lint

extract.md

@@ -398,6 +398,6 @@ Another option (orthogonal to the above) is to break the document into smaller s
 ## Additional Resources
 
 - [Extract Documentation](https://docs.cloud.llamaindex.ai/llamaextract/getting_started) - Details on Extract features, API and examples.
-- [Example Notebook](examples/extract/resume_screening.ipynb) - Detailed walkthrough of resume parsing
+- [Example Notebook](docs/examples-py/extract/resume_screening.ipynb) - Detailed walkthrough of resume parsing
 - [Example Application with TypeScript](./examples-ts/extract/) - End-to-end examples using LlamaExtract TypeScript client.
 - [Discord Community](https://discord.com/invite/eN6D2HQ4aX) - Get help and share feedback

parse.md

@@ -97,7 +97,7 @@ for page in result.pages:
     print(page.structuredData)
 ```
 
-See more details about the result object in the [example notebook](./examples/parse/demo_json_tour.ipynb).
+See more details about the result object in the [example notebook](./docs/examples-py/parse/demo_json_tour.ipynb).
 
 ### Using with file object / bytes
 
@@ -153,10 +153,10 @@ Full documentation for `SimpleDirectoryReader` can be found on the [LlamaIndex D
 
 Several end-to-end indexing examples can be found in the examples folder
 
-- [Getting Started](examples/parse/demo_basic.ipynb)
-- [Advanced RAG Example](examples/parse/demo_advanced.ipynb)
-- [Raw API Usage](examples/parse/demo_api.ipynb)
-- [Result Object Tour](examples/parse/demo_json_tour.ipynb)
+- [Getting Started](docs/examples-py/parse/demo_basic.ipynb)
+- [Advanced RAG Example](docs/examples-py/parse/demo_advanced.ipynb)
+- [Raw API Usage](docs/examples-py/parse/demo_api.ipynb)
+- [Result Object Tour](docs/examples-py/parse/demo_json_tour.ipynb)
 
 ## Documentation
 

py/CHANGELOG.md

@@ -1,24 +1,5 @@
 # llama-cloud-services-py
 
-## 0.6.91
-
-### Patch Changes
-
-- 07ec282: Bump up patch versions for python packages
-- 3040951: Use error description in ExtractedData invalid extraction error
-
-## 0.6.90
-
-### Patch Changes
-
-- 19cbb25: Remove extension filter
-
-## 0.6.89
-
-### Patch Changes
-
-- b9b83c9: Parse bounding boxes from extract jobs results in agent data
-
 ## 0.6.88
 
 ### Patch Changes

py/llama_cloud_services/beta/agent_data/__init__.py

@@ -11,9 +11,6 @@ from .schema import (
     InvalidExtractionData,
     ExtractedFieldMetadata,
     ExtractedFieldMetaDataDict,
-    FieldCitation,
-    BoundingBox,
-    PageDimensions,
 )
 from .client import AsyncAgentDataClient
 
@@ -31,7 +28,4 @@ __all__ = [
     "InvalidExtractionData",
     "ExtractedFieldMetadata",
     "ExtractedFieldMetaDataDict",
-    "FieldCitation",
-    "BoundingBox",
-    "PageDimensions",
 ]

py/llama_cloud_services/beta/agent_data/schema.py

@@ -174,22 +174,6 @@ class TypedAgentDataItems(BaseModel, Generic[AgentDataT]):
     )
 
 
-class BoundingBox(BaseModel):
-    """Bounding box coordinates for a citation location on a page."""
-
-    x: float = Field(description="X coordinate of the bounding box origin")
-    y: float = Field(description="Y coordinate of the bounding box origin")
-    w: float = Field(description="Width of the bounding box")
-    h: float = Field(description="Height of the bounding box")
-
-
-class PageDimensions(BaseModel):
-    """Dimensions of a page in the source document."""
-
-    width: float = Field(description="Width of the page")
-    height: float = Field(description="Height of the page")
-
-
 class FieldCitation(BaseModel):
     page: Optional[int] = Field(
         None, description="The page number that the field occurred on"
@@ -198,14 +182,6 @@ class FieldCitation(BaseModel):
         None,
         description="The original text this field's value was derived from",
     )
-    bounding_boxes: Optional[List[BoundingBox]] = Field(
-        None,
-        description="Bounding boxes indicating where the citation appears on the page",
-    )
-    page_dimensions: Optional[PageDimensions] = Field(
-        None,
-        description="Dimensions of the page containing the citation",
-    )
 
 
 class ExtractedFieldMetadata(BaseModel):
@@ -225,10 +201,6 @@ class ExtractedFieldMetadata(BaseModel):
         None,
         description="The confidence score for the field based on the extracted text only",
     )
-    parsing_confidence: Optional[float] = Field(
-        None,
-        description="The confidence score for the field based on the parsing/OCR quality",
-    )
     citation: Optional[List[FieldCitation]] = Field(
         None,
         description="The citation for the field, including page number and matching text",
@@ -475,49 +447,26 @@ class ExtractedData(BaseModel, Generic[ExtractedT]):
                 },
             )
         except ValidationError as e:
-            # Capture the job-level error from the extraction run if available
-            job_error = result.error
-
             invalid_item = ExtractedData[Dict[str, Any]].create(
                 data=result.data or {},
                 status="error",
                 field_metadata=field_metadata,
-                metadata={
-                    "extraction_error": str(e),
-                    **({"job_error": job_error} if job_error else {}),
-                    **(metadata or {}),
-                },
+                metadata={"extraction_error": str(e), **(metadata or {})},
                 file_id=file_id,
                 file_name=file_name,
                 file_hash=file_hash,
             )
-            raise InvalidExtractionData(invalid_item, extraction_error=job_error) from e
+            raise InvalidExtractionData(invalid_item) from e
 
 
 class InvalidExtractionData(Exception):
     """
     Exception raised when the extracted data does not conform to the schema.
