mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
ed58eeb9c5
Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
import pytest
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.retrievers.bm25 import BM25Retriever
|
|
|
|
|
|
@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]
|