[如何合并连续相同类型的消息，提升消息处理效率！]-CSDN博客

本文链接：https://blog.csdn.net/sjufgwgfhoia/article/details/142798557

# 如何合并连续相同类型的消息，提升消息处理效率！

## 引言
在消息处理系统中，可能会遇到连续的相同类型的消息，这些称为“消息流”。某些模型可能不支持传递这些连续的消息类型，为了解决这个问题，可以使用`merge_message_runs`工具轻松合并这些消息流。本文将介绍如何使用该工具，并提供实用的代码示例。

## 主要内容
### 为什么需要合并消息流？
在分布式系统或自然语言处理模型中，处理连续的相同类型的消息可能导致性能问题或模型行为异常。通过合并这些消息，可以简化输入，减少处理开销。

### `merge_message_runs` 的基本用法
`merge_message_runs` 能够自动识别并合并连续相同类型的消息。以下是如何在代码中实现这一功能的示例：

```python
from langchain_core.messages import (
    AIMessage,
    HumanMessage,
    SystemMessage,
    merge_message_runs,
)

messages = [
    SystemMessage("you're a good assistant."),
    SystemMessage("you always respond with a joke."),
    HumanMessage([{"type": "text", "text": "i wonder why it's called langchain"}]),
    HumanMessage("and who is harrison chasing anyways"),
    AIMessage(
        'Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'
    ),
    AIMessage("Why, he's probably chasing after the last cup of coffee in the office!"),
]

# 合并相同类型的消息
merged = merge_message_runs(messages)
print("\n\n".join([repr(x) for x in merged]))

使用`+`运算符合并

merge_message_runs 还支持使用+运算符来合并消息流：

messages = (
    SystemMessage("you're a good assistant.")
    + SystemMessage("you always respond with a joke.")
    + HumanMessage([{"type": "text", "text": "i wonder why it's called langchain"}])
    + HumanMessage("and who is harrison chasing anyways")
    + AIMessage(
        'Well, I guess they thought "WordRope" and "SentenceString" just didn\'t have the same ring to it!'
    )
    + AIMessage(
        "Why, he's probably chasing after the last cup of coffee in the office!"
    )
)

merged = merge_message_runs(messages)
print("\n\n".join([repr(x) for x in merged]))