-
-    Attributes:
-        invalid_item: The ExtractedData instance containing the invalid data and metadata
-        extraction_error: The error message from the extraction job, if available
     """
 
-    def __init__(
-        self,
-        invalid_item: ExtractedData[Dict[str, Any]],
-        extraction_error: Optional[str] = None,
-    ):
+    def __init__(self, invalid_item: ExtractedData[Dict[str, Any]]):
         self.invalid_item = invalid_item
-        self.extraction_error = extraction_error
-
-        # Build an informative error message
-        if extraction_error:
-            message = f"Extraction error: {extraction_error}"
-        else:
-            message = "Not able to parse the extracted data, parsed invalid format"
-
-        super().__init__(message)
+        super().__init__("Not able to parse the extracted data, parsed invalid format")
 
 
 def calculate_overall_confidence(

py/llama_cloud_services/files/client.py

@@ -3,7 +3,7 @@ from typing import BinaryIO
 import os
 from pathlib import Path
 from llama_cloud.client import AsyncLlamaCloud
-from llama_cloud.types import File
+from llama_cloud.types import File, FileCreate
 from typing import Optional
 from llama_cloud_services.utils import SourceText, FileInput
 
@@ -73,9 +73,11 @@ class FileClient:
             presigned_url = await self.client.files.generate_presigned_url(
                 project_id=self.project_id,
                 organization_id=self.organization_id,
-                name=name,
-                external_file_id=external_file_id,
-                file_size=file_size,
+                request=FileCreate(
+                    name=name,
+                    external_file_id=external_file_id,
+                    file_size=file_size,
+                ),
             )
             httpx_client = self.client._client_wrapper.httpx_client
             upload_response = await httpx_client.put(

py/llama_cloud_services/index/base.py

@@ -21,6 +21,7 @@ from llama_cloud import (
     PipelineCreateTransformConfig,
     PipelineFileCreateCustomMetadataValue,
     PipelineType,
+    ProjectCreate,
     ManagedIngestionStatus,
     CloudDocumentCreate,
     CloudDocument,
@@ -506,19 +507,14 @@ class LlamaCloudIndex(BaseManagedIndex):
         client = get_client(api_key, base_url, app_url, timeout)
 
         if project_id is None:
-            # get project by name
-            projects = client.projects.list_projects(
+            # create project if it doesn't exist
+            project = client.projects.upsert_project(
                 organization_id=organization_id,
-                project_name=project_name,
+                request=ProjectCreate(name=project_name),
             )
-            if not projects:
-                raise ValueError(
-                    f"Project '{project_name}' not found. Please create it first in the LlamaCloud UI."
-                )
-            project = projects[0]
             project_id = project.id
             if verbose:
-                print(f"Found project {project_id} with name {project_name}")
+                print(f"Created project {project_id} with name {project_name}")
 
         # create pipeline
         pipeline_create = PipelineCreate(
@@ -567,20 +563,15 @@ class LlamaCloudIndex(BaseManagedIndex):
         app_url = app_url or os.environ.get("LLAMA_CLOUD_APP_URL", DEFAULT_APP_URL)
         aclient = get_aclient(api_key, base_url, app_url, timeout)
 
-        # get project by name
-        projects = await aclient.projects.list_projects(
-            organization_id=organization_id, project_name=project_name
+        # create project if it doesn't exist
+        project = await aclient.projects.upsert_project(
+            organization_id=organization_id, request=ProjectCreate(name=project_name)
         )
-        if not projects:
-            raise ValueError(
-                f"Project '{project_name}' not found. Please create it first in the LlamaCloud UI."
-            )
-        project = projects[0]
         if project.id is None:
-            raise ValueError(f"Failed to get project {project_name}")
+            raise ValueError(f"Failed to create/get project {project_name}")
 
         if verbose:
-            print(f"Found project {project.id} with name {project.name}")
+            print(f"Created project {project.id} with name {project.name}")
 
         # create pipeline
         pipeline_create = PipelineCreate(

py/llama_cloud_services/parse/base.py

@@ -751,9 +751,11 @@ class LlamaParse(BasePydanticReader):
             file_path = str(file_input)
             file_ext = os.path.splitext(file_path)[1].lower()
             if file_ext not in SUPPORTED_FILE_TYPES:
-                mime_type = "application/octet-stream"
-            else:
-                mime_type = mimetypes.guess_type(file_path)[0]
+                raise Exception(
+                    f"Currently, only the following file types are supported: {SUPPORTED_FILE_TYPES}\n"
+                    f"Current file type: {file_ext}"
+                )
+            mime_type = mimetypes.guess_type(file_path)[0]
             # Open the file here for the duration of the async context
             # load data, set the mime type
             fs = fs or get_default_fs()

py/llama_parse/CHANGELOG.md

@@ -1,29 +1,5 @@
 # llama_parse
 
-## 0.6.91
-
-### Patch Changes
-
-- 07ec282: Bump up patch versions for python packages
-- Updated dependencies [07ec282]
-- Updated dependencies [3040951]
-  - llama-cloud-services-py@0.6.91
-
-## 0.6.90
-
-### Patch Changes
-
-- 19cbb25: Remove extension filter
-- Updated dependencies [19cbb25]
-  - llama-cloud-services-py@0.6.90
-
-## 0.6.89
-
-### Patch Changes
-
-- Updated dependencies [b9b83c9]
-  - llama-cloud-services-py@0.6.89
-
 ## 0.6.88
 
 ### Patch Changes

py/llama_parse/README.md

@@ -146,9 +146,9 @@ Full documentation for `SimpleDirectoryReader` can be found on the [LlamaIndex D
 
 Several end-to-end indexing examples can be found in the examples folder
 
-- [Getting Started](../../examples/parse/demo_basic.ipynb)
-- [Advanced RAG Example](../../examples/parse/demo_advanced.ipynb)
-- [Raw API Usage](../../examples/parse/demo_api.ipynb)
+- [Getting Started](/docs/examples-py/parse/demo_basic.ipynb)
+- [Advanced RAG Example](/docs/examples-py/parse/demo_advanced.ipynb)
+- [Raw API Usage](/docs/examples-py/parse/demo_api.ipynb)
 
 ## Documentation
 

py/llama_parse/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama_parse",
-  "version": "0.6.91",
+  "version": "0.6.88",
   "description": "",
   "main": "index.js",
   "private": false,

py/llama_parse/pyproject.toml

@@ -11,13 +11,13 @@ dev = [
 
 [project]
 name = "llama-parse"
-version = "0.6.91"
+version = "0.6.88"
 description = "Parse files into RAG-Optimized formats."
 authors = [{name = "Logan Markewich", email = "logan@llamaindex.ai"}]
 requires-python = ">=3.9,<4.0"
 readme = "README.md"
 license = "MIT"
-dependencies = ["llama-cloud-services>=0.6.91"]
+dependencies = ["llama-cloud-services>=0.6.88"]
 
 [project.scripts]
 llama-parse = "llama_parse.cli.main:parse"

py/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama-cloud-services-py",
-  "version": "0.6.91",
+  "version": "0.6.88",
   "private": false,
   "license": "MIT",
   "scripts": {},

py/pyproject.toml

@@ -23,7 +23,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.91"
+version = "0.6.88"
 description = "Tailored SDK clients for LlamaCloud services."
