langchain/tests/integration_tests/retrievers/test_merger_retriever.py
Nuno Campos 81e5b1ad36
Add serialized object to retriever start callback (#7074)
<!-- Thank you for contributing to LangChain!

Replace this comment with:
  - Description: a description of the change, 
  - Issue: the issue # it fixes (if applicable),
  - Dependencies: any dependencies required for this change,
- Tag maintainer: for a quicker response, tag the relevant maintainer
(see below),
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
  2. an example notebook showing its use.

Maintainer responsibilities:
  - General / Misc / if you don't know who to tag: @dev2049
  - DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
  - Models / Prompts: @hwchase17, @dev2049
  - Memory: @hwchase17
  - Agents / Tools / Toolkits: @vowelparrot
  - Tracing / Callbacks: @agola11
  - Async: @agola11

If no one reviews your PR within a few days, feel free to @-mention the
same people again.

See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
 -->
2023-07-05 18:04:43 +01:00

33 lines
1.2 KiB
Python

from langchain.embeddings import OpenAIEmbeddings
from langchain.retrievers.merger_retriever import MergerRetriever
from langchain.vectorstores import Chroma
def test_merger_retriever_get_relevant_docs() -> None:
"""Test get_relevant_docs."""
texts_group_a = [
"This is a document about the Boston Celtics",
"Fly me to the moon is one of my favourite songs."
"I simply love going to the movies",
]
texts_group_b = [
"This is a document about the Poenix Suns",
"The Boston Celtics won the game by 20 points",
"Real stupidity beats artificial intelligence every time. TP",
]
embeddings = OpenAIEmbeddings()
retriever_a = Chroma.from_texts(texts_group_a, embedding=embeddings).as_retriever(
search_kwargs={"k": 1}
)
retriever_b = Chroma.from_texts(texts_group_b, embedding=embeddings).as_retriever(
search_kwargs={"k": 1}
)
# The Lord of the Retrievers.
lotr = MergerRetriever(retrievers=[retriever_a, retriever_b])
actual = lotr.get_relevant_documents("Tell me about the Celtics")
assert len(actual) == 2
assert texts_group_a[0] in [d.page_content for d in actual]
assert texts_group_b[1] in [d.page_content for d in actual]