向量记忆¶

注意：此记忆示例已弃用，请使用更新、更灵活的 Memory 类。请参阅最新文档。

向量记忆模块使用向量搜索（由向量数据库支持）根据用户输入检索相关的对话项。

本笔记本演示了如何使用 VectorMemory 类。我们将向您展示如何使用其各个函数。向量记忆的一个典型用例是作为聊天消息的长期记忆存储。您可以

初始化和实验记忆模块¶

在这里，我们初始化一个原始记忆模块，并演示其功能 - 从 ChatMessage 对象存入和检索。

• 请注意，retriever_kwargs 与您在 VectorIndexRetriever 或 index.as_retriever(..) 上指定的参数相同。

输入 [ ]

from llama_index.core.memory import VectorMemory
from llama_index.embeddings.openai import OpenAIEmbedding


vector_memory = VectorMemory.from_defaults(
    vector_store=None,  # leave as None to use default in-memory vector store
    embed_model=OpenAIEmbedding(),
    retriever_kwargs={"similarity_top_k": 1},
)

from llama_index.core.memory import VectorMemory from llama_index.embeddings.openai import OpenAIEmbedding vector_memory = VectorMemory.from_defaults( vector_store=None, # leave as None to use default in-memory vector store embed_model=OpenAIEmbedding(), retriever_kwargs={"similarity_top_k": 1}, )

输入 [ ]

from llama_index.core.llms import ChatMessage

msgs = [
    ChatMessage.from_str("Jerry likes juice.", "user"),
    ChatMessage.from_str("Bob likes burgers.", "user"),
    ChatMessage.from_str("Alice likes apples.", "user"),
]

from llama_index.core.llms import ChatMessage msgs = [ ChatMessage.from_str("Jerry likes juice.", "user"), ChatMessage.from_str("Bob likes burgers.", "user"), ChatMessage.from_str("Alice likes apples.", "user"), ]

输入 [ ]

# load into memory
for m in msgs:
    vector_memory.put(m)

# 加载到记忆中 for m in msgs: vector_memory.put(m)

输入 [ ]

# retrieve from memory
msgs = vector_memory.get("What does Jerry like?")
msgs

# 从记忆中检索 msgs = vector_memory.get("What does Jerry like?") msgs

输出 [ ]

[ChatMessage(role=<MessageRole.USER: 'user'>, content='Jerry likes juice.', additional_kwargs={})]

输入 [ ]

vector_memory.reset()

vector_memory.reset()

现在让我们尝试重置并再次尝试。这次，我们将添加一个助手消息。请注意，用户/助手消息默认是捆绑在一起的。

输入 [ ]

msgs = [
    ChatMessage.from_str("Jerry likes burgers.", "user"),
    ChatMessage.from_str("Bob likes apples.", "user"),
    ChatMessage.from_str("Indeed, Bob likes apples.", "assistant"),
    ChatMessage.from_str("Alice likes juice.", "user"),
]
vector_memory.set(msgs)

msgs = [ ChatMessage.from_str("Jerry likes burgers.", "user"), ChatMessage.from_str("Bob likes apples.", "user"), ChatMessage.from_str("Indeed, Bob likes apples.", "assistant"), ChatMessage.from_str("Alice likes juice.", "user"), ] vector_memory.set(msgs)

输入 [ ]

msgs = vector_memory.get("What does Bob like?")
msgs

msgs = vector_memory.get("What does Bob like?") msgs

输出 [ ]

[ChatMessage(role=<MessageRole.USER: 'user'>, content='Bob likes apples.', additional_kwargs={}),
 ChatMessage(role=<MessageRole.ASSISTANT: 'assistant'>, content='Indeed, Bob likes apples.', additional_kwargs={})]