 authors = [{name = "Logan Markewich", email = "logan@runllama.ai"}]
 requires-python = ">=3.9,<4.0"
@@ -31,7 +31,7 @@ readme = "README.md"
 license = "MIT"
 dependencies = [
   "llama-index-core>=0.12.0",
-  "llama-cloud==0.1.46",
+  "llama-cloud==0.1.45",
   "pydantic>=2.8,!=2.10",
   "click>=8.1.7,<9",
   "python-dotenv>=1.0.1,<2",

py/tests/extract/conftest.py

@@ -1,43 +1,11 @@
 import os
-from typing import Any, Dict, List, Optional, Union
-
-from llama_cloud.core.api_error import ApiError
-from llama_cloud.types import ExtractConfig
-from pydantic import BaseModel
-from tenacity import (
-    retry,
-    retry_if_exception,
-    stop_after_attempt,
-    wait_exponential,
-)
-
-from llama_cloud_services.extract import ExtractionAgent, LlamaExtract
+from typing import List
+from llama_cloud_services.extract import LlamaExtract
 
 # Global storage for agents to cleanup
 _TEST_AGENTS_TO_CLEANUP: List[str] = []
 
 
-def _is_rate_limit_error(exception: BaseException) -> bool:
-    """Check if the exception is a rate limit error (429)."""
-    return isinstance(exception, ApiError) and exception.status_code == 429
-
-
-@retry(
-    retry=retry_if_exception(_is_rate_limit_error),
-    wait=wait_exponential(multiplier=1, min=1, max=30),
-    stop=stop_after_attempt(5),
-    reraise=True,
-)
-def create_agent_with_retry(
-    extractor: LlamaExtract,
-    name: str,
-    data_schema: Union[Dict[str, Any], type[BaseModel]],
-    config: Optional[ExtractConfig] = None,
-) -> ExtractionAgent:
-    """Create an extraction agent with retry logic for rate limiting."""
-    return extractor.create_agent(name=name, data_schema=data_schema, config=config)
-
-
 def pytest_configure(config):
     """Register custom markers for extract tests."""
     config.addinivalue_line("markers", "agent_name: custom agent name for test")

py/tests/extract/test_extract_api.py

@@ -6,7 +6,7 @@ from pydantic import BaseModel
 from llama_cloud_services.extract import LlamaExtract, ExtractionAgent, SourceText
 from llama_cloud.types import ExtractConfig, ExtractMode, ExtractRun
 from tests.extract.util import load_test_dotenv
-from .conftest import register_agent_for_cleanup, create_agent_with_retry
+from .conftest import register_agent_for_cleanup
 
 load_test_dotenv()
 
@@ -87,7 +87,7 @@ def test_agent(llama_extract, test_agent_name, test_schema_dict, request):
     except Exception as e:
         print(f"Warning: Failed to cleanup existing agent: {e}")
 
-    agent = create_agent_with_retry(llama_extract, name=name, data_schema=schema)
+    agent = llama_extract.create_agent(name=name, data_schema=schema)
 
     # Add agent to cleanup list via conftest helper
     register_agent_for_cleanup(agent.id)

py/tests/extract/test_extract_e2e.py

@@ -8,7 +8,7 @@ import uuid
 from llama_cloud.types import ExtractConfig, ExtractMode
 from deepdiff import DeepDiff
 from tests.extract.util import json_subset_match_score, load_test_dotenv
-from .conftest import register_agent_for_cleanup, create_agent_with_retry
+from .conftest import register_agent_for_cleanup
 
 load_test_dotenv()
 
@@ -117,10 +117,8 @@ def extraction_agent(test_case: ExtractionTestCase, extractor: LlamaExtract):
     except Exception as e:
         print(f"Warning: Failed to cleanup existing agent: {str(e)}")
 
-    # Create new agent with retry logic for rate limiting
-    agent = create_agent_with_retry(
-        extractor, name=agent_name, data_schema=schema, config=test_case.config
-    )
+    # Create new agent
+    agent = extractor.create_agent(agent_name, schema, config=test_case.config)
 
     # Register agent for cleanup at the end of the test session
     register_agent_for_cleanup(agent.id)

py/tests/index/test_index.py

@@ -8,6 +8,7 @@ from llama_cloud import (
     AutoTransformConfig,
     PipelineCreate,
     PipelineFileCreate,
+    ProjectCreate,
     CompositeRetrievalMode,
     LlamaParseParameters,
     ReRankConfig,
@@ -59,15 +60,11 @@ def local_figures_file() -> str:
 def _setup_index_with_file(
     client: LlamaCloud, index_name: str, remote_file: Tuple[str, str]
 ) -> LlamaCloudIndex:
-    # get project by name
-    projects = client.projects.list_projects(
-        organization_id=organization_id, project_name=project_name
+    # create project if it doesn't exist
+    project_create = ProjectCreate(name=project_name)
+    project = client.projects.upsert_project(
+        organization_id=organization_id, request=project_create
     )
-    if not projects:
-        raise ValueError(
-            f"Project '{project_name}' not found. Please create it first in the LlamaCloud UI."
-        )
-    project = projects[0]
 
     # create pipeline
     pipeline_create = PipelineCreate(

py/unit_tests/beta/agent/test_agent_data_schema.py

@@ -11,12 +11,10 @@ from llama_cloud.types.aggregate_group import AggregateGroup
 from pydantic import BaseModel, Field, ValidationError
 
 from llama_cloud_services.beta.agent_data.schema import (
-    BoundingBox,
     ExtractedData,
     ExtractedFieldMetadata,
     FieldCitation,
     InvalidExtractionData,
-    PageDimensions,
     TypedAgentData,
     TypedAggregateGroup,
     calculate_overall_confidence,
@@ -423,7 +421,6 @@ def create_extract_run(
     },
     data_schema: Dict[str, Any] = {},
     file: File = create_file(),
-    error: Optional[str] = None,
 ) -> ExtractRun:
     return ExtractRun.parse_obj(
         {
@@ -440,7 +437,6 @@ def create_extract_run(
             "status": "SUCCESS",
             "project_id": str(uuid.uuid4()),
             "from_ui": False,
-            "error": error,
         }
     )
 
@@ -546,46 +542,6 @@ def test_extracted_data_from_extraction_result_invalid_data():
     assert invalid_data.field_metadata["name"].confidence == 0.9
     assert invalid_data.overall_confidence == 0.9
 
-    # Verify default error message when no job error present
-    assert exc_info.value.extraction_error is None
-    assert "Not able to parse the extracted data" in str(exc_info.value)
-
-
-def test_extracted_data_from_extraction_result_with_job_error():
-    """Test ExtractedData.from_extraction_result with job-level error prominently displayed."""
