:
     """Class representing a single extraction agent with methods for extraction operations."""
 
@@ -178,7 +198,7 @@ class ExtractionAgent:
             )
         validated_schema = self._run_in_thread(
             self._client.llama_extract.validate_extraction_schema(
-                request=ExtractSchemaValidateRequest(data_schema=processed_schema)
+                data_schema=processed_schema
             )
         )
         self._data_schema = validated_schema.data_schema
@@ -189,6 +209,7 @@ class ExtractionAgent:
 
     @config.setter
     def config(self, config: ExtractConfig) -> None:
+        _extraction_config_warning(config)
         self._config = config
 
     def _run_in_thread(self, coro: Coroutine[Any, Any, T]) -> T:
@@ -307,10 +328,8 @@ class ExtractionAgent:
         self._agent = self._run_in_thread(
             self._client.llama_extract.update_extraction_agent(
                 extraction_agent_id=self.id,
-                request=ExtractAgentUpdate(
-                    data_schema=self.data_schema,
-                    config=self.config,
-                ),
+                data_schema=self.data_schema,
+                config=self.config,
             )
         )
 
@@ -602,7 +621,7 @@ class LlamaExtract(BaseComponent):
             httpx_timeout=httpx_timeout,
             verbose=verbose,
         )
-        self._httpx_client = httpx.AsyncClient(verify=verify, timeout=httpx_timeout)
+        self._httpx_client = httpx.AsyncClient(verify=verify, timeout=httpx_timeout)  # type: ignore
         self.verify = verify
         self.httpx_timeout = httpx_timeout
 
@@ -659,11 +678,7 @@ class LlamaExtract(BaseComponent):
             ExtractionAgent: The created extraction agent
         """
         if config is not None:
-            if config.extraction_mode == ExtractMode.ACCURATE:
-                warnings.warn(
-                    "ACCURATE extraction mode is deprecated. Using BALANCED instead."
-                )
-                config.extraction_mode = ExtractMode.BALANCED
+            _extraction_config_warning(config)
         else:
             config = DEFAULT_EXTRACT_CONFIG
 
@@ -680,11 +695,9 @@ class LlamaExtract(BaseComponent):
             self._async_client.llama_extract.create_extraction_agent(
                 project_id=self._project_id,
                 organization_id=self._organization_id,
-                request=ExtractAgentCreate(
-                    name=name,
-                    data_schema=data_schema,
-                    config=config,
-                ),
+                name=name,
+                data_schema=data_schema,
+                config=config,
             )
         )
 

llama_cloud_services/extract/utils.py

@@ -32,3 +32,9 @@ def augment_async_errors() -> Generator[None, None, None]:
 
 JSONType = Union[Dict[str, Any], List[Any], str, int, float, bool, None]
 JSONObjectType = Dict[str, JSONType]
+
+
+class ExperimentalWarning(Warning):
+    """Warning for experimental features."""
+
+    pass

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[FailedPageMode] = 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 +772,19 @@ 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.value
+
+        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/types.py

@@ -60,8 +60,12 @@ class ImageItem(BaseModel):
     width: float = Field(description="The width of the image.")
     x: float = Field(description="The x-coordinate of the image.")
     y: float = Field(description="The y-coordinate of the image.")
-    original_width: int = Field(description="The original width of the image.")
-    original_height: int = Field(description="The original height of the image.")
+    original_width: Optional[int] = Field(
+        default=None, description="The original width of the image."
+    )
+    original_height: Optional[int] = Field(
+        default=None, description="The original height of the image."
+    )
     type: Optional[str] = Field(default=None, description="The type of the image.")
 
 

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 = "0.6.17"
 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 = ">=0.6.17"
 
 [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 = "0.6.17"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = ["Logan Markewich <logan@runllama.ai>"]
 license = "MIT"
@@ -18,7 +18,7 @@ packages = [{include = "llama_cloud_services"}]
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
 llama-index-core = ">=0.11.0"
-llama-cloud = "^0.1.18"
+llama-cloud = "==0.1.19"
 pydantic = "!=2.10"
 click = "^8.1.7"
 python-dotenv = "^1.0.1"

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",
 )