mirror of
https://github.com/run-llama/template-workflow-document-parsing.git
synced 2026-07-01 21:14:00 -04:00
935ad538fb
- extract-reconcile-invoice: index_contract.py called files.get_file / files.read_file_content / files.upload_file (v1 SDK surface removed in v2), breaking every Upload Contract click. Switched to files.list + files.get + files.create. - Added test_index_contract_workflow and test_metadata_workflow to exercise the full v2 surface (files.list, files.get, pipelines.upsert, pipelines.documents.upsert, configurations.retrieve). - document-parsing and invoice-extraction had only placeholder tests — wired up llama-cloud-fake and added parametrized tests covering every tier/mode. invoice-extraction's test drives the HIL step. - Bumped requires-python to >=3.12 on both (fake floor).
22 lines
806 B
Python
22 lines
806 B
Python
import pytest
|
|
from document_parsing.workflow import workflow
|
|
from llama_cloud_fake import FakeLlamaCloudServer
|
|
|
|
|
|
@pytest.mark.parametrize("parsing_mode", ["cost_effective", "agentic", "agentic_plus"])
|
|
async def test_document_parsing_workflow(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
fake: FakeLlamaCloudServer,
|
|
parsing_mode: str,
|
|
) -> None:
|
|
"""Exercise parsing.parse against the fake for each tier."""
|
|
monkeypatch.setenv("LLAMA_CLOUD_API_KEY", "fake-api-key")
|
|
result = await workflow.run(
|
|
document_path="tests/files/test.pdf",
|
|
parsing_mode=parsing_mode,
|
|
)
|
|
# The SDK call succeeded and returned markdown_full as a string.
|
|
# The fake's payload may be empty; we only care the v2 `parsing.parse`
|
|
# surface is wired correctly.
|
|
assert isinstance(result, str)
|