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

chain.py — langchain Source File

Architecture documentation for chain.py, a python file in the langchain codebase. 15 imports, 0 dependents.

File python CoreAbstractions RunnableInterface 15 imports 5 functions 1 classes

Entity Profile

Dependency Diagram

graph LR
  860b0864_9436_83ab_1629_fa6791becd88["chain.py"]
  cfe2bde5_180e_e3b0_df2b_55b3ebaca8e7["collections.abc"]
  860b0864_9436_83ab_1629_fa6791becd88 --> cfe2bde5_180e_e3b0_df2b_55b3ebaca8e7
  8e2034b7_ceb8_963f_29fc_2ea6b50ef9b3["typing"]
  860b0864_9436_83ab_1629_fa6791becd88 --> 8e2034b7_ceb8_963f_29fc_2ea6b50ef9b3
  b19a8b7e_fbee_95b1_65b8_509a1ed3cad7["langchain_core._api"]
  860b0864_9436_83ab_1629_fa6791becd88 --> b19a8b7e_fbee_95b1_65b8_509a1ed3cad7
  f3bc7443_c889_119d_0744_aacc3620d8d2["langchain_core.callbacks"]
  860b0864_9436_83ab_1629_fa6791becd88 --> f3bc7443_c889_119d_0744_aacc3620d8d2
  ba43b74d_3099_7e1c_aac3_cf594720469e["langchain_core.language_models"]
  860b0864_9436_83ab_1629_fa6791becd88 --> ba43b74d_3099_7e1c_aac3_cf594720469e
  e6b4f61e_7b98_6666_3641_26b069517d4a["langchain_core.prompts"]
  860b0864_9436_83ab_1629_fa6791becd88 --> e6b4f61e_7b98_6666_3641_26b069517d4a
  9b4ec80f_d8de_a6e0_4f16_67ba56685088["langchain_classic.chains"]
  860b0864_9436_83ab_1629_fa6791becd88 --> 9b4ec80f_d8de_a6e0_4f16_67ba56685088
  a0d4f6c3_2d96_364c_720a_e778ffd171a0["langchain_classic.chains.combine_documents.base"]
  860b0864_9436_83ab_1629_fa6791becd88 --> a0d4f6c3_2d96_364c_720a_e778ffd171a0
  6d71bcfe_5d92_7e40_c7e2_fcdbf7baf6b1["langchain_classic.chains.combine_documents.map_reduce"]
  860b0864_9436_83ab_1629_fa6791becd88 --> 6d71bcfe_5d92_7e40_c7e2_fcdbf7baf6b1
  79156da2_e724_3283_1bf7_b4549775b347["langchain_classic.chains.combine_documents.map_rerank"]
  860b0864_9436_83ab_1629_fa6791becd88 --> 79156da2_e724_3283_1bf7_b4549775b347
  8ee8a976_803a_5da1_9bc4_533b3c16afb3["langchain_classic.chains.combine_documents.refine"]
  860b0864_9436_83ab_1629_fa6791becd88 --> 8ee8a976_803a_5da1_9bc4_533b3c16afb3
  2bdb44fe_f0bd_1fb7_7a70_02295a883921["langchain_classic.chains.combine_documents.stuff"]
  860b0864_9436_83ab_1629_fa6791becd88 --> 2bdb44fe_f0bd_1fb7_7a70_02295a883921
  31974615_0d58_bd26_13f1_776e0a9d1413["langchain_classic.chains.llm"]
  860b0864_9436_83ab_1629_fa6791becd88 --> 31974615_0d58_bd26_13f1_776e0a9d1413
  e6ac18e7_d796_7f28_0e10_bc2c76a20556["langchain_classic.chains.question_answering"]
  860b0864_9436_83ab_1629_fa6791becd88 --> e6ac18e7_d796_7f28_0e10_bc2c76a20556
  style 860b0864_9436_83ab_1629_fa6791becd88 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

"""Load question answering chains."""

from collections.abc import Mapping
from typing import Any, Protocol

from langchain_core._api import deprecated
from langchain_core.callbacks import BaseCallbackManager, Callbacks
from langchain_core.language_models import BaseLanguageModel
from langchain_core.prompts import BasePromptTemplate

from langchain_classic.chains import ReduceDocumentsChain
from langchain_classic.chains.combine_documents.base import BaseCombineDocumentsChain
from langchain_classic.chains.combine_documents.map_reduce import (
    MapReduceDocumentsChain,
)
from langchain_classic.chains.combine_documents.map_rerank import (
    MapRerankDocumentsChain,
)
from langchain_classic.chains.combine_documents.refine import RefineDocumentsChain
from langchain_classic.chains.combine_documents.stuff import StuffDocumentsChain
from langchain_classic.chains.llm import LLMChain
from langchain_classic.chains.question_answering import (
    map_reduce_prompt,
    refine_prompts,
    stuff_prompt,
)
from langchain_classic.chains.question_answering.map_rerank_prompt import (
    PROMPT as MAP_RERANK_PROMPT,
)


class LoadingCallable(Protocol):
    """Interface for loading the combine documents chain."""

    def __call__(
        self,
        llm: BaseLanguageModel,
        **kwargs: Any,
    ) -> BaseCombineDocumentsChain:
        """Callable to load the combine documents chain."""


def _load_map_rerank_chain(
    llm: BaseLanguageModel,
    *,
    prompt: BasePromptTemplate = MAP_RERANK_PROMPT,
    verbose: bool = False,
    document_variable_name: str = "context",
    rank_key: str = "score",
    answer_key: str = "answer",
    callback_manager: BaseCallbackManager | None = None,
    callbacks: Callbacks = None,
    **kwargs: Any,
) -> MapRerankDocumentsChain:
    llm_chain = LLMChain(
        llm=llm,
        prompt=prompt,
        verbose=verbose,
        callback_manager=callback_manager,
        callbacks=callbacks,
// ... (225 more lines)

Domain

Subdomains

Functions

Classes

Dependencies

  • collections.abc
  • langchain_classic.chains
  • langchain_classic.chains.combine_documents.base
  • langchain_classic.chains.combine_documents.map_reduce
  • langchain_classic.chains.combine_documents.map_rerank
  • langchain_classic.chains.combine_documents.refine
  • langchain_classic.chains.combine_documents.stuff
  • langchain_classic.chains.llm
  • langchain_classic.chains.question_answering
  • langchain_classic.chains.question_answering.map_rerank_prompt
  • langchain_core._api
  • langchain_core.callbacks
  • langchain_core.language_models
  • langchain_core.prompts
  • typing

Source

Frequently Asked Questions

What does chain.py do?
chain.py is a source file in the langchain codebase, written in python. It belongs to the CoreAbstractions domain, RunnableInterface subdomain.
What functions are defined in chain.py?
chain.py defines 5 function(s): _load_map_reduce_chain, _load_map_rerank_chain, _load_refine_chain, _load_stuff_chain, load_qa_chain.
What does chain.py depend on?
chain.py imports 15 module(s): collections.abc, langchain_classic.chains, langchain_classic.chains.combine_documents.base, langchain_classic.chains.combine_documents.map_reduce, langchain_classic.chains.combine_documents.map_rerank, langchain_classic.chains.combine_documents.refine, langchain_classic.chains.combine_documents.stuff, langchain_classic.chains.llm, and 7 more.
Where is chain.py in the architecture?
chain.py is located at libs/langchain/langchain_classic/chains/question_answering/chain.py (domain: CoreAbstractions, subdomain: RunnableInterface, directory: libs/langchain/langchain_classic/chains/question_answering).

Analyze Your Own Codebase

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

Try Supermodel Free