Update pyproject.toml

back out of version bump

.changeset/ninety-goats-look.md

@@ -0,0 +1,6 @@
+---
+"llama_parse": patch
+"llama-cloud-services-py": patch
+---
+
+Remove extension filter

py/CHANGELOG.md

@@ -1,18 +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

py/llama_cloud_services/beta/agent_data/schema.py

@@ -475,49 +475,26 @@ 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_parse/CHANGELOG.md

@@ -1,22 +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

py/llama_parse/package.json

@@ -1,6 +1,6 @@
 {
   "name": "llama_parse",
-  "version": "0.6.91",
+  "version": "0.6.89",
   "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 = "0.6.89"
 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>=0.6.89"]
 
 [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": "0.6.89",
   "private": false,
   "license": "MIT",
   "scripts": {},

py/pyproject.toml

@@ -23,7 +23,7 @@ dev = [
 
 [project]
 name = "llama-cloud-services"
-version = "0.6.91"
+version = "0.6.89"
 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

@@ -423,7 +423,6 @@ def create_extract_run(
     },
     data_schema: Dict[str, Any] = {},
     file: File = create_file(),
-    error: Optional[str] = None,
 ) -> ExtractRun:
     return ExtractRun.parse_obj(
         {
@@ -440,7 +439,6 @@ def create_extract_run(
             "status": "SUCCESS",
             "project_id": str(uuid.uuid4()),
             "from_ui": False,
-            "error": error,
         }
     )
 
@@ -546,46 +544,6 @@ 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(

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

@@ -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 = "0.6.88"
 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" },