feat(document-search): Allow to create DocumentSearch instances from config #117
GitHub Actions / JUnit Test Report
failed
Oct 7, 2024 in 0s
82 tests run, 76 passed, 4 skipped, 2 failed.
Annotations
Check failure on line 27 in packages/ragbits-document-search/tests/unit/test_document_search.py
github-actions / JUnit Test Report
test_document_search
ValueError: UNSTRUCTURED_API_KEY environment variable is not set
Raw output
async def test_document_search():
document_search = DocumentSearch(embedder=NoopEmbeddings(), vector_store=InMemoryVectorStore())
> await document_search.ingest_document(
DocumentMeta.create_text_document_from_literal("Name of Peppa's brother is George")
)
packages/ragbits-document-search/tests/unit/test_document_search.py:27:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
packages/ragbits-document-search/src/ragbits/document_search/_main.py:119: in ingest_document
elements = await document_processor.process(document_meta)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <ragbits.document_search.ingestion.providers.unstructured.UnstructuredProvider object at 0x7fd882ea94b0>
document_meta = DocumentMeta(document_type=<DocumentType.TXT: 'txt'>, source=LocalFileSource(source_type='local_file', path=PosixPath('/tmp/tmp7w8yk0qr')))
async def process(self, document_meta: DocumentMeta) -> list[Element]:
"""Process the document using the Unstructured API.
Args:
document_meta: The document to process.
Returns:
The list of elements extracted from the document.
Raises:
ValueError: If the UNSTRUCTURED_API_KEY or UNSTRUCTURED_API_URL environment variables are not set.
DocumentTypeNotSupportedError: If the document type is not supported.
"""
self.validate_document_type(document_meta.document_type)
if (api_key := os.getenv(UNSTRUCTURED_API_KEY_ENV)) is None:
> raise ValueError(f"{UNSTRUCTURED_API_KEY_ENV} environment variable is not set")
E ValueError: UNSTRUCTURED_API_KEY environment variable is not set
packages/ragbits-document-search/src/ragbits/document_search/ingestion/providers/unstructured.py:79: ValueError
Check failure on line 42 in packages/ragbits-document-search/tests/unit/test_document_search.py
github-actions / JUnit Test Report
test_document_search.test_document_search_from_config
ValueError: UNSTRUCTURED_API_KEY environment variable is not set
Raw output
async def test_document_search_from_config():
document_search = DocumentSearch.from_config(CONFIG)
> await document_search.ingest_document(
DocumentMeta.create_text_document_from_literal("Name of Peppa's brother is George")
)
packages/ragbits-document-search/tests/unit/test_document_search.py:42:
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
packages/ragbits-document-search/src/ragbits/document_search/_main.py:119: in ingest_document
elements = await document_processor.process(document_meta)
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
self = <ragbits.document_search.ingestion.providers.unstructured.UnstructuredProvider object at 0x7fd88340f550>
document_meta = DocumentMeta(document_type=<DocumentType.TXT: 'txt'>, source=LocalFileSource(source_type='local_file', path=PosixPath('/tmp/tmpojvcopfz')))
async def process(self, document_meta: DocumentMeta) -> list[Element]:
"""Process the document using the Unstructured API.
Args:
document_meta: The document to process.
Returns:
The list of elements extracted from the document.
Raises:
ValueError: If the UNSTRUCTURED_API_KEY or UNSTRUCTURED_API_URL environment variables are not set.
DocumentTypeNotSupportedError: If the document type is not supported.
"""
self.validate_document_type(document_meta.document_type)
if (api_key := os.getenv(UNSTRUCTURED_API_KEY_ENV)) is None:
> raise ValueError(f"{UNSTRUCTURED_API_KEY_ENV} environment variable is not set")
E ValueError: UNSTRUCTURED_API_KEY environment variable is not set
packages/ragbits-document-search/src/ragbits/document_search/ingestion/providers/unstructured.py:79: ValueError
Loading