ConversationVectorStoreTokenBufferMemory Class — langchain Architecture

Source Code

libs/langchain/langchain_classic/memory/vectorstore_token_buffer_memory.py lines 37–183

class ConversationVectorStoreTokenBufferMemory(ConversationTokenBufferMemory):
    """Conversation chat memory with token limit and vectordb backing.

    load_memory_variables() will return a dict with the key "history".
    It contains background information retrieved from the vector store
    plus recent lines of the current conversation.

    To help the LLM understand the part of the conversation stored in the
    vectorstore, each interaction is timestamped and the current date and
    time is also provided in the history. A side effect of this is that the
    LLM will have access to the current date and time.

    Initialization arguments:

    This class accepts all the initialization arguments of
    ConversationTokenBufferMemory, such as `llm`. In addition, it
    accepts the following additional arguments

        retriever: (required) A VectorStoreRetriever object to use
            as the vector backing store

        split_chunk_size: (optional, 1000) Token chunk split size
            for long messages generated by the AI

        previous_history_template: (optional) Template used to format
            the contents of the prompt history


    Example using ChromaDB:

    ```python
    from langchain_classic.memory.token_buffer_vectorstore_memory import (
        ConversationVectorStoreTokenBufferMemory,
    )
    from langchain_chroma import Chroma
    from langchain_community.embeddings import HuggingFaceInstructEmbeddings
    from langchain_openai import OpenAI

    embedder = HuggingFaceInstructEmbeddings(
        query_instruction="Represent the query for retrieval: "
    )
    chroma = Chroma(
        collection_name="demo",
        embedding_function=embedder,
        collection_metadata={"hnsw:space": "cosine"},
    )

    retriever = chroma.as_retriever(
        search_type="similarity_score_threshold",
        search_kwargs={
            "k": 5,
            "score_threshold": 0.75,
        },
    )

    conversation_memory = ConversationVectorStoreTokenBufferMemory(
        return_messages=True,
        llm=OpenAI(),
        retriever=retriever,
        max_token_limit=1000,
    )

    conversation_memory.save_context({"Human": "Hi there"}, {"AI": "Nice to meet you!"})
    conversation_memory.save_context(
        {"Human": "Nice day isn't it?"}, {"AI": "I love Wednesdays."}
    )
    conversation_memory.load_memory_variables({"input": "What time is it?"})
    ```
    """

    retriever: VectorStoreRetriever = Field(exclude=True)
    memory_key: str = "history"
    previous_history_template: str = DEFAULT_HISTORY_TEMPLATE
    split_chunk_size: int = 1000

    _memory_retriever: VectorStoreRetrieverMemory | None = PrivateAttr(default=None)
    _timestamps: list[datetime] = PrivateAttr(default_factory=list)

    @property
    def memory_retriever(self) -> VectorStoreRetrieverMemory:
        """Return a memory retriever from the passed retriever object."""