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

fix: support long texts for labels in ElasticsearchDocumentStore #3346

Merged
merged 16 commits into from
Nov 2, 2022
Merged

fix: support long texts for labels in ElasticsearchDocumentStore #3346

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
16 commits
Select commit Hold shift + click to select a range
d9c8e32
first try and test
anakin87 Oct 7, 2022
163ebc4
first try and test
anakin87 Oct 7, 2022
30248ef
try to fix schema
anakin87 Oct 7, 2022
7d77101
Merge remote-tracking branch 'upstream/main' into support_long_texts_…
anakin87 Oct 18, 2022
2527a0a
fix schemas
anakin87 Oct 18, 2022
b66ffce
fix openapi
anakin87 Oct 18, 2022
46df8ca
Merge remote-tracking branch 'origin/main' into support_long_texts_El…
anakin87 Oct 23, 2022
4fdad1f
Merge branch 'main' into support_long_texts_ElasticsearchDocumentStore
anakin87 Oct 27, 2022
388e622
fix test
anakin87 Oct 27, 2022
de98525
fix schema
anakin87 Oct 27, 2022
3ccfcf4
fix schema 2
anakin87 Oct 27, 2022
0eabc24
Merge branch 'main' into support_long_texts_ElasticsearchDocumentStore
anakin87 Oct 28, 2022
78ece56
try to change my test
anakin87 Oct 28, 2022
6aef9cc
fix test
anakin87 Oct 27, 2022
7da26a5
new try
anakin87 Oct 28, 2022
0754cee
imporve test
anakin87 Oct 30, 2022
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
4 changes: 2 additions & 2 deletions haystack/document_stores/elasticsearch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -521,8 +521,8 @@ def _create_label_index(self, index_name: str, headers: Optional[Dict[str, str]]
"mappings": {
"properties": {
"query": {"type": "text"},
"answer": {"type": "flattened"}, # light-weight but less search options than full object
"document": {"type": "flattened"},
"answer": {"type": "nested"},
"document": {"type": "nested"},
"is_correct_answer": {"type": "boolean"},
"is_correct_document": {"type": "boolean"},
"origin": {"type": "keyword"}, # e.g. user-feedback or gold-label
Expand Down
24 changes: 24 additions & 0 deletions test/document_stores/test_document_store.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -877,6 +877,30 @@ def test_labels(document_store: BaseDocumentStore):
assert len(labels) == 0


@pytest.mark.parametrize("document_store", ["elasticsearch", "opensearch"], indirect=True)
def test_labels_with_long_texts(document_store: BaseDocumentStore):
document_store.delete_index("label")
label = Label(
query="question1",
answer=Answer(
answer="answer",
type="extractive",
score=0.0,
context="something " * 10_000,
offsets_in_document=[Span(start=12, end=14)],
offsets_in_context=[Span(start=12, end=14)],
),
is_correct_answer=True,
is_correct_document=True,
document=Document(content="something " * 10_000, id="123"),
origin="gold-label",
)
document_store.write_labels(labels=[label], index="label")
labels = document_store.get_all_labels(index="label")
assert len(labels) == 1
assert label == labels[0]


# exclude weaviate because it does not support storing labels
@pytest.mark.parametrize("document_store", ["elasticsearch", "faiss", "memory", "milvus1", "pinecone"], indirect=True)
def test_multilabel(document_store: BaseDocumentStore):
Expand Down