-    job_error_message = "Failed to process document: unsupported file format"
-
-    # Create ExtractRun with both invalid data AND a job-level error
-    extract_run = create_extract_run(
-        data={
-            "missing_name": "Valid Name",
-            "age": "not_a_number",
-        },  # Invalid age, missing name
-        extraction_metadata={
-            "name": {"confidence": 0.9},
-        },
-        data_schema={},
-        file=create_file(id="error-file", name="bad_data.pdf"),
-        error=job_error_message,
-    )
-
-    # Should raise InvalidExtractionData with the job error prominently displayed
-    with pytest.raises(InvalidExtractionData) as exc_info:
-        ExtractedData.from_extraction_result(
-            extract_run, Person, metadata={"test": "metadata"}
-        )
-
-    # Verify the exception message prominently shows the job error
-    exception = exc_info.value
-    assert exception.extraction_error == job_error_message
-    assert f"Extraction error: {job_error_message}" == str(exception)
-
-    # Verify the invalid_item contains both errors in metadata
-    invalid_data = exception.invalid_item
-    assert invalid_data.metadata.get("job_error") == job_error_message
-    assert "extraction_error" in invalid_data.metadata  # Validation error still present
-    assert "test" in invalid_data.metadata  # Original metadata preserved
-
 
 class Dimensions(BaseModel):
     length: Optional[str] = Field(
@@ -707,69 +663,3 @@ def test_field_conflict_in_schema():
     assert isinstance(
         extracted["majority_opinion"]["reasoning"], ExtractedFieldMetadata
     )
-
-
-def test_parse_extracted_field_metadata_with_bounding_boxes():
-    """Test parse_extracted_field_metadata with bounding boxes and page dimensions."""
-    raw_metadata = {
-        "document_type": {
-            "citation": [
-                {
-                    "page": 1,
-                    "matching_text": "FACTURE ORIGINALE",
-                    "bounding_boxes": [{"x": 77.28, "y": 615.12, "w": 70.6, "h": 7.2}],
-                    "page_dimensions": {"width": 222.24, "height": 736.56},
-                }
-            ],
-            "parsing_confidence": 1.0,
-            "extraction_confidence": 0.7252506422636493,
-            "confidence": 0.7252506422636493,
-        },
-        "summary": {
-            "citation": [
-                {
-                    "page": 1,
-                    "matching_text": "FACTURE ORIGINALE",
-                    "bounding_boxes": [{"x": 77.28, "y": 615.12, "w": 70.6, "h": 7.2}],
-                    "page_dimensions": {"width": 222.24, "height": 736.56},
-                },
-                {
-                    "page": 1,
-                    "matching_text": "Café filtre assiette — $1.90",
-                    "bounding_boxes": [
-                        {"x": 10.56, "y": 172.83, "w": 171.85, "h": 497.01}
-                    ],
-                    "page_dimensions": {"width": 222.24, "height": 736.56},
-                },
-            ],
-            "parsing_confidence": 1.0,
-            "extraction_confidence": 0.5700013128334419,
-            "confidence": 0.5700013128334419,
-        },
-    }
-
-    result = parse_extracted_field_metadata(raw_metadata)
-
-    # Verify document_type citation with bounding boxes
-    assert isinstance(result["document_type"], ExtractedFieldMetadata)
-    assert result["document_type"].parsing_confidence == 1.0
-    assert result["document_type"].extraction_confidence == 0.7252506422636493
-    assert result["document_type"].confidence == 0.7252506422636493
-    assert len(result["document_type"].citation) == 1
-
-    citation = result["document_type"].citation[0]
-    assert citation.page == 1
-    assert citation.matching_text == "FACTURE ORIGINALE"
-    assert len(citation.bounding_boxes) == 1
-    assert citation.bounding_boxes[0] == BoundingBox(x=77.28, y=615.12, w=70.6, h=7.2)
-    assert citation.page_dimensions == PageDimensions(width=222.24, height=736.56)
-
-    # Verify summary citation with multiple bounding boxes
-    assert isinstance(result["summary"], ExtractedFieldMetadata)
-    assert len(result["summary"].citation) == 2
-    assert result["summary"].citation[0].bounding_boxes[0].x == 77.28
-    assert result["summary"].citation[1].bounding_boxes[0].x == 10.56
-
-    # Verify round-trip serialization
-    result2 = parse_extracted_field_metadata(result)
-    assert result2 == result

py/unit_tests/index/test_unit_index.py

@@ -34,10 +34,9 @@ TEST_PIPELINE = Pipeline(
 def mock_client() -> MagicMock:
     """Mock client with sensible defaults."""
     client = MagicMock()
-    default_project = Project(
+    client.projects.upsert_project.return_value = Project(
         id="default-proj", name=DEFAULT_PROJECT_NAME, organization_id="default-org"
     )
-    client.projects.list_projects.return_value = [default_project]
     client.pipelines.upsert_pipeline.return_value = Pipeline(
         id="default-pipe",
         name="default",
@@ -101,8 +100,8 @@ def test_from_documents_uses_provided_project_id(mock_client: MagicMock) -> None
             project_id=provided_project_id,
         )
 
-    # Assert - project list not called (project_id provided); pipeline uses provided project_id
-    mock_client.projects.list_projects.assert_not_called()
+    # Assert - project upsert not called; pipeline uses provided project_id
