APIChain Class — langchain Architecture

Architecture documentation for the APIChain class in base.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7["APIChain"]
  097a4781_5519_0b5d_6244_98c64eadc0d6["Chain"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|extends| 097a4781_5519_0b5d_6244_98c64eadc0d6
  36d37670_e012_f502_4b19_b9823ce99006["base.py"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|defined in| 36d37670_e012_f502_4b19_b9823ce99006
  6a781639_503d_3e65_71b0_6368c121e3a6["input_keys()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| 6a781639_503d_3e65_71b0_6368c121e3a6
  538dbcbf_eae4_a634_0caa_7467381430fa["output_keys()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| 538dbcbf_eae4_a634_0caa_7467381430fa
  89683746_57f3_bd9f_bd34_28ab7062703b["validate_api_request_prompt()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| 89683746_57f3_bd9f_bd34_28ab7062703b
  d9d8b2a6_d3a3_1e7c_7873_172e347bf89a["validate_limit_to_domains()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| d9d8b2a6_d3a3_1e7c_7873_172e347bf89a
  30f8581a_4237_56c0_3da8_ecfbaf619726["validate_api_answer_prompt()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| 30f8581a_4237_56c0_3da8_ecfbaf619726
  096043c7_109b_33c8_6174_555916dfa31d["_call()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| 096043c7_109b_33c8_6174_555916dfa31d
  5e2c283f_f554_cf10_de83_b02c230485df["_acall()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| 5e2c283f_f554_cf10_de83_b02c230485df
  f522adc6_2d27_7793_1e1a_f61f9d779a68["from_llm_and_api_docs()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| f522adc6_2d27_7793_1e1a_f61f9d779a68
  41e5bb71_4821_21f9_69da_ff2725873641["_chain_type()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| 41e5bb71_4821_21f9_69da_ff2725873641
  d49191ac_6f75_4948_5d94_f94fbe4f03de["__init__()"]
  4c838e88_66f9_ad4e_abe5_a1e623b7b6c7 -->|method| d49191ac_6f75_4948_5d94_f94fbe4f03de

Relationship Graph

Source Code

libs/langchain/langchain_classic/chains/api/base.py lines 68–386

    class APIChain(Chain):
        """Chain that makes API calls and summarizes the responses to answer a question.

        **Security Note**: This API chain uses the requests toolkit
            to make `GET`, `POST`, `PATCH`, `PUT`, and `DELETE` requests to an API.

            Exercise care in who is allowed to use this chain. If exposing
            to end users, consider that users will be able to make arbitrary
            requests on behalf of the server hosting the code. For example,
            users could ask the server to make a request to a private API
            that is only accessible from the server.

            Control access to who can submit issue requests using this toolkit and
            what network access it has.

            See https://docs.langchain.com/oss/python/security-policy for more
            information.

        !!! note
            This class is deprecated. See below for a replacement implementation using
            LangGraph. The benefits of this implementation are:

        - Uses LLM tool calling features to encourage properly-formatted API requests;
        - Support for both token-by-token and step-by-step streaming;
        - Support for checkpointing and memory of chat history;
        - Easier to modify or extend
            (e.g., with additional tools, structured responses, etc.)

        Install LangGraph with:

        ```bash
        pip install -U langgraph
        ```

        ```python
        from typing import Annotated, Sequence
        from typing_extensions import TypedDict

        from langchain_classic.chains.api.prompt import API_URL_PROMPT
        from langchain_community.agent_toolkits.openapi.toolkit import RequestsToolkit
        from langchain_community.utilities.requests import TextRequestsWrapper
        from langchain_core.messages import BaseMessage
        from langchain_core.prompts import ChatPromptTemplate
        from langchain_openai import ChatOpenAI
        from langchain_core.runnables import RunnableConfig
        from langgraph.graph import END, StateGraph
        from langgraph.graph.message import add_messages
        from langgraph.prebuilt.tool_node import ToolNode

        # NOTE: There are inherent risks in giving models discretion
        # to execute real-world actions. We must "opt-in" to these
        # risks by setting allow_dangerous_request=True to use these tools.
        # This can be dangerous for calling unwanted requests. Please make
        # sure your custom OpenAPI spec (yaml) is safe and that permissions
        # associated with the tools are narrowly-scoped.
        ALLOW_DANGEROUS_REQUESTS = True

        # Subset of spec for https://jsonplaceholder.typicode.com
        api_spec = \"\"\"
        openapi: 3.0.0
        info:
          title: JSONPlaceholder API
          version: 1.0.0
        servers:
          - url: https://jsonplaceholder.typicode.com
        paths:
          /posts:
            get:
              summary: Get posts
              parameters: &id001
                - name: _limit
                  in: query
                  required: false
                  schema:
                    type: integer
                  example: 2
                  description: Limit the number of results
        \"\"\"

        model = ChatOpenAI(model="gpt-4o-mini", temperature=0)
        toolkit = RequestsToolkit(