mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
f92006de3c
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>
20 lines
744 B
Python
20 lines
744 B
Python
"""Test splitting with page numbers included."""
|
|
import os
|
|
|
|
from langchain_community.document_loaders import PyPDFLoader
|
|
from langchain_community.embeddings.openai import OpenAIEmbeddings
|
|
from langchain_community.vectorstores import FAISS
|
|
|
|
|
|
def test_pdf_pagesplitter() -> None:
|
|
"""Test splitting with page numbers included."""
|
|
script_dir = os.path.dirname(__file__)
|
|
loader = PyPDFLoader(os.path.join(script_dir, "examples/hello.pdf"))
|
|
docs = loader.load()
|
|
assert "page" in docs[0].metadata
|
|
assert "source" in docs[0].metadata
|
|
|
|
faiss_index = FAISS.from_documents(docs, OpenAIEmbeddings())
|
|
docs = faiss_index.similarity_search("Complete this sentence: Hello", k=1)
|
|
assert "Hello world" in docs[0].page_content
|