
    3fi                         d Z ddlmZ ddlmZ ddlmZmZmZ ddl	m
Z
mZ ddlmZ ddlmZ ddlmZ dd	lmZ  ed
dd       G d de             Zy)z6Chain that carries on a conversation and calls an LLM.    )
deprecated)BasePromptTemplate)
ConfigDictFieldmodel_validator)Selfoverride)
BaseMemory)PROMPT)LLMChain)ConversationBufferMemoryz0.2.7z;langchain_core.runnables.history.RunnableWithMessageHistoryz1.0)sincealternativeremovalc                       e Zd ZU dZ ee      Zeed<   	 e	Z
eed<   	 dZeed<   dZeed<    ed	d
      Zeedefd              Zedee   fd       Z ed      defd       Zy)ConversationChaina  Chain to have a conversation and load context from memory.

    This class is deprecated in favor of `RunnableWithMessageHistory`. Please refer
    to this tutorial for more detail: https://python.langchain.com/docs/tutorials/chatbot/

    `RunnableWithMessageHistory` offers several benefits, including:

    - Stream, batch, and async support;
    - More flexible memory handling, including the ability to manage memory
        outside the chain;
    - Support for multiple threads.

    Below is a minimal implementation, analogous to using `ConversationChain` with
    the default `ConversationBufferMemory`:

        ```python
        from langchain_core.chat_history import InMemoryChatMessageHistory
        from langchain_core.runnables.history import RunnableWithMessageHistory
        from langchain_openai import ChatOpenAI


        store = {}  # memory is maintained outside the chain


        def get_session_history(session_id: str) -> InMemoryChatMessageHistory:
            if session_id not in store:
                store[session_id] = InMemoryChatMessageHistory()
            return store[session_id]


        model = ChatOpenAI(model="gpt-3.5-turbo-0125")

        chain = RunnableWithMessageHistory(model, get_session_history)
        chain.invoke(
            "Hi I'm Bob.",
            config={"configurable": {"session_id": "1"}},
        )  # session_id determines thread
        ```

    Memory objects can also be incorporated into the `get_session_history` callable:

        ```python
        from langchain_classic.memory import ConversationBufferWindowMemory
        from langchain_core.chat_history import InMemoryChatMessageHistory
        from langchain_core.runnables.history import RunnableWithMessageHistory
        from langchain_openai import ChatOpenAI


        store = {}  # memory is maintained outside the chain


        def get_session_history(session_id: str) -> InMemoryChatMessageHistory:
            if session_id not in store:
                store[session_id] = InMemoryChatMessageHistory()
                return store[session_id]

            memory = ConversationBufferWindowMemory(
                chat_memory=store[session_id],
                k=3,
                return_messages=True,
            )
            assert len(memory.memory_variables) == 1
            key = memory.memory_variables[0]
            messages = memory.load_memory_variables({})[key]
            store[session_id] = InMemoryChatMessageHistory(messages=messages)
            return store[session_id]


        model = ChatOpenAI(model="gpt-3.5-turbo-0125")

        chain = RunnableWithMessageHistory(model, get_session_history)
        chain.invoke(
            "Hi I'm Bob.",
            config={"configurable": {"session_id": "1"}},
        )  # session_id determines thread
        ```

    Example:
        ```python
        from langchain_classic.chains import ConversationChain
        from langchain_openai import OpenAI

        conversation = ConversationChain(llm=OpenAI())
        ```
    )default_factorymemorypromptinput	input_keyresponse
output_keyTforbid)arbitrary_types_allowedextrareturnc                      y)NF )clss    h/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_classic/chains/conversation/base.pyis_lc_serializablez$ConversationChain.is_lc_serializablew   s         c                     | j                   gS )z5Use this since so some prompt vars come from history.)r   )selfs    r!   
input_keyszConversationChain.input_keys|   s     r#   after)modec                    | j                   j                  }| j                  }||v rd| d| d}t        |      | j                  j
                  }g ||}t        |      t        |      k7  rd| d| d| d}t        |      | S )z4Validate that prompt input variables are consistent.zThe input key z$ was also found in the memory keys (z+) - please provide keys that don't overlap.z:Got unexpected prompt input variables. The prompt expects z
, but got z as inputs from memory, and z as the normal input key.)r   memory_variablesr   
ValueErrorr   input_variablesset)r%   memory_keysr   msgprompt_variablesexpected_keyss         r!   validate_prompt_input_variablesz1ConversationChain.validate_prompt_input_variables   s     kk22NN	#  ,= KM  S/!;;661+1y1}%5!66L#$J{m <(k)BD 
 S/!r#   N)__name__
__module____qualname____doc__r   r   r   r
   __annotations__r   r   r   r   strr   r   model_configclassmethodr	   boolr"   propertylistr&   r   r   r2   r   r#   r!   r   r      s    Tl /GHFJH!'F'-Is J  $L
 4     DI     '"  #r#   r   N)r6   langchain_core._apir   langchain_core.promptsr   pydanticr   r   r   typing_extensionsr   r	   langchain_classic.base_memoryr
   ,langchain_classic.chains.conversation.promptr   langchain_classic.chains.llmr   langchain_classic.memory.bufferr   r   r   r#   r!   <module>rF      sO    < * 5 7 7 , 4 ? 1 D 
M
B B
Br#   