Compare commits

...

5 Commits

Author SHA1 Message Date
Neeraj Pradhan 483110704b revert changes to parse 2026-01-21 12:00:21 -08:00
Neeraj Pradhan 484c139ce1 add exp backoff on agent creation 2026-01-21 11:42:34 -08:00
Neeraj Pradhan 2b5d9e8fce fix types; retry 2026-01-21 11:27:56 -08:00
Neeraj Pradhan 2d4c56cb04 Fix files and tests 2026-01-21 11:08:16 -08:00
Neeraj Pradhan af5eb1ffd3 Bump up minor version for python packages 2026-01-21 10:53:41 -08:00
10 changed files with 101 additions and 50 deletions
+6
View File
@@ -0,0 +1,6 @@
---
"llama-cloud-services-py": minor
"llama_parse": minor
---
Incorporate updates from llama-cloud
+4 -6
View File
@@ -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, FileCreate
from llama_cloud.types import File
from typing import Optional
from llama_cloud_services.utils import SourceText, FileInput
@@ -73,11 +73,9 @@ class FileClient:
presigned_url = await self.client.files.generate_presigned_url(
project_id=self.project_id,
organization_id=self.organization_id,
request=FileCreate(
name=name,
external_file_id=external_file_id,
file_size=file_size,
),
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(
+19 -10
View File
@@ -21,7 +21,6 @@ from llama_cloud import (
PipelineCreateTransformConfig,
PipelineFileCreateCustomMetadataValue,
PipelineType,
ProjectCreate,
ManagedIngestionStatus,
CloudDocumentCreate,
CloudDocument,
@@ -507,14 +506,19 @@ class LlamaCloudIndex(BaseManagedIndex):
client = get_client(api_key, base_url, app_url, timeout)
if project_id is None:
# create project if it doesn't exist
project = client.projects.upsert_project(
# get project by name
projects = client.projects.list_projects(
organization_id=organization_id,
request=ProjectCreate(name=project_name),
project_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"Created project {project_id} with name {project_name}")
print(f"Found project {project_id} with name {project_name}")
# create pipeline
pipeline_create = PipelineCreate(
@@ -563,15 +567,20 @@ 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)
# create project if it doesn't exist
project = await aclient.projects.upsert_project(
organization_id=organization_id, request=ProjectCreate(name=project_name)
# get project by name
projects = await aclient.projects.list_projects(
organization_id=organization_id, project_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 create/get project {project_name}")
raise ValueError(f"Failed to get project {project_name}")
if verbose:
print(f"Created project {project.id} with name {project.name}")
print(f"Found project {project.id} with name {project.name}")
# create pipeline
pipeline_create = PipelineCreate(
+1 -1
View File
@@ -31,7 +31,7 @@ readme = "README.md"
license = "MIT"
dependencies = [
"llama-index-core>=0.12.0",
"llama-cloud==0.1.45",
"llama-cloud==0.1.46",
"pydantic>=2.8,!=2.10",
"click>=8.1.7,<9",
"python-dotenv>=1.0.1,<2",
+34 -2
View File
@@ -1,11 +1,43 @@
import os
from typing import List
from llama_cloud_services.extract import LlamaExtract
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
# 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")
+2 -2
View File
@@ -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
from .conftest import register_agent_for_cleanup, create_agent_with_retry
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 = llama_extract.create_agent(name=name, data_schema=schema)
agent = create_agent_with_retry(llama_extract, name=name, data_schema=schema)
# Add agent to cleanup list via conftest helper
register_agent_for_cleanup(agent.id)
+5 -3
View File
@@ -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
from .conftest import register_agent_for_cleanup, create_agent_with_retry
load_test_dotenv()
@@ -117,8 +117,10 @@ 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
agent = extractor.create_agent(agent_name, schema, config=test_case.config)
# 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
)
# Register agent for cleanup at the end of the test session
register_agent_for_cleanup(agent.id)
+8 -5
View File
@@ -8,7 +8,6 @@ from llama_cloud import (
