test_from_texts.py — langchain Source File

Source Code

from __future__ import annotations

import uuid

import pytest
from langchain_core.documents import Document
from qdrant_client import models

from langchain_qdrant import QdrantVectorStore, RetrievalMode
from langchain_qdrant.qdrant import QdrantVectorStoreError
from tests.integration_tests.common import (
    ConsistentFakeEmbeddings,
    ConsistentFakeSparseEmbeddings,
    assert_documents_equals,
)
from tests.integration_tests.fixtures import qdrant_locations, retrieval_modes


@pytest.mark.parametrize("location", qdrant_locations())
@pytest.mark.parametrize("retrieval_mode", retrieval_modes())
def test_vectorstore_from_texts(location: str, retrieval_mode: RetrievalMode) -> None:
    """Test end to end Qdrant.from_texts stores texts."""
    collection_name = uuid.uuid4().hex

    vec_store = QdrantVectorStore.from_texts(
        ["Lorem ipsum dolor sit amet", "Ipsum dolor sit amet"],
        ConsistentFakeEmbeddings(),
        collection_name=collection_name,
        location=location,
        retrieval_mode=retrieval_mode,
        sparse_embedding=ConsistentFakeSparseEmbeddings(),
    )

    assert vec_store.client.count(collection_name).count == 2


@pytest.mark.parametrize("batch_size", [1, 64])
@pytest.mark.parametrize("vector_name", ["", "my-vector"])
@pytest.mark.parametrize(
    "sparse_vector_name", ["my-sparse-vector", "another-sparse-vector"]
)
@pytest.mark.parametrize("location", qdrant_locations())
@pytest.mark.parametrize("retrieval_mode", retrieval_modes())
def test_qdrant_from_texts_stores_ids(
    batch_size: int,
    vector_name: str,
    sparse_vector_name: str,
    location: str,
    retrieval_mode: RetrievalMode,
) -> None:
    """Test end to end Qdrant.from_texts stores provided ids."""
    collection_name = uuid.uuid4().hex
    ids: list[str | int] = [
        "fa38d572-4c31-4579-aedc-1960d79df6df",
        786,
    ]
    vec_store = QdrantVectorStore.from_texts(
        ["abc", "def"],
        ConsistentFakeEmbeddings(),
        ids=ids,
// ... (326 more lines)