Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
121 changes: 0 additions & 121 deletions _test_unstructured_client/integration/test_integration.py
Original file line number Diff line number Diff line change
Expand Up @@ -221,127 +221,6 @@ async def call_api():
assert len(elements) > 0


@pytest.mark.parametrize("split_pdf", [True, False])
@pytest.mark.parametrize("vlm_model", ["gpt-4o"])
@pytest.mark.parametrize("vlm_model_provider", ["openai"])
@pytest.mark.parametrize(
"filename",
[
"layout-parser-paper-fast.pdf",
"fake-power-point.ppt",
"embedded-images-tables.jpg",
]
)
def test_partition_strategy_vlm_openai(split_pdf, vlm_model, vlm_model_provider, client, doc_path, filename):
with open(doc_path / filename, "rb") as f:
files = shared.Files(
content=f.read(),
file_name=filename,
)

req = operations.PartitionRequest(
partition_parameters=shared.PartitionParameters(
files=files,
strategy="vlm",
vlm_model=vlm_model,
vlm_model_provider=vlm_model_provider,
languages=["eng"],
split_pdf_page=split_pdf,
)
)

response = client.general.partition(
request=req
)
assert response.status_code == 200
assert len(response.elements) > 0
assert response.elements[0]["metadata"]["partitioner_type"] == "vlm_partition"


@pytest.mark.parametrize("split_pdf", [True, False])
@pytest.mark.parametrize("vlm_model",
[
"us.amazon.nova-pro-v1:0",
"us.amazon.nova-lite-v1:0",
"us.anthropic.claude-3-5-sonnet-20241022-v2:0",
"us.anthropic.claude-3-opus-20240229-v1:0",
"us.anthropic.claude-3-haiku-20240307-v1:0",
"us.anthropic.claude-3-sonnet-20240229-v1:0",
"us.meta.llama3-2-90b-instruct-v1:0",
"us.meta.llama3-2-11b-instruct-v1:0",
]
)
@pytest.mark.parametrize("vlm_model_provider", ["bedrock"])
@pytest.mark.parametrize(
"filename",
[
"layout-parser-paper-fast.pdf",
"fake-power-point.ppt",
"embedded-images-tables.jpg",
]
)
def test_partition_strategy_vlm_bedrock(split_pdf, vlm_model, vlm_model_provider, client, doc_path, filename):
with open(doc_path / filename, "rb") as f:
files = shared.Files(
content=f.read(),
file_name=filename,
)

req = operations.PartitionRequest(
partition_parameters=shared.PartitionParameters(
files=files,
strategy="vlm",
vlm_model=vlm_model,
vlm_model_provider=vlm_model_provider,
languages=["eng"],
split_pdf_page=split_pdf,
)
)

response = client.general.partition(
request=req
)
assert response.status_code == 200
assert len(response.elements) > 0
assert response.elements[0]["metadata"]["partitioner_type"] == "vlm_partition"

@pytest.mark.parametrize("split_pdf", [True, False])
@pytest.mark.parametrize("vlm_model", ["claude-3-5-sonnet-20241022",])
@pytest.mark.parametrize("vlm_model_provider", ["anthropic"])
@pytest.mark.parametrize(
"filename",
[
"layout-parser-paper-fast.pdf",
"fake-power-point.ppt",
"embedded-images-tables.jpg",
]
)
def test_partition_strategy_vlm_anthropic(split_pdf, vlm_model, vlm_model_provider, client, doc_path, filename):
with open(doc_path / filename, "rb") as f:
files = shared.Files(
content=f.read(),
file_name=filename,
)

req = operations.PartitionRequest(
partition_parameters=shared.PartitionParameters(
files=files,
strategy="vlm",
vlm_model=vlm_model,
vlm_model_provider=vlm_model_provider,
languages=["eng"],
split_pdf_page=split_pdf,
)
)

response = client.general.partition(
request=req
)
assert response.status_code == 200
assert len(response.elements) > 0
assert response.elements[0]["metadata"]["partitioner_type"] == "vlm_partition"


def test_returns_422_for_invalid_pdf(
caplog: pytest.LogCaptureFixture,
doc_path: Path,
Expand Down