AutoTransformConfig,
PipelineCreate,
PipelineFileCreate,
ProjectCreate,
CompositeRetrievalMode,
LlamaParseParameters,
ReRankConfig,
@@ -60,11 +59,15 @@ def local_figures_file() -> str:
def _setup_index_with_file(
client: LlamaCloud, index_name: str, remote_file: Tuple[str, str]
) -> LlamaCloudIndex:
# 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
# get project by name
projects = client.projects.list_projects(
organization_id=organization_id, project_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]
# create pipeline
pipeline_create = PipelineCreate(
+17 -16
View File
@@ -34,9 +34,10 @@ TEST_PIPELINE = Pipeline(
def mock_client() -> MagicMock:
"""Mock client with sensible defaults."""
client = MagicMock()
client.projects.upsert_project.return_value = Project(
default_project = 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",
@@ -100,8 +101,8 @@ def test_from_documents_uses_provided_project_id(mock_client: MagicMock) -> None
project_id=provided_project_id,
)
# Assert - project upsert not called; pipeline uses provided project_id
mock_client.projects.upsert_project.assert_not_called()
# Assert - project list not called (project_id provided); pipeline uses provided project_id
mock_client.projects.list_projects.assert_not_called()
assert mock_client.pipelines.upsert_pipeline.call_count == 1
assert (
mock_client.pipelines.upsert_pipeline.call_args.kwargs["project_id"]
@@ -110,29 +111,29 @@ def test_from_documents_uses_provided_project_id(mock_client: MagicMock) -> None
assert index.project.id == provided_project_id
def test_from_documents_upserts_project_when_project_id_missing(
def test_from_documents_lists_project_when_project_id_missing(
mock_client: MagicMock,
) -> None:
organization_id = "org-xyz"
index_name = "my_new_index"
# Project is created when project_id is not provided
upserted_project = Project(
# Project is found by name when project_id is not provided
found_project = Project(
id="proj-999", name=DEFAULT_PROJECT_NAME, organization_id=organization_id
)
mock_client.projects.upsert_project.return_value = upserted_project
mock_client.projects.list_projects.return_value = [found_project]
test_pipeline = Pipeline(
id="pipe-xyz",
name=index_name,
project_id=upserted_project.id,
project_id=found_project.id,
embedding_config=EMBEDDING_CONFIG,
)
with patch.object(
base,
"resolve_project_and_pipeline",
return_value=(upserted_project, test_pipeline),
return_value=(found_project, test_pipeline),
):
docs = [Document(text="world")]
index = LlamaCloudIndex.from_documents(
@@ -141,15 +142,15 @@ def test_from_documents_upserts_project_when_project_id_missing(
organization_id=organization_id,
)
# 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 - 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 kwargs["organization_id"] == organization_id
assert kwargs["request"].name == DEFAULT_PROJECT_NAME
assert kwargs["project_name"] == DEFAULT_PROJECT_NAME
# Pipeline created under the upserted project id
# Pipeline created under the found project id
assert (
mock_client.pipelines.upsert_pipeline.call_args.kwargs["project_id"]
== upserted_project.id
== found_project.id
)
assert index.project.id == upserted_project.id
assert index.project.id == found_project.id
Generated
+5 -5
View File
@@ -1595,21 +1595,21 @@ wheels = [
[[package]]
name = "llama-cloud"
version = "0.1.45"
version = "0.1.46"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "certifi" },
{ name = "httpx" },
{ name = "pydantic" },
]
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" }
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" }
wheels = [
{ 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" },
{ 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" },
]
[[package]]
name = "llama-cloud-services"
version = "0.6.88"
version = "0.6.90"
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 = "==0.1.45" },
{ name = "llama-cloud", specifier = "==0.1.46" },
{ name = "llama-index-core", specifier = ">=0.12.0" },
{ name = "packaging", specifier = ">=23.0" },
{ name = "platformdirs", specifier = ">=4.3.7,<5" },