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

vectorstores.py — langchain Source File

Architecture documentation for vectorstores.py, a python file in the langchain codebase. 16 imports, 0 dependents.

File python CoreAbstractions MessageSchema 16 imports 6 functions 1 classes

Entity Profile

Dependency Diagram

graph LR
  d4a05de9_1f0f_3b21_8171_181bb47227ef["vectorstores.py"]
  66c6348c_7716_027c_42d7_71449bc64eeb["base64"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> 66c6348c_7716_027c_42d7_71449bc64eeb
  2a7f66a7_8738_3d47_375b_70fcaa6ac169["logging"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> 2a7f66a7_8738_3d47_375b_70fcaa6ac169
  8dfa0cac_d802_3ccd_f710_43a5e70da3a5["uuid"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> 8dfa0cac_d802_3ccd_f710_43a5e70da3a5
  cfe2bde5_180e_e3b0_df2b_55b3ebaca8e7["collections.abc"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> cfe2bde5_180e_e3b0_df2b_55b3ebaca8e7
  b6ee5de5_719a_eeb5_1e11_e9c63bc22ef8["pathlib"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> b6ee5de5_719a_eeb5_1e11_e9c63bc22ef8
  8e2034b7_ceb8_963f_29fc_2ea6b50ef9b3["typing"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> 8e2034b7_ceb8_963f_29fc_2ea6b50ef9b3
  d98e8b62_bf78_a37b_60df_6acbcc3d5521["chromadb"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> d98e8b62_bf78_a37b_60df_6acbcc3d5521
  d533015f_a415_cc9a_d461_50b1acd925d0["chromadb.config"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> d533015f_a415_cc9a_d461_50b1acd925d0
  cd17727f_b882_7f06_aadc_71fbf75bebb0["numpy"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> cd17727f_b882_7f06_aadc_71fbf75bebb0
  c45be9d8_4862_0a1e_47f1_1abb2540ba7f["chromadb.api"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> c45be9d8_4862_0a1e_47f1_1abb2540ba7f
  c554676d_b731_47b2_a98f_c1c2d537c0aa["langchain_core.documents"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> c554676d_b731_47b2_a98f_c1c2d537c0aa
  bc46b61d_cfdf_3f6b_a9dd_ac2a328d84b3["langchain_core.embeddings"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> bc46b61d_cfdf_3f6b_a9dd_ac2a328d84b3
  f4d905c6_a2b2_eb8f_be9b_7808b72f6a16["langchain_core.utils"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> f4d905c6_a2b2_eb8f_be9b_7808b72f6a16
  d55af636_303c_0eb6_faee_20d89bd952d5["langchain_core.vectorstores"]
  d4a05de9_1f0f_3b21_8171_181bb47227ef --> d55af636_303c_0eb6_faee_20d89bd952d5
  style d4a05de9_1f0f_3b21_8171_181bb47227ef fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

"""This is the langchain_chroma.vectorstores module.

It contains the Chroma class which is a vector store for handling various tasks.
"""

from __future__ import annotations

import base64
import logging
import uuid
from collections.abc import Callable, Iterable, Sequence
from pathlib import Path
from typing import (
    TYPE_CHECKING,
    Any,
)

import chromadb
import chromadb.config
import numpy as np
from chromadb import Search, Settings
from chromadb.api import CreateCollectionConfiguration
from langchain_core.documents import Document
from langchain_core.embeddings import Embeddings
from langchain_core.utils import xor_args
from langchain_core.vectorstores import VectorStore

if TYPE_CHECKING:
    from chromadb.api.types import Where, WhereDocument

logger = logging.getLogger()
DEFAULT_K = 4  # Number of Documents to return.


def _results_to_docs(results: Any) -> list[Document]:
    return [doc for doc, _ in _results_to_docs_and_scores(results)]


def _results_to_docs_and_scores(results: Any) -> list[tuple[Document, float]]:
    return [
        # TODO: Chroma can do batch querying,
        # we shouldn't hard code to the 1st result
        (
            Document(page_content=result[0], metadata=result[1] or {}, id=result[2]),
            result[3],
        )
        for result in zip(
            results["documents"][0],
            results["metadatas"][0],
            results["ids"][0],
            results["distances"][0],
            strict=False,
        )
        if result[0] is not None
    ]


def _results_to_docs_and_vectors(results: Any) -> list[tuple[Document, np.ndarray]]:
    """Convert ChromaDB results to documents and vectors, filtering out None content."""
    return [
// ... (1400 more lines)

Domain

Subdomains

Functions

Classes

Dependencies

  • base64
  • chromadb
  • chromadb.api
  • chromadb.api.types
  • chromadb.config
  • chromadb.utils.batch_utils
  • collections.abc
  • langchain_core.documents
  • langchain_core.embeddings
  • langchain_core.utils
  • langchain_core.vectorstores
  • logging
  • numpy
  • pathlib
  • typing
  • uuid

Source

Frequently Asked Questions

What does vectorstores.py do?
vectorstores.py is a source file in the langchain codebase, written in python. It belongs to the CoreAbstractions domain, MessageSchema subdomain.
What functions are defined in vectorstores.py?
vectorstores.py defines 6 function(s): _results_to_docs, _results_to_docs_and_scores, _results_to_docs_and_vectors, chromadb, cosine_similarity, maximal_marginal_relevance.
What does vectorstores.py depend on?
vectorstores.py imports 16 module(s): base64, chromadb, chromadb.api, chromadb.api.types, chromadb.config, chromadb.utils.batch_utils, collections.abc, langchain_core.documents, and 8 more.
Where is vectorstores.py in the architecture?
vectorstores.py is located at libs/partners/chroma/langchain_chroma/vectorstores.py (domain: CoreAbstractions, subdomain: MessageSchema, directory: libs/partners/chroma/langchain_chroma).

Analyze Your Own Codebase

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

Try Supermodel Free