+    mock_client.projects.upsert_project.assert_not_called()
     assert mock_client.pipelines.upsert_pipeline.call_count == 1
     assert (
         mock_client.pipelines.upsert_pipeline.call_args.kwargs["project_id"]
@@ -111,29 +110,29 @@ def test_from_documents_uses_provided_project_id(mock_client: MagicMock) -> None
     assert index.project.id == provided_project_id
 
 
-def test_from_documents_lists_project_when_project_id_missing(
+def test_from_documents_upserts_project_when_project_id_missing(
     mock_client: MagicMock,
 ) -> None:
     organization_id = "org-xyz"
     index_name = "my_new_index"
 
-    # Project is found by name when project_id is not provided
-    found_project = Project(
+    # Project is created when project_id is not provided
+    upserted_project = Project(
         id="proj-999", name=DEFAULT_PROJECT_NAME, organization_id=organization_id
     )
-    mock_client.projects.list_projects.return_value = [found_project]
+    mock_client.projects.upsert_project.return_value = upserted_project
 
     test_pipeline = Pipeline(
         id="pipe-xyz",
         name=index_name,
-        project_id=found_project.id,
+        project_id=upserted_project.id,
         embedding_config=EMBEDDING_CONFIG,
     )
 
     with patch.object(
         base,
         "resolve_project_and_pipeline",
-        return_value=(found_project, test_pipeline),
+        return_value=(upserted_project, test_pipeline),
     ):
         docs = [Document(text="world")]
         index = LlamaCloudIndex.from_documents(
@@ -142,15 +141,15 @@ def test_from_documents_lists_project_when_project_id_missing(
             organization_id=organization_id,
         )
 
-    # Assert - project was listed with org id and default project name
-    mock_client.projects.list_projects.assert_called_once()
-    kwargs = mock_client.projects.list_projects.call_args.kwargs
+    # Assert - project was upserted with org id and default project name
+    mock_client.projects.upsert_project.assert_called_once()
+    kwargs = mock_client.projects.upsert_project.call_args.kwargs
     assert kwargs["organization_id"] == organization_id
-    assert kwargs["project_name"] == DEFAULT_PROJECT_NAME
+    assert kwargs["request"].name == DEFAULT_PROJECT_NAME
 
-    # Pipeline created under the found project id
+    # Pipeline created under the upserted project id
     assert (
         mock_client.pipelines.upsert_pipeline.call_args.kwargs["project_id"]
-        == found_project.id
+        == upserted_project.id
     )
-    assert index.project.id == found_project.id
+    assert index.project.id == upserted_project.id

py/uv.lock

@@ -1,5 +1,5 @@
 version = 1
-revision = 3
+revision = 2
 requires-python = ">=3.9, <4.0"
 resolution-markers = [
     "python_full_version >= '3.14'",
@@ -1595,21 +1595,21 @@ wheels = [
 
 [[package]]
 name = "llama-cloud"
-version = "0.1.46"
+version = "0.1.45"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "certifi" },
     { name = "httpx" },
     { name = "pydantic" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/40/f3/f4d6520f8d546e6c5a02f6ebeed5c09774a074b8d2c24ad559ace97a56a6/llama_cloud-0.1.46.tar.gz", hash = "sha256:e86f8791c053590d70cc59e0fc13ce72f9b681a8e658bc61df86d0285288d8ee", size = 127752, upload-time = "2026-01-21T18:40:57.103Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e0/b7/3a2a209f1c3fa516de172cb13e03f5a897adea5523f2ee0f544d035e3704/llama_cloud-0.1.45.tar.gz", hash = "sha256:140244008cc5710e31ae97c6043973a3a9969a51b0f38155fa33a8434078e8aa", size = 140968, upload-time = "2025-12-03T02:22:49.484Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c4/3a/6caaea28c8c804add33c91d356ed7d5a5412d6c9598e1450af95a15e0bcd/llama_cloud-0.1.46-py3-none-any.whl", hash = "sha256:6c6546c09c04a038c86d84d42f00eae8fd3bff49991ad3aab844bd866ecdf352", size = 361989, upload-time = "2026-01-21T18:40:54.863Z" },
+    { url = "https://files.pythonhosted.org/packages/62/1d/466b0df69b81ce9410ad6ec7229a1e6601ff69640f02f246e06cfcc7428c/llama_cloud-0.1.45-py3-none-any.whl", hash = "sha256:500299a6d3f25f97bcf6755d6338523023564fa8f376955c2cf299bbc9561cc2", size = 397184, upload-time = "2025-12-03T02:22:48.335Z" },
 ]
 
 [[package]]
 name = "llama-cloud-services"
-version = "0.6.90"
+version = "0.6.85"
 source = { editable = "." }
 dependencies = [
     { name = "click", version = "8.1.8", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
@@ -1649,7 +1649,7 @@ dev = [
 requires-dist = [
     { name = "click", specifier = ">=8.1.7,<9" },
     { name = "eval-type-backport", marker = "python_full_version < '3.10'", specifier = ">=0.2.0,<0.3" },
-    { name = "llama-cloud", specifier = "==0.1.46" },
+    { name = "llama-cloud", specifier = "==0.1.45" },
     { name = "llama-index-core", specifier = ">=0.12.0" },
     { name = "packaging", specifier = ">=23.0" },
     { name = "platformdirs", specifier = ">=4.3.7,<5" },

ts/llama_cloud_services/CHANGELOG.md

@@ -1,38 +1,5 @@
 # llama-cloud-services
 
-## 0.5.3
-
-### Patch Changes
-
-- d7864af: bugfixes in retry logic for LlamaExtract and LlamaClassify
-
-## 0.5.2
-
-### Patch Changes
-
-- 997bcc8: Add types for bounding boxes
-
-## 0.5.1
-
-### Patch Changes
-
-- d5b18a0: Fix publishing
-
-## 0.5.0
-
-### Minor Changes
-
-- 576c3d9: feat: support zod v4 & v3
-
-  Adds support for zod v4 while maintaining backward compatibility with v3.
