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>
74 lines
3.1 KiB
Python
74 lines
3.1 KiB
Python
"""Integration test for embedding-based redundant doc filtering."""
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_transformers.embeddings_redundant_filter import (
|
|
EmbeddingsClusteringFilter,
|
|
EmbeddingsRedundantFilter,
|
|
_DocumentWithState,
|
|
)
|
|
from langchain_community.embeddings import OpenAIEmbeddings
|
|
|
|
|
|
def test_embeddings_redundant_filter() -> None:
|
|
texts = [
|
|
"What happened to all of my cookies?",
|
|
"Where did all of my cookies go?",
|
|
"I wish there were better Italian restaurants in my neighborhood.",
|
|
]
|
|
docs = [Document(page_content=t) for t in texts]
|
|
embeddings = OpenAIEmbeddings()
|
|
redundant_filter = EmbeddingsRedundantFilter(embeddings=embeddings)
|
|
actual = redundant_filter.transform_documents(docs)
|
|
assert len(actual) == 2
|
|
assert set(texts[:2]).intersection([d.page_content for d in actual])
|
|
|
|
|
|
def test_embeddings_redundant_filter_with_state() -> None:
|
|
texts = ["What happened to all of my cookies?", "foo bar baz"]
|
|
state = {"embedded_doc": [0.5] * 10}
|
|
docs = [_DocumentWithState(page_content=t, state=state) for t in texts]
|
|
embeddings = OpenAIEmbeddings()
|
|
redundant_filter = EmbeddingsRedundantFilter(embeddings=embeddings)
|
|
actual = redundant_filter.transform_documents(docs)
|
|
assert len(actual) == 1
|
|
|
|
|
|
def test_embeddings_clustering_filter() -> None:
|
|
texts = [
|
|
"What happened to all of my cookies?",
|
|
"A cookie is a small, baked sweet treat and you can find it in the cookie",
|
|
"monsters' jar.",
|
|
"Cookies are good.",
|
|
"I have nightmares about the cookie monster.",
|
|
"The most popular pizza styles are: Neapolitan, New York-style and",
|
|
"Chicago-style. You can find them on iconic restaurants in major cities.",
|
|
"Neapolitan pizza: This is the original pizza style,hailing from Naples,",
|
|
"Italy.",
|
|
"I wish there were better Italian Pizza restaurants in my neighborhood.",
|
|
"New York-style pizza: This is characterized by its large, thin crust, and",
|
|
"generous toppings.",
|
|
"The first movie to feature a robot was 'A Trip to the Moon' (1902).",
|
|
"The first movie to feature a robot that could pass for a human was",
|
|
"'Blade Runner' (1982)",
|
|
"The first movie to feature a robot that could fall in love with a human",
|
|
"was 'Her' (2013)",
|
|
"A robot is a machine capable of carrying out complex actions automatically.",
|
|
"There are certainly hundreds, if not thousands movies about robots like:",
|
|
"'Blade Runner', 'Her' and 'A Trip to the Moon'",
|
|
]
|
|
|
|
docs = [Document(page_content=t) for t in texts]
|
|
embeddings = OpenAIEmbeddings()
|
|
redundant_filter = EmbeddingsClusteringFilter(
|
|
embeddings=embeddings,
|
|
num_clusters=3,
|
|
num_closest=1,
|
|
sorted=True,
|
|
)
|
|
actual = redundant_filter.transform_documents(docs)
|
|
assert len(actual) == 3
|
|
assert texts[1] in [d.page_content for d in actual]
|
|
assert texts[4] in [d.page_content for d in actual]
|
|
assert texts[11] in [d.page_content for d in actual]
|