Llama.cpp

llama.cpp python library is a simple Python bindings for @ggerganov llama.cpp.

This package provides:

Low-level access to C API via ctypes interface.

High-level Python API for text completion

OpenAI-like API

LangChain compatibility

LlamaIndex compatibility

OpenAI compatible web server

Local Copilot replacement

Function Calling support

Vision API support

Multiple Models

概览

集成详情

类	包	本地	可序列化的	JS 支持
ChatLlamaCpp	langchain-community	✅	❌	❌

模型特性

工具调用	结构化输出	JSON模式	图像输入	音频输入	视频输入	令牌级流式传输	原生异步	令牌使用量	对数概率
✅	✅	❌	❌	❌	❌	✅	❌	❌	✅

设置

要开始并使用以下显示的所有功能，我们建议使用经过微调以支持工具调用的模型。

我们将使用 NousResearch 提供的 Hermes-2-Pro-Llama-3-8B-GGUF。

Hermes 2 Pro is an upgraded version of Nous Hermes 2, consisting of an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house. This new version of Hermes maintains its excellent general task and conversation capabilities - but also excels at Function Calling

查看我们关于本地模型的指南以深入了解：

安装

LangChain LlamaCpp 集成位于 langchain-community 和 llama-cpp-python 包中：

%pip install -qU langchain-community llama-cpp-python

实例化

现在我们可以实例化我们的模型对象并生成聊天补全：

# Path to your model weights
local_model = "local/path/to/Hermes-2-Pro-Llama-3-8B-Q8_0.gguf"

import multiprocessing

from langchain_community.chat_models import ChatLlamaCpp

llm = ChatLlamaCpp(
    temperature=0.5,
    model_path=local_model,
    n_ctx=10000,
    n_gpu_layers=8,
    n_batch=300,  # Should be between 1 and n_ctx, consider the amount of VRAM in your GPU.
    max_tokens=512,
    n_threads=multiprocessing.cpu_count() - 1,
    repeat_penalty=1.5,
    top_p=0.5,
    verbose=True,
)

API 参考：ChatLlamaCpp

调用

messages = [
    (
        "system",
        "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ),
    ("human", "I love programming."),
]

ai_msg = llm.invoke(messages)
ai_msg

print(ai_msg.content)

J'aime programmer. (In France, "programming" is often used in its original sense of scheduling or organizing events.) 

If you meant computer-programming: 
Je suis amoureux de la programmation informatique.

(You might also say simply 'programmation', which would be understood as both meanings - depending on context).

链式调用

我们可以像这样将我们的模型与提示模板链接：

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a helpful assistant that translates {input_language} to {output_language}.",
        ),
        ("human", "{input}"),
    ]
)

chain = prompt | llm
chain.invoke(
    {
        "input_language": "English",
        "output_language": "German",
        "input": "I love programming.",
    }
)

API 参考：ChatPromptTemplate

工具调用

首先，它的工作方式与 OpenAI 函数调用大多相同。

OpenAI 提供了一个工具调用（在这里我们交替使用“工具调用”和“函数调用”）API，允许你描述工具及其参数，并让模型返回一个包含要调用的工具及该工具输入的JSON对象。工具调用在构建使用工具的链和代理时非常有用，也更广泛地适用于从模型中获取结构化输出。

通过 ChatLlamaCpp.bind_tools，我们可以轻松地将 Pydantic 类、字典模式、LangChain 工具，甚至函数作为工具传递给模型。在底层，这些会被转换为 OpenAI 工具模式，其格式如下：

{
    "name": "...",
    "description": "...",
    "parameters": {...}  # JSONSchema
}

并在每次模型调用时传入。

然而，它无法自动触发一个函数/工具，我们需要通过指定“工具选择”参数来强制执行。该参数的格式通常如下所述。

{"type": "function", "function": {"name": <<tool_name>>}}.

from langchain_core.tools import tool
from pydantic import BaseModel, Field


class WeatherInput(BaseModel):
    location: str = Field(description="The city and state, e.g. San Francisco, CA")
    unit: str = Field(enum=["celsius", "fahrenheit"])


@tool("get_current_weather", args_schema=WeatherInput)
def get_weather(location: str, unit: str):
    """Get the current weather in a given location"""
    return f"Now the weather in {location} is 22 {unit}"


llm_with_tools = llm.bind_tools(
    tools=[get_weather],
    tool_choice={"type": "function", "function": {"name": "get_current_weather"}},
)

API 参考：工具

ai_msg = llm_with_tools.invoke(
    "what is the weather like in HCMC in celsius",
)

ai_msg.tool_calls

[{'name': 'get_current_weather',
  'args': {'location': 'Ho Chi Minh City', 'unit': 'celsius'},
  'id': 'call__0_get_current_weather_cmpl-394d9943-0a1f-425b-8139-d2826c1431f2'}]

class MagicFunctionInput(BaseModel):
    magic_function_input: int = Field(description="The input value for magic function")


@tool("get_magic_function", args_schema=MagicFunctionInput)
def magic_function(magic_function_input: int):
    """Get the value of magic function for an input."""
    return magic_function_input + 2


llm_with_tools = llm.bind_tools(
    tools=[magic_function],
    tool_choice={"type": "function", "function": {"name": "get_magic_function"}},
)

ai_msg = llm_with_tools.invoke(
    "What is magic function of 3?",
)

ai_msg

ai_msg.tool_calls

[{'name': 'get_magic_function',
  'args': {'magic_function_input': 3},
  'id': 'call__0_get_magic_function_cmpl-cd83a994-b820-4428-957c-48076c68335a'}]

结构化输出

from langchain_core.utils.function_calling import convert_to_openai_tool
from pydantic import BaseModel


class Joke(BaseModel):
    """A setup to a joke and the punchline."""

    setup: str
    punchline: str


dict_schema = convert_to_openai_tool(Joke)
structured_llm = llm.with_structured_output(dict_schema)
result = structured_llm.invoke("Tell me a joke about birds")
result

API 参考：convert_to_openai_tool

result

{'setup': '- Why did the chicken cross the playground?',
 'punchline': '\n\n- To get to its gilded cage on the other side!'}

流式传输

for chunk in llm.stream("what is 25x5"):
    print(chunk.content, end="\n", flush=True)

API 参考

有关ChatLlamaCpp所有功能和配置的详细文档，请访问API参考： https://python.langchain.com/api_reference/community/chat_models/langchain_community.chat_models.llamacpp.ChatLlamaCpp.html

聊天模型概念指南
聊天模型操操作指南

概览​

集成详情​

模型特性​

设置​

安装​

实例化​

调用​

链式调用​

工具调用​