Home / File/ test_base.py — langchain Source File

test_base.py — langchain Source File

Architecture documentation for test_base.py, a python file in the langchain codebase. 6 imports, 0 dependents.

File python CoreAbstractions Serialization 6 imports 7 functions

Entity Profile

Dependency Diagram

graph LR
  8a6d5332_62df_10bf_dacc_92ebb46285a4["test_base.py"]
  9e98f0a7_ec6e_708f_4f1b_e9428b316e1c["os"]
  8a6d5332_62df_10bf_dacc_92ebb46285a4 --> 9e98f0a7_ec6e_708f_4f1b_e9428b316e1c
  8e2034b7_ceb8_963f_29fc_2ea6b50ef9b3["typing"]
  8a6d5332_62df_10bf_dacc_92ebb46285a4 --> 8e2034b7_ceb8_963f_29fc_2ea6b50ef9b3
  525a7d6f_f455_56e3_854a_c8a7da4a1417["unittest.mock"]
  8a6d5332_62df_10bf_dacc_92ebb46285a4 --> 525a7d6f_f455_56e3_854a_c8a7da4a1417
  120e2591_3e15_b895_72b6_cb26195e40a6["pytest"]
  8a6d5332_62df_10bf_dacc_92ebb46285a4 --> 120e2591_3e15_b895_72b6_cb26195e40a6
  6e58aaea_f08e_c099_3cc7_f9567bfb1ae7["pydantic"]
  8a6d5332_62df_10bf_dacc_92ebb46285a4 --> 6e58aaea_f08e_c099_3cc7_f9567bfb1ae7
  0b28cff6_d823_1571_d2bb_ec61508cc89c["langchain_openai"]
  8a6d5332_62df_10bf_dacc_92ebb46285a4 --> 0b28cff6_d823_1571_d2bb_ec61508cc89c
  style 8a6d5332_62df_10bf_dacc_92ebb46285a4 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

import os
from typing import Any
from unittest.mock import Mock, patch

import pytest
from pydantic import SecretStr

from langchain_openai import OpenAIEmbeddings

os.environ["OPENAI_API_KEY"] = "foo"


def test_openai_invalid_model_kwargs() -> None:
    with pytest.raises(ValueError):
        OpenAIEmbeddings(model_kwargs={"model": "foo"})


def test_openai_incorrect_field() -> None:
    with pytest.warns(match="not default parameter"):
        llm = OpenAIEmbeddings(foo="bar")  # type: ignore[call-arg]
    assert llm.model_kwargs == {"foo": "bar"}


def test_embed_documents_with_custom_chunk_size() -> None:
    embeddings = OpenAIEmbeddings(chunk_size=2)
    texts = ["text1", "text2", "text3", "text4"]
    custom_chunk_size = 3

    with patch.object(embeddings.client, "create") as mock_create:
        mock_create.side_effect = [
            {"data": [{"embedding": [0.1, 0.2]}, {"embedding": [0.3, 0.4]}]},
            {"data": [{"embedding": [0.5, 0.6]}, {"embedding": [0.7, 0.8]}]},
        ]

        result = embeddings.embed_documents(texts, chunk_size=custom_chunk_size)
        _, tokens, __, ___ = embeddings._tokenize(texts, custom_chunk_size)
        mock_create.call_args
        mock_create.assert_any_call(input=tokens[0:3], **embeddings._invocation_params)
        mock_create.assert_any_call(input=tokens[3:4], **embeddings._invocation_params)

    assert result == [[0.1, 0.2], [0.3, 0.4], [0.5, 0.6], [0.7, 0.8]]


def test_embed_documents_with_custom_chunk_size_no_check_ctx_length() -> None:
    embeddings = OpenAIEmbeddings(chunk_size=2, check_embedding_ctx_length=False)
    texts = ["text1", "text2", "text3", "text4"]
    custom_chunk_size = 3

    with patch.object(embeddings.client, "create") as mock_create:
        mock_create.side_effect = [
            {"data": [{"embedding": [0.1, 0.2]}, {"embedding": [0.3, 0.4]}]},
            {"data": [{"embedding": [0.5, 0.6]}, {"embedding": [0.7, 0.8]}]},
        ]

        result = embeddings.embed_documents(texts, chunk_size=custom_chunk_size)

        mock_create.call_args
        mock_create.assert_any_call(input=texts[0:3], **embeddings._invocation_params)
        mock_create.assert_any_call(input=texts[3:4], **embeddings._invocation_params)

// ... (91 more lines)

Subdomains

Dependencies

  • langchain_openai
  • os
  • pydantic
  • pytest
  • typing
  • unittest.mock

Frequently Asked Questions

What does test_base.py do?
test_base.py is a source file in the langchain codebase, written in python. It belongs to the CoreAbstractions domain, Serialization subdomain.
What functions are defined in test_base.py?
test_base.py defines 7 function(s): test_embed_documents_with_custom_chunk_size, test_embed_documents_with_custom_chunk_size_no_check_ctx_length, test_embed_with_kwargs, test_embed_with_kwargs_async, test_embeddings_respects_token_limit, test_openai_incorrect_field, test_openai_invalid_model_kwargs.
What does test_base.py depend on?
test_base.py imports 6 module(s): langchain_openai, os, pydantic, pytest, typing, unittest.mock.
Where is test_base.py in the architecture?
test_base.py is located at libs/partners/openai/tests/unit_tests/embeddings/test_base.py (domain: CoreAbstractions, subdomain: Serialization, directory: libs/partners/openai/tests/unit_tests/embeddings).

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free