From f25416b0ffdb04cef5fbace73646989182cae4e7 Mon Sep 17 00:00:00 2001 From: Yiorgis Gozadinos Date: Fri, 18 Jul 2025 20:55:28 +0300 Subject: [PATCH] Properly test cohere reranker --- src/haiku/rag/config.py | 2 - tests/test_reranker.py | 95 +++++++++-------------------------------- 2 files changed, 21 insertions(+), 76 deletions(-) diff --git a/src/haiku/rag/config.py b/src/haiku/rag/config.py index 6151a80c..8fb2bef1 100644 --- a/src/haiku/rag/config.py +++ b/src/haiku/rag/config.py @@ -19,8 +19,6 @@ class AppConfig(BaseModel): EMBEDDINGS_MODEL: str = "mxbai-embed-large" EMBEDDINGS_VECTOR_DIM: int = 1024 - # RERANK_PROVIDER: str = "cohere" - # RERANK_MODEL: str = "rerank-v3.5" RERANK_MODEL: str = "mixedbread-ai/mxbai-rerank-base-v2" RERANK_PROVIDER: str = "mxbai" diff --git a/tests/test_reranker.py b/tests/test_reranker.py index 39a515c1..c83c2d3d 100644 --- a/tests/test_reranker.py +++ b/tests/test_reranker.py @@ -1,10 +1,23 @@ import pytest -from haiku.rag.reranking import get_reranker from haiku.rag.reranking.base import RerankerBase from haiku.rag.reranking.mxbai import MxBAIReranker from haiku.rag.store.models.chunk import Chunk +chunks = [ + Chunk(content=content, document_id=i) + for i, content in enumerate( + [ + "To Kill a Mockingbird is a novel by Harper Lee published in 1960. It was immediately successful, winning the Pulitzer Prize, and has become a classic of modern American literature.", + "The novel Moby-Dick was written by Herman Melville and first published in 1851. It is considered a masterpiece of American literature and deals with complex themes of obsession, revenge, and the conflict between good and evil.", + "Harper Lee, an American novelist widely known for her novel To Kill a Mockingbird, was born in 1926 in Monroeville, Alabama. She received the Pulitzer Prize for Fiction in 1961.", + "Jane Austen was an English novelist known primarily for her six major novels, which interpret, critique and comment upon the British landed gentry at the end of the 18th century.", + "The Harry Potter series, which consists of seven fantasy novels written by British author J.K. Rowling, is among the most popular and critically acclaimed books of the modern era.", + "The Great Gatsby, a novel written by American author F. Scott Fitzgerald, was published in 1925. The story is set in the Jazz Age and follows the life of millionaire Jay Gatsby and his pursuit of Daisy Buchanan.", + ] + ) +] + @pytest.mark.asyncio async def test_reranker_base(): @@ -18,20 +31,6 @@ async def test_reranker_base(): @pytest.mark.asyncio async def test_mxbai_reranker(): reranker = MxBAIReranker() - chunks = [ - Chunk(content=content, document_id=i) - for i, content in enumerate( - [ - "To Kill a Mockingbird is a novel by Harper Lee published in 1960. It was immediately successful, winning the Pulitzer Prize, and has become a classic of modern American literature.", - "The novel Moby-Dick was written by Herman Melville and first published in 1851. It is considered a masterpiece of American literature and deals with complex themes of obsession, revenge, and the conflict between good and evil.", - "Harper Lee, an American novelist widely known for her novel To Kill a Mockingbird, was born in 1926 in Monroeville, Alabama. She received the Pulitzer Prize for Fiction in 1961.", - "Jane Austen was an English novelist known primarily for her six major novels, which interpret, critique and comment upon the British landed gentry at the end of the 18th century.", - "The Harry Potter series, which consists of seven fantasy novels written by British author J.K. Rowling, is among the most popular and critically acclaimed books of the modern era.", - "The Great Gatsby, a novel written by American author F. Scott Fitzgerald, was published in 1925. The story is set in the Jazz Age and follows the life of millionaire Jay Gatsby and his pursuit of Daisy Buchanan.", - ] - ) - ] - reranked = await reranker.rerank( "Who wrote 'To Kill a Mockingbird'?", chunks, top_n=2 ) @@ -41,67 +40,15 @@ async def test_mxbai_reranker(): @pytest.mark.asyncio async def test_cohere_reranker(): try: - # Mock the client - class MockResult: - def __init__(self, index): - self.index = index + from haiku.rag.reranking.cohere import CohereReranker - class MockResponse: - def __init__(self, results): - self.results = results + reranker = CohereReranker() + assert reranker._model == "rerank-v3.5" - class MockClient: - def __init__(self, api_key=None): - pass - - def rerank(self, model, query, documents, top_n): - return MockResponse([MockResult(1), MockResult(0)]) - - import haiku.rag.reranking.cohere - - original_client = haiku.rag.reranking.cohere.cohere.ClientV2 - haiku.rag.reranking.cohere.cohere.ClientV2 = MockClient - - try: - from haiku.rag.reranking.cohere import CohereReranker - - reranker = CohereReranker() - assert reranker._model == "rerank-v3.5" - - chunks = [ - Chunk(id=1, content="First chunk", document_id=1), - Chunk(id=2, content="Second chunk", document_id=1), - ] - - result = await reranker.rerank("test query", chunks) - assert len(result) == 2 - assert result[0] == chunks[1] # Should return chunk at index 1 first - assert result[1] == chunks[0] # Should return chunk at index 0 second - finally: - haiku.rag.reranking.cohere.cohere.ClientV2 = original_client + reranked = await reranker.rerank( + "Who wrote 'To Kill a Mockingbird'?", chunks, top_n=2 + ) + assert [r.document_id for r in reranked] == [0, 2] except ImportError: pytest.skip("Cohere package not installed") - - -@pytest.mark.asyncio -async def test_get_reranker(): - try: - - class MockClient: - def __init__(self, api_key=None): - pass - - import haiku.rag.reranking.cohere - - original_client = haiku.rag.reranking.cohere.cohere.ClientV2 - haiku.rag.reranking.cohere.cohere.ClientV2 = MockClient - - try: - reranker = get_reranker() - assert reranker._model == "rerank-v3.5" - assert hasattr(reranker, "rerank") - finally: - haiku.rag.reranking.cohere.cohere.ClientV2 = original_client - except ImportError: - pytest.skip("Cohere package not installed")