-  - Updated zod peer dependency to accept both v3 and v4: `^3.25.76 || ^4.0.0`
-  - Migrated all import statements to use `zod/v4` import path for compatibility
-
-### Patch Changes
-
-- c8321d2: Improve parse results polling
-- 576c3d9: Support zod v3 an v4
-
 ## 0.4.3
 
 ### Patch Changes

ts/llama_cloud_services/package.json

@@ -1,12 +1,12 @@
 {
   "name": "llama-cloud-services",
-  "version": "0.5.3",
+  "version": "0.4.3",
   "type": "module",
   "license": "MIT",
   "scripts": {
     "get-openapi": "node ./scripts/get-openapi.js",
     "generate": "./node_modules/.bin/openapi-ts",
-    "build": "bunchee",
+    "build": "pnpm run generate && bunchee",
     "dev": "bunchee --watch",
     "lint": "eslint src/ --ignore-pattern client/*.ts --no-warn-ignored",
     "format": "prettier --write ./src/ tests/",
@@ -116,9 +116,9 @@
     "@eslint/js": "^9.32.0",
     "@hey-api/client-fetch": "^0.10.1",
     "@hey-api/openapi-ts": "^0.67.5",
-    "@llamaindex/core": "^0.6.22",
+    "@llamaindex/core": "^0.6.19",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/workflow-core": "^1.3.3",
+    "@llamaindex/workflow-core": "^0.4.1",
     "@types/node": "^20.19.9",
     "@typescript-eslint/eslint-plugin": "^8.38.0",
     "@typescript-eslint/parser": "^8.38.0",
@@ -131,19 +131,18 @@
     "turbo": "^2.5.5",
     "typescript": "^5.8.3",
     "typescript-eslint": "^8.38.0",
-    "vitest": "^2.0.0",
-    "zod": "^4.1.13"
+    "vitest": "^2.0.0"
   },
   "peerDependencies": {
     "@llamaindex/core": "^0.6.19",
     "@llamaindex/env": "^0.1.30",
-    "@llamaindex/workflow-core": "^1.3.3",
-    "zod": "^3.25.0 || ^4.0.0"
+    "@llamaindex/workflow-core": "^0.4.1"
   },
   "dependencies": {
     "ajv": "^8.17.1",
     "file-type": "^21.0.0",
-    "p-retry": "^6.2.1"
+    "p-retry": "^6.2.1",
+    "zod": "^3.25.76"
   },
   "packageManager": "pnpm@10.8.1"
 }

ts/llama_cloud_services/src/beta/agent/index.ts

@@ -2,14 +2,11 @@ export { AgentClient, createAgentDataClient } from "./client";
 
 export type {
   AggregateAgentDataOptions,
-  BoundingBox,
   ComparisonOperator,
   ExtractedData,
   ExtractedFieldMetadata,
   ExtractedFieldMetadataDict,
-  FieldCitation,
   FilterOperation,
-  PageDimensions,
   SearchAgentDataOptions,
   StatusType,
   TypedAgentData,

ts/llama_cloud_services/src/beta/agent/types.ts

@@ -28,44 +28,6 @@ export type ComparisonOperator =
  */
 export type FilterOperation = RawFilterOperation;
 
-/**
- * Bounding box coordinates for a citation location on a page
- */
-export interface BoundingBox {
-  /** X coordinate of the bounding box origin */
-  x: number;
-  /** Y coordinate of the bounding box origin */
-  y: number;
-  /** Width of the bounding box */
-  w: number;
-  /** Height of the bounding box */
-  h: number;
-}
-
-/**
- * Dimensions of a page in the source document
- */
-export interface PageDimensions {
-  /** Width of the page */
-  width: number;
-  /** Height of the page */
-  height: number;
-}
-
-/**
- * Citation information for an extracted field
- */
-export interface FieldCitation {
-  /** The page number that the field occurred on */
-  page?: number;
-  /** The original text this field's value was derived from */
-  matching_text?: string;
-  /** Bounding boxes indicating where the citation appears on the page */
-  bounding_boxes?: BoundingBox[];
-  /** Dimensions of the page containing the citation */
-  page_dimensions?: PageDimensions;
-}
-
 /**
  * Metadata for an extracted field, including confidence and citation information
  */
@@ -76,11 +38,16 @@ export interface ExtractedFieldMetadata {
   confidence?: number;
   /** The confidence score for the field based on the extracted text only */
   extraction_confidence?: number;
-  /** The confidence score for the field based on the parsing/OCR quality */
-  parsing_confidence?: number;
   citation?: FieldCitation[];
 }
 
+export interface FieldCitation {
+  /** The page number that the field occurred on */
+  page?: number;
+  /** The original text this field's value was derived from */
+  matching_text?: string;
+}
+
 /**
  * Dictionary mapping field names to their metadata
  * Values can be ExtractedFieldMetadata objects, nested dictionaries, or arrays

ts/llama_cloud_services/src/classify.ts

@@ -108,19 +108,20 @@ async function pollForJobCompletion({
     }
     const response =
       await getClassifyJobApiV1ClassifierJobsClassifyJobIdGet(jobOptions);
+    if (!response.response.ok) {
+      numIterations++;
+    }
     if (typeof response.data != "undefined") {
       status = response.data.status as StatusEnum;
       if (status == StatusEnum.CANCELLED || status == StatusEnum.ERROR) {
-        throw new Error("There was an error extracting data from your file.");
-      } else if (
-        status == StatusEnum.SUCCESS ||
-        status == StatusEnum.PARTIAL_SUCCESS
-      ) {
+        throw new Error("There was an error during the classification job.");
+      } else if (status == StatusEnum.SUCCESS) {
         return true;
+      } else {
+        numIterations++;
+        await sleep(interval * 1000);
       }
     }
-    numIterations++;
-    await sleep(interval * 1000);
   }
 }
 
@@ -168,7 +169,7 @@ async function getJobResult({
       retries++;
       await sleep(retryInterval * 1000);
     }
-    if (response.response.ok && typeof response.data != "undefined") {
+    if (typeof response.data != "undefined") {
       return response.data as ClassifyJobResults;
     } else {
       throw new Error(

ts/llama_cloud_services/src/client/zod.gen.ts

@@ -1,6 +1,6 @@
 // This file is auto-generated by @hey-api/openapi-ts
 
-import { z } from "zod/v4";
+import { z } from "zod";
 
 export const zNoneSegmentationConfig = z.object({
   mode: z.literal("none").optional().default("none"),
@@ -770,7 +770,7 @@ export const zMetadataFilter = z.object({
 
 export const zFilterCondition: z.ZodTypeAny = z.enum(["and", "or", "not"]);
 
-export const zMetadataFilters: z.ZodObject<z.ZodRawShape> = z.object({
+export const zMetadataFilters: z.AnyZodObject = z.object({
   filters: z.array(z.unknown()),
   condition: z.union([zFilterCondition, z.null()]).optional(),
 });
@@ -782,7 +782,7 @@ export const zRetrievalMode: z.ZodTypeAny = z.enum([
   "auto_routed",
 ]);
 
-export const zPresetRetrievalParams: z.ZodObject<z.ZodRawShape> = z.object({
+export const zPresetRetrievalParams: z.AnyZodObject = z.object({
   dense_similarity_top_k: z
     .union([z.number().int().gte(1).lte(100), z.null()])
     .optional(),
@@ -825,7 +825,7 @@ export const zSupportedLlmModelNames: z.ZodTypeAny = z.enum([
   "VERTEX_AI_CLAUDE_3_5_SONNET_V2",
 ]);
 
-export const zLlmParameters: z.ZodObject<z.ZodRawShape> = z.object({
+export const zLlmParameters: z.AnyZodObject = z.object({
   model_name: zSupportedLlmModelNames.optional(),
   system_prompt: z.union([z.string().max(3000), z.null()]).optional(),
   temperature: z.union([z.number(), z.null()]).optional(),
@@ -834,7 +834,7 @@ export const zLlmParameters: z.ZodObject<z.ZodRawShape> = z.object({
