Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: Azure converter updates #7409

Merged
merged 13 commits into from
Apr 9, 2024
Merged

feat: Azure converter updates #7409

Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
2169f82
Initial commit
vblagoje Mar 21, 2024
e5f994d
Remove old mock tests
vblagoje Mar 22, 2024
f1d2d24
Fix current_last_page_number calculation
vblagoje Mar 22, 2024
f267837
Carry over unit tests from the other side
vblagoje Mar 22, 2024
6968cf3
Update pydocs, skip failing tests
vblagoje Mar 22, 2024
60f7466
Fix pylint and mypy
vblagoje Mar 22, 2024
674fa17
Minor adjustments
vblagoje Mar 22, 2024
8917838
Add release note
vblagoje Mar 22, 2024
a062fbd
Minor touch ups
vblagoje Mar 27, 2024
dc86fe2
Resolve Document unique id issue by using custom id calculation
vblagoje Apr 5, 2024
caf58c8
Better hashing, add unit tests
vblagoje Apr 5, 2024
ca9c8b9
Small fixes
vblagoje Apr 5, 2024
8347a14
Merge branch 'main' into azure_converter
vblagoje Apr 8, 2024
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
Prev Previous commit
Next Next commit
Remove old mock tests
  • Loading branch information
@vblagoje
vblagoje committed Mar 27, 2024
commit e5f994d6495b3f9120cab985b6ef98c104097e92
48 changes: 4 additions & 44 deletions test/components/converters/test_azure_ocr_doc_converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
import os
from unittest.mock import patch, Mock
from unittest.mock import Mock, patch

import pytest

Expand Down Expand Up @@ -28,48 +28,8 @@ def test_to_dict(self, mock_resolve_value):
},
}

@patch("haystack.utils.auth.EnvVarSecret.resolve_value")
def test_run(self, mock_resolve_value, test_files_path):
mock_resolve_value.return_value = "test_api_key"
with patch("haystack.components.converters.azure.DocumentAnalysisClient") as mock_azure_client:
mock_result = Mock(pages=[Mock(lines=[Mock(content="mocked line 1"), Mock(content="mocked line 2")])])
mock_result.to_dict.return_value = {
"api_version": "2023-02-28-preview",
"model_id": "prebuilt-read",
"content": "mocked line 1\nmocked line 2\n\f",
"pages": [{"lines": [{"content": "mocked line 1"}, {"content": "mocked line 2"}]}],
}
mock_azure_client.return_value.begin_analyze_document.return_value.result.return_value = mock_result

component = AzureOCRDocumentConverter(endpoint="test_endpoint")
output = component.run(sources=[test_files_path / "pdf" / "sample_pdf_1.pdf"])
document = output["documents"][0]
assert document.content == "mocked line 1\nmocked line 2\n\f"
assert "raw_azure_response" in output
assert output["raw_azure_response"][0] == {
"api_version": "2023-02-28-preview",
"model_id": "prebuilt-read",
"content": "mocked line 1\nmocked line 2\n\f",
"pages": [{"lines": [{"content": "mocked line 1"}, {"content": "mocked line 2"}]}],
}

@patch("haystack.utils.auth.EnvVarSecret.resolve_value")
def test_run_with_meta(self, mock_resolve_value, test_files_path):
mock_resolve_value.return_value = "test_api_key"
bytestream = ByteStream(data=b"test", meta={"author": "test_author", "language": "en"})
with patch("haystack.components.converters.azure.DocumentAnalysisClient"):
component = AzureOCRDocumentConverter(endpoint="test_endpoint")
output = component.run(
sources=[bytestream, test_files_path / "pdf" / "sample_pdf_1.pdf"], meta={"language": "it"}
)

# check that the metadata from the bytestream is merged with that from the meta parameter
assert output["documents"][0].meta["author"] == "test_author"
assert output["documents"][0].meta["language"] == "it"
assert output["documents"][1].meta["language"] == "it"

@pytest.mark.integration
@pytest.mark.skipif(not os.environ.get("CORE_AZURE_CS_ENDPOINT", None), reason="Azure credentials not available")
@pytest.mark.skipif(not os.environ.get("CORE_AZURE_CS_ENDPOINT", None), reason="Azure endpoint not available")
@pytest.mark.skipif(not os.environ.get("CORE_AZURE_CS_API_KEY", None), reason="Azure credentials not available")
def test_run_with_pdf_file(self, test_files_path):
component = AzureOCRDocumentConverter(
Expand All @@ -83,7 +43,7 @@ def test_run_with_pdf_file(self, test_files_path):
assert "Page 4 of Sample PDF" in documents[0].content

@pytest.mark.integration
@pytest.mark.skipif(not os.environ.get("CORE_AZURE_CS_ENDPOINT", None), reason="Azure credentials not available")
@pytest.mark.skipif(not os.environ.get("CORE_AZURE_CS_ENDPOINT", None), reason="Azure endpoint not available")
@pytest.mark.skipif(not os.environ.get("CORE_AZURE_CS_API_KEY", None), reason="Azure credentials not available")
def test_with_image_file(self, test_files_path):
component = AzureOCRDocumentConverter(
Expand All @@ -96,7 +56,7 @@ def test_with_image_file(self, test_files_path):
assert "by deepset" in documents[0].content

@pytest.mark.integration
@pytest.mark.skipif(not os.environ.get("CORE_AZURE_CS_ENDPOINT", None), reason="Azure credentials not available")
@pytest.mark.skipif(not os.environ.get("CORE_AZURE_CS_ENDPOINT", None), reason="Azure endpoint not available")
@pytest.mark.skipif(not os.environ.get("CORE_AZURE_CS_API_KEY", None), reason="Azure credentials not available")
def test_run_with_docx_file(self, test_files_path):
component = AzureOCRDocumentConverter(
Expand Down