langchain Architecture Docs
Home / File/ test_embedding.py — langchain Source File

test_embedding.py — langchain Source File

Architecture documentation for test_embedding.py, a python file in the langchain codebase. 4 imports, 0 dependents.

File python LangChainCore MessageInterface 4 imports 10 functions

Entity Profile

Dependency Diagram

graph LR
  89627e7b_46a2_902e_b342_68623bc9d7ef["test_embedding.py"]
  eea920d0_5f0d_7728_8367_275e1830e552["numpy"]
  89627e7b_46a2_902e_b342_68623bc9d7ef --> eea920d0_5f0d_7728_8367_275e1830e552
  f69d6389_263d_68a4_7fbf_f14c0602a9ba["pytest"]
  89627e7b_46a2_902e_b342_68623bc9d7ef --> f69d6389_263d_68a4_7fbf_f14c0602a9ba
  11152143_939d_f18c_9466_cbcb3fa40dfe["langchain_classic.evaluation.embedding_distance"]
  89627e7b_46a2_902e_b342_68623bc9d7ef --> 11152143_939d_f18c_9466_cbcb3fa40dfe
  cd808c2d_1198_e671_b11f_16844d1f10da["scipy.spatial.distance"]
  89627e7b_46a2_902e_b342_68623bc9d7ef --> cd808c2d_1198_e671_b11f_16844d1f10da
  style 89627e7b_46a2_902e_b342_68623bc9d7ef fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

import numpy as np
import pytest

from langchain_classic.evaluation.embedding_distance import (
    EmbeddingDistance,
    EmbeddingDistanceEvalChain,
    PairwiseEmbeddingDistanceEvalChain,
)


@pytest.fixture
def vectors() -> tuple[np.ndarray, np.ndarray]:
    """Create two random vectors."""
    vector_a = np.array(
        [
            0.5488135,
            0.71518937,
            0.60276338,
            0.54488318,
            0.4236548,
            0.64589411,
            0.43758721,
            0.891773,
            0.96366276,
            0.38344152,
        ],
    )
    vector_b = np.array(
        [
            0.79172504,
            0.52889492,
            0.56804456,
            0.92559664,
            0.07103606,
            0.0871293,
            0.0202184,
            0.83261985,
            0.77815675,
            0.87001215,
        ],
    )
    return vector_a, vector_b


@pytest.fixture
def pairwise_embedding_distance_eval_chain() -> PairwiseEmbeddingDistanceEvalChain:
    """Create a PairwiseEmbeddingDistanceEvalChain."""
    return PairwiseEmbeddingDistanceEvalChain()


@pytest.fixture
def embedding_distance_eval_chain() -> EmbeddingDistanceEvalChain:
    """Create a EmbeddingDistanceEvalChain."""
    return EmbeddingDistanceEvalChain()


@pytest.mark.requires("scipy")
def test_pairwise_embedding_distance_eval_chain_cosine_similarity(
    pairwise_embedding_distance_eval_chain: PairwiseEmbeddingDistanceEvalChain,
    vectors: tuple[np.ndarray, np.ndarray],
// ... (91 more lines)

Domain

Subdomains

Functions

Dependencies

  • langchain_classic.evaluation.embedding_distance
  • numpy
  • pytest
  • scipy.spatial.distance

Source

Frequently Asked Questions

What does test_embedding.py do?
test_embedding.py is a source file in the langchain codebase, written in python. It belongs to the LangChainCore domain, MessageInterface subdomain.
What functions are defined in test_embedding.py?
test_embedding.py defines 10 function(s): embedding_distance_eval_chain, pairwise_embedding_distance_eval_chain, test_embedding_distance_eval_chain, test_pairwise_embedding_distance_eval_chain_chebyshev_distance, test_pairwise_embedding_distance_eval_chain_cosine_similarity, test_pairwise_embedding_distance_eval_chain_embedding_distance, test_pairwise_embedding_distance_eval_chain_euclidean_distance, test_pairwise_embedding_distance_eval_chain_hamming_distance, test_pairwise_embedding_distance_eval_chain_manhattan_distance, vectors.
What does test_embedding.py depend on?
test_embedding.py imports 4 module(s): langchain_classic.evaluation.embedding_distance, numpy, pytest, scipy.spatial.distance.
Where is test_embedding.py in the architecture?
test_embedding.py is located at libs/langchain/tests/integration_tests/evaluation/embedding_distance/test_embedding.py (domain: LangChainCore, subdomain: MessageInterface, directory: libs/langchain/tests/integration_tests/evaluation/embedding_distance).

Analyze Your Own Codebase

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

Try Supermodel Free