   class_name: z.string().optional().default("base_component"),
 });
 
-export const zChatData: z.ZodObject<z.ZodRawShape> = z.object({
+export const zChatData: z.AnyZodObject = z.object({
   retrieval_parameters: zPresetRetrievalParams.optional(),
   llm_parameters: z.union([zLlmParameters, z.null()]).optional(),
   class_name: z.string().optional().default("base_component"),
@@ -2141,7 +2141,7 @@ export const zTextItem = z.object({
   value: z.string(),
 });
 
-export const zListItem: z.ZodObject<z.ZodRawShape> = z.object({
+export const zListItem: z.AnyZodObject = z.object({
   type: z.literal("list").optional().default("list"),
   bBox: z.union([z.unknown(), z.null()]).optional(),
   items: z.array(z.unknown()),

ts/llama_cloud_services/src/events.ts

@@ -1,6 +1,6 @@
 import { workflowEvent } from "@llamaindex/workflow-core";
 import { zodEvent } from "@llamaindex/workflow-core/util/zod";
-import { z } from "zod/v4";
+import { z } from "zod";
 import { parseFormSchema } from "./schema";
 
 export const uploadEvent = zodEvent(

ts/llama_cloud_services/src/extract.ts

@@ -296,16 +296,20 @@ async function pollForJobCompletion(
       return false;
     }
     const response = await getJobApiV1ExtractionJobsJobIdGet(jobOptions);
+    if (!response.response.ok) {
+      numIterations++;
+    }
     if (typeof response.data != "undefined") {
       status = response.data.status as StatusEnum;
       if (status == StatusEnum.CANCELLED || status == StatusEnum.ERROR) {
         throw new Error("There was an error extracting data from your file.");
       } else if (status == StatusEnum.SUCCESS) {
         return true;
+      } else {
+        numIterations++;
+        await sleep(interval * 1000);
       }
     }
-    numIterations++;
-    await sleep(interval * 1000);
   }
 }
 
@@ -346,7 +350,7 @@ async function getJobResult(
       retries++;
       await sleep(retryInterval * 1000);
     }
-    if (response.response.ok && typeof response.data != "undefined") {
+    if (typeof response.data != "undefined") {
       return {
         data: response.data.data,
         extractionMetadata: response.data.extraction_metadata,

ts/llama_cloud_services/src/query-tool.ts

@@ -2,7 +2,7 @@ import type { JSONValue } from "@llamaindex/core/global";
 import type { ToolMetadata } from "@llamaindex/core/llms";
 import type { BaseQueryEngine } from "@llamaindex/core/query-engine";
 import { tool } from "@llamaindex/core/tools";
-import { z } from "zod/v4";
+import { z } from "zod";
 
 const DEFAULT_NAME = "llama_cloud_index_tool";
 const DEFAULT_DESCRIPTION =
@@ -21,7 +21,9 @@ export function createQueryEngineTool(
     name: metadata?.name ?? DEFAULT_NAME,
     description: metadata?.description ?? DEFAULT_DESCRIPTION,
     parameters: z.object({
-      query: z.string().describe("The query to search for"),
+      query: z.string({
+        description: "The query to search for",
+      }),
     }),
     execute: async ({ query }) => {
       const response = await queryEngine.query({ query });

ts/llama_cloud_services/src/reader.ts

@@ -1,10 +1,9 @@
 /* eslint-disable @typescript-eslint/no-explicit-any */
 import { type Client, createClient, createConfig } from "@hey-api/client-fetch";
-import { type FailedAttemptError } from "p-retry";
 import { Document, FileReader } from "@llamaindex/core/schema";
 import { fs, getEnv, path } from "@llamaindex/env";
 import {
-  type BodyUploadFileApiV1ParsingUploadPost,
+  type BodyUploadFileApiParsingUploadPost,
   type FailPageMode,
   type ParserLanguages,
   type ParsingMode,
@@ -33,33 +32,6 @@ type WriteStream = {
 // eslint-disable-next-line no-var
 var process: any;
 
-function handleFailedAttempt(
-  error: FailedAttemptError,
-  jobId: string,
-  verbose: boolean,
-) {
-  // Retry only on 5XX or socket errors.
-  const status = (error.cause as any)?.response?.status;
-  if (
-    !(
-      (status && status >= 500 && status < 600) ||
-      ((error.cause as any)?.code &&
-        ((error.cause as any).code === "ECONNRESET" ||
-          (error.cause as any).code === "ETIMEDOUT" ||
-          (error.cause as any).code === "ECONNREFUSED")) ||
-      (status && status === 404)
-    )
-  ) {
-    throw error;
-  }
-
-  if (verbose) {
-    console.warn(
-      `Attempting to get job ${jobId} result (attempt ${error.attemptNumber}) failed. Retrying...`,
-    );
-  }
-}
-
 /**
  * Represents a reader for parsing files using the LlamaParse API.
  * See https://github.com/run-llama/llama_parse
@@ -216,16 +188,6 @@ export class LlamaParseReader extends FileReader {
   extract_printed_page_number?: boolean | undefined;
   tier?: string | undefined;
   version?: string | undefined;
-  layout_aware?: boolean | undefined;
-  line_level_bounding_box?: boolean | undefined;
-  specialized_image_parsing?: boolean | undefined;
-  aggressive_table_extraction?: boolean | undefined;
-  preserve_very_small_text?: boolean | undefined;
-  spreadsheet_force_formula_computation?: boolean | undefined;
-  inline_images_in_markdown?: boolean | undefined;
-  keep_page_separator_when_merging_tables?: boolean | undefined;
-  remove_hidden_text?: boolean | undefined;
-  presentation_out_of_bounds_content?: boolean | undefined;
 
   constructor(
     params: Partial<Omit<LlamaParseReader, "language" | "apiKey">> & {
@@ -425,25 +387,11 @@ export class LlamaParseReader extends FileReader {
       extract_printed_page_number: this.extract_printed_page_number,
       tier: this.tier,
       version: this.version,
-      layout_aware: this.layout_aware,
-      line_level_bounding_box: this.line_level_bounding_box,
-      specialized_image_parsing: this.specialized_image_parsing,
-      aggressive_table_extraction: this.aggressive_table_extraction,
-      preserve_very_small_text: this.preserve_very_small_text,
-      spreadsheet_force_formula_computation:
-        this.spreadsheet_force_formula_computation,
-      inline_images_in_markdown: this.inline_images_in_markdown,
-      webhook_configurations: undefined,
-      keep_page_separator_when_merging_tables:
-        this.keep_page_separator_when_merging_tables,
-      remove_hidden_text: this.remove_hidden_text,
-      presentation_out_of_bounds_content:
-        this.presentation_out_of_bounds_content,
     } satisfies {
-      [Key in keyof BodyUploadFileApiV1ParsingUploadPost]-?:
-        | BodyUploadFileApiV1ParsingUploadPost[Key]
+      [Key in keyof BodyUploadFileApiParsingUploadPost]-?:
+        | BodyUploadFileApiParsingUploadPost[Key]
         | undefined;
-    } as unknown as BodyUploadFileApiV1ParsingUploadPost;
+    } as unknown as BodyUploadFileApiParsingUploadPost;
 
     const response = await uploadFileApiV1ParsingUploadPost({
       client: this.#client,
@@ -495,8 +443,26 @@ export class LlamaParseReader extends FileReader {
             }),
           {
             retries: this.maxErrorCount,
-            onFailedAttempt: (error) =>
-              handleFailedAttempt(error, jobId, this.verbose),
+            onFailedAttempt: (error) => {
+              // Retry only on 5XX or socket errors.
