mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
ee40d37098
- Description: Add a BM25 Retriever that do not need Elastic search - Dependencies: rank_bm25(if it is not installed it will be install by using pip, just like TFIDFRetriever do) - Tag maintainer: @rlancemartin, @eyurtsev - Twitter handle: DayuanJian21687 --------- Co-authored-by: Bagatur <baskaryan@gmail.com>
35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
import pytest
|
|
|
|
from langchain.retrievers.bm25 import BM25Retriever
|
|
from langchain.schema import Document
|
|
|
|
|
|
@pytest.mark.requires("rank_bm25")
|
|
def test_from_texts() -> None:
|
|
input_texts = ["I have a pen.", "Do you have a pen?", "I have a bag."]
|
|
bm25_retriever = BM25Retriever.from_texts(texts=input_texts)
|
|
assert len(bm25_retriever.docs) == 3
|
|
assert bm25_retriever.vectorizer.doc_len == [4, 5, 4]
|
|
|
|
|
|
@pytest.mark.requires("rank_bm25")
|
|
def test_from_texts_with_bm25_params() -> None:
|
|
input_texts = ["I have a pen.", "Do you have a pen?", "I have a bag."]
|
|
bm25_retriever = BM25Retriever.from_texts(
|
|
texts=input_texts, bm25_params={"epsilon": 10}
|
|
)
|
|
# should count only multiple words (have, pan)
|
|
assert bm25_retriever.vectorizer.epsilon == 10
|
|
|
|
|
|
@pytest.mark.requires("rank_bm25")
|
|
def test_from_documents() -> None:
|
|
input_docs = [
|
|
Document(page_content="I have a pen."),
|
|
Document(page_content="Do you have a pen?"),
|
|
Document(page_content="I have a bag."),
|
|
]
|
|
bm25_retriever = BM25Retriever.from_documents(documents=input_docs)
|
|
assert len(bm25_retriever.docs) == 3
|
|
assert bm25_retriever.vectorizer.doc_len == [4, 5, 4]
|