yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-11-13 16:43:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix id for documents returned by the TfidfRetriever (#232)

Browse Source
This commit is contained in:
Tanay Soni 2020-07-15 14:55:07 +02:00 committed by GitHub
parent 4e10a1520d
commit 912e98cd40
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
haystack/retriever/sparse.py
View File

@ -186,7 +186,7 @@ class TfidfRetriever(BaseRetriever):
for para, meta in zip(paragraphs, meta_data): for para, meta in zip(paragraphs, meta_data):
documents.append( documents.append(
Document( Document(
id=meta["paragraph_id"], id=meta["document_id"],
text=para, text=para,
meta=meta.get("meta", {}) meta=meta.get("meta", {})
)) ))

1
test/test_finder.py
View File

@ -16,7 +16,6 @@ def test_finder_get_answers(reader, document_store_with_docs):
assert prediction["answers"][0]["probability"] >= 0 assert prediction["answers"][0]["probability"] >= 0
assert prediction["answers"][0]["meta"]["meta_field"] == "test1" assert prediction["answers"][0]["meta"]["meta_field"] == "test1"
assert prediction["answers"][0]["context"] == "My name is Carla and I live in Berlin" assert prediction["answers"][0]["context"] == "My name is Carla and I live in Berlin"
assert prediction["answers"][0]["document_id"] == "0"
assert len(prediction["answers"]) == 3 assert len(prediction["answers"]) == 3

2
test/test_tfidf_retriever.py
View File

@ -18,7 +18,7 @@ def test_tfidf_retriever():
retriever.fit() retriever.fit()
assert retriever.retrieve("godzilla", top_k=1) == [ assert retriever.retrieve("godzilla", top_k=1) == [
Document( Document(
id='0', id='26f84672c6d7aaeb8e2cd53e9c62d62d',
text='godzilla says hello', text='godzilla says hello',
external_source_id=None, external_source_id=None,
question=None, question=None,