+              const status = (error.cause as any)?.response?.status;
+              if (
+                !(
+                  (status && status >= 500 && status < 600) ||
+                  ((error.cause as any)?.code &&
+                    ((error.cause as any).code === "ECONNRESET" ||
+                      (error.cause as any).code === "ETIMEDOUT" ||
+                      (error.cause as any).code === "ECONNREFUSED"))
+                )
+              ) {
+                throw error;
+              }
+              if (this.verbose) {
+                console.warn(
+                  `Attempting to get job ${jobId} result (attempt ${error.attemptNumber}) failed. Retrying...`,
+                );
+              }
+            },
           },
         );
       } catch (e: any) {
@@ -509,69 +475,49 @@ export class LlamaParseReader extends FileReader {
       const status = (data as Record<string, unknown>)["status"];
 
       if (status === "SUCCESS") {
+        let resultData;
         switch (resultType) {
           case "json": {
-            const resultData = await pRetry(
-              () =>
-                getJobJsonResultApiV1ParsingJobJobIdResultJsonGet({
-                  client: this.#client,
-                  throwOnError: true,
-                  path: { job_id: jobId },
-                  query: {
-                    organization_id: this.organization_id ?? null,
-                  },
-                  signal: AbortSignal.timeout(this.maxTimeout * 1000),
-                }),
-              {
-                retries: this.maxErrorCount,
-                onFailedAttempt: (error) =>
-                  handleFailedAttempt(error, jobId, this.verbose),
-              },
-            );
-            return resultData.data;
+            resultData =
+              await getJobJsonResultApiV1ParsingJobJobIdResultJsonGet({
+                client: this.#client,
+                throwOnError: true,
+                path: { job_id: jobId },
+                query: {
+                  organization_id: this.organization_id ?? null,
+                },
+                signal: AbortSignal.timeout(this.maxTimeout * 1000),
+              });
+            break;
           }
           case "markdown": {
-            const resultData = await pRetry(
-              () =>
-                getJobResultApiV1ParsingJobJobIdResultMarkdownGet({
-                  client: this.#client,
-                  throwOnError: true,
-                  path: { job_id: jobId },
-                  query: {
-                    organization_id: this.organization_id ?? null,
-                  },
-                  signal: AbortSignal.timeout(this.maxTimeout * 1000),
-                }),
-              {
-                retries: this.maxErrorCount,
-                onFailedAttempt: (error) =>
-                  handleFailedAttempt(error, jobId, this.verbose),
-              },
-            );
-            return resultData.data;
+            resultData =
+              await getJobResultApiV1ParsingJobJobIdResultMarkdownGet({
+                client: this.#client,
+                throwOnError: true,
+                path: { job_id: jobId },
+                query: {
+                  organization_id: this.organization_id ?? null,
+                },
+                signal: AbortSignal.timeout(this.maxTimeout * 1000),
+              });
+            break;
           }
           case "text": {
-            const resultData = await pRetry(
-              () =>
-                getJobTextResultApiV1ParsingJobJobIdResultTextGet({
-                  client: this.#client,
-                  throwOnError: true,
-                  path: { job_id: jobId },
-                  query: {
-                    organization_id: this.organization_id ?? null,
-                  },
-                  signal: AbortSignal.timeout(this.maxTimeout * 1000),
-                }),
-              {
-                retries: this.maxErrorCount,
-                onFailedAttempt: (error) =>
-                  handleFailedAttempt(error, jobId, this.verbose),
-              },
-            );
-
-            return resultData.data;
+            resultData =
+              await getJobTextResultApiV1ParsingJobJobIdResultTextGet({
+                client: this.#client,
+                throwOnError: true,
+                path: { job_id: jobId },
+                query: {
+                  organization_id: this.organization_id ?? null,
+                },
+                signal: AbortSignal.timeout(this.maxTimeout * 1000),
+              });
+            break;
           }
         }
+        return resultData.data;
       } else if (status === "PENDING") {
         if (this.verbose && tries % 10 === 0) {
           this.stdout?.write(".");

ts/llama_cloud_services/src/schema.ts

@@ -1,6 +1,6 @@
 import { FailPageMode, ParserLanguages, ParsingMode } from "./client";
 
-import { z } from "zod/v4";
+import { z } from "zod";
 
 type Language = ParserLanguages;
 const VALUES: [Language, ...Language[]] = [
@@ -52,10 +52,9 @@ export const parseFormSchema = z.object({
   html_remove_navigation_elements: z.boolean().optional(),
   http_proxy: z
     .string()
-    .url({
-      error:
-        'Set a valid URL for the HTTP proxy, e.g., "http://proxy.example.com:8080"',
-    })
+    .url(
+      'Set a valid URL for the HTTP proxy, e.g., "http://proxy.example.com:8080"',
+    )
     .refine(
       (url) => {
         try {
@@ -68,7 +67,7 @@ export const parseFormSchema = z.object({
         }
       },
       {
-        error: "Invalid HTTP proxy URL",
+        message: "Invalid HTTP proxy URL",
       },
     )
     .optional(),
@@ -101,7 +100,7 @@ export const parseFormSchema = z.object({
   vendor_multimodal_model_name: z.string().optional(),
   model: z.string().optional(),
   webhook_url: z.string().url().optional(),
-  parse_mode: z.enum(ParsingMode).nullable().optional(),
+  parse_mode: z.nativeEnum(ParsingMode).nullable().optional(),
   system_prompt: z.string().optional(),
   system_prompt_append: z.string().optional(),
   user_prompt: z.string().optional(),
@@ -130,7 +129,7 @@ export const parseFormSchema = z.object({
   compact_markdown_table: z.boolean().optional(),
   markdown_table_multiline_header_separator: z.string().optional(),
   page_error_tolerance: z.number().min(0).max(1).optional(),
-  replace_failed_page_mode: z.enum(FailPageMode).nullable().optional(),
+  replace_failed_page_mode: z.nativeEnum(FailPageMode).nullable().optional(),
   replace_failed_page_with_error_message_prefix: z.string().optional(),
   replace_failed_page_with_error_message_suffix: z.string().optional(),
 });