Skip to content

feat: Update S3Downloader to auto call run warm_up on first run instead raising error #2673

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

Merged
sjrl merged 2 commits into from
Jan 8, 2026
Merged

feat: Update S3Downloader to auto call run warm_up on first run instead raising error #2673

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
63c37bd
Auto call warm_up at runtime
sjrl Jan 8, 2026
4f67e55
Remove unnecessary calls
sjrl Jan 8, 2026
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
3 changes: 1 addition & 2 deletions ...tions/amazon_bedrock/src/haystack_integrations/components/downloaders/s3/s3_downloader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,8 +142,7 @@ def run(
"""

if self._storage is None:
msg = f"The component {self.__class__.__name__} was not warmed up. Call 'warm_up()' before calling run()."
raise RuntimeError(msg)
self.warm_up()

filtered_documents = self._filter_documents_by_extensions(documents) if self.file_extensions else documents

Expand Down
38 changes: 9 additions & 29 deletions integrations/amazon_bedrock/tests/test_s3_downloader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,7 +129,6 @@ def test_to_dict_with_parameters(self, tmp_path):

def test_run(self, tmp_path, mock_s3_storage, mock_boto3_session):
d = S3Downloader(file_root_path=str(tmp_path))
S3Downloader.warm_up(d)
d._storage = mock_s3_storage

docs = [
Expand All @@ -141,7 +140,6 @@ def test_run(self, tmp_path, mock_s3_storage, mock_boto3_session):

def test_run_with_extensions(self, tmp_path, mock_s3_storage, mock_boto3_session):
d = S3Downloader(file_root_path=str(tmp_path), file_extensions=[".txt"])
S3Downloader.warm_up(d)
d._storage = mock_s3_storage

docs = [
Expand All @@ -155,25 +153,19 @@ def test_run_with_extensions(self, tmp_path, mock_s3_storage, mock_boto3_session

def test_run_with_input_file_meta_key(self, tmp_path, mock_s3_storage, mock_boto3_session):
d = S3Downloader(file_root_path=str(tmp_path), file_name_meta_key="custom_file_key")
S3Downloader.warm_up(d)
d._storage = mock_s3_storage

docs = [
Document(meta={"file_id": str(uuid4()), "custom_file_key": "a.txt"}),
]
docs = [Document(meta={"file_id": str(uuid4()), "custom_file_key": "a.txt"})]

out = d.run(documents=docs)
assert len(out["documents"]) == 1
assert out["documents"][0].meta["custom_file_key"] == "a.txt"

def test_run_with_s3_key_generation_function(self, tmp_path, mock_s3_storage, mock_boto3_session):
d = S3Downloader(file_root_path=str(tmp_path), s3_key_generation_function=s3_key_generation_function)
S3Downloader.warm_up(d)
d._storage = mock_s3_storage

docs = [
Document(meta={"file_id": str(uuid4()), "file_name": "a.txt"}),
]
docs = [Document(meta={"file_id": str(uuid4()), "file_name": "a.txt"})]
out = d.run(documents=docs)
assert len(out["documents"]) == 1
assert out["documents"][0].meta["file_name"] == "a.txt"
Expand All @@ -189,7 +181,6 @@ def test_run_with_s3_key_generation_function_and_file_extensions(
s3_key_generation_function=s3_key_generation_function,
file_extensions=[".txt"],
)
S3Downloader.warm_up(d)
d._storage = mock_s3_storage

docs = [
Expand All @@ -210,8 +201,6 @@ def test_run_with_s3_key_generation_function_and_file_extensions(
def test_live_run(self, tmp_path, monkeypatch):
d = S3Downloader(file_root_path=str(tmp_path))
monkeypatch.setenv("S3_DOWNLOADER_PREFIX", "")
S3Downloader.warm_up(d)

docs = [
Document(meta={"file_id": str(uuid4()), "file_name": "text-sample.txt"}),
Document(meta={"file_id": str(uuid4()), "file_name": "document-sample.pdf"}),
Expand All @@ -229,9 +218,7 @@ def test_live_run(self, tmp_path, monkeypatch):
)
def test_live_run_with_no_documents(self, tmp_path):
d = S3Downloader(file_root_path=str(tmp_path))
S3Downloader.warm_up(d)
docs = []
out = d.run(documents=docs)
out = d.run(documents=[])
assert len(out["documents"]) == 0

@pytest.mark.integration
Expand All @@ -247,10 +234,8 @@ def test_live_run_with_no_documents(self, tmp_path):
def test_live_run_with_custom_meta_key(self, tmp_path, monkeypatch):
d = S3Downloader(file_root_path=str(tmp_path), file_name_meta_key="custom_name")
monkeypatch.setenv("S3_DOWNLOADER_PREFIX", "")
S3Downloader.warm_up(d)
docs = [
Document(meta={"custom_name": "text-sample.txt"}),
]
d.warm_up()
docs = [Document(meta={"custom_name": "text-sample.txt"})]
out = d.run(documents=docs)
assert len(out["documents"]) == 1
assert out["documents"][0].meta["custom_name"] == "text-sample.txt"
Expand All @@ -263,11 +248,8 @@ def test_live_run_with_custom_meta_key(self, tmp_path, monkeypatch):
def test_live_run_with_prefix(self, tmp_path, monkeypatch):
d = S3Downloader(file_root_path=str(tmp_path))
monkeypatch.setenv("S3_DOWNLOADER_PREFIX", "subfolder/")

S3Downloader.warm_up(d)
docs = [
Document(meta={"file_name": "employees.json"}),
]
d.warm_up()
docs = [Document(meta={"file_name": "employees.json"})]
out = d.run(documents=docs)
assert len(out["documents"]) == 1
assert out["documents"][0].meta["file_name"] == "employees.json"
Expand All @@ -286,10 +268,8 @@ def test_live_run_with_s3_key_generation_function_and_file_extensions(self, tmp_
file_name_meta_key="file_name",
s3_key_generation_function=s3_key_generation_function,
)
S3Downloader.warm_up(d)
docs = [
Document(meta={"file_name": "dog.jpg"}),
]
d.warm_up()
docs = [Document(meta={"file_name": "dog.jpg"})]
out = d.run(documents=docs)
assert len(out["documents"]) == 1
assert out["documents"][0].meta["file_name"] == "dog.jpg"