langchain/libs/community/tests/integration_tests/chains/test_retrieval_qa.py
Eugene Yurtsev f92006de3c
multiple: langchain 0.2 in master (#21191)
0.2rc 

migrations

- [x] Move memory
- [x] Move remaining retrievers
- [x] graph_qa chains
- [x] some dependency from evaluation code potentially on math utils
- [x] Move openapi chain from `langchain.chains.api.openapi` to
`langchain_community.chains.openapi`
- [x] Migrate `langchain.chains.ernie_functions` to
`langchain_community.chains.ernie_functions`
- [x] migrate `langchain/chains/llm_requests.py` to
`langchain_community.chains.llm_requests`
- [x] Moving `langchain_community.cross_enoders.base:BaseCrossEncoder`
->
`langchain_community.retrievers.document_compressors.cross_encoder:BaseCrossEncoder`
(namespace not ideal, but it needs to be moved to `langchain` to avoid
circular deps)
- [x] unit tests langchain -- add pytest.mark.community to some unit
tests that will stay in langchain
- [x] unit tests community -- move unit tests that depend on community
to community
- [x] mv integration tests that depend on community to community
- [x] mypy checks

Other todo

- [x] Make deprecation warnings not noisy (need to use warn deprecated
and check that things are implemented properly)
- [x] Update deprecation messages with timeline for code removal (likely
we actually won't be removing things until 0.4 release) -- will give
people more time to transition their code.
- [ ] Add information to deprecation warning to show users how to
migrate their code base using langchain-cli
- [ ] Remove any unnecessary requirements in langchain (e.g., is
SQLALchemy required?)

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-05-08 16:46:52 -04:00

30 lines
1.2 KiB
Python

"""Test RetrievalQA functionality."""
from pathlib import Path
from langchain.chains import RetrievalQA
from langchain.chains.loading import load_chain
from langchain_text_splitters.character import CharacterTextSplitter
from langchain_community.document_loaders import TextLoader
from langchain_community.embeddings.openai import OpenAIEmbeddings
from langchain_community.llms import OpenAI
from langchain_community.vectorstores import FAISS
def test_retrieval_qa_saving_loading(tmp_path: Path) -> None:
"""Test saving and loading."""
loader = TextLoader("docs/extras/modules/state_of_the_union.txt")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
docsearch = FAISS.from_documents(texts, embeddings)
qa = RetrievalQA.from_llm(llm=OpenAI(), retriever=docsearch.as_retriever())
qa.run("What did the president say about Ketanji Brown Jackson?")
file_path = tmp_path / "RetrievalQA_chain.yaml"
qa.save(file_path=file_path)
qa_loaded = load_chain(file_path, retriever=docsearch.as_retriever())
assert qa_loaded == qa