跳到主要内容
Open In ColabOpen on GitHub

ChatGoodfire

这将帮助您开始使用 Goodfire 聊天模型。有关所有 ChatGoodfire 功能和配置的详细文档,请访问 PyPI 项目页面,或直接查阅 Goodfire SDK 文档。所有 Goodfire 特定功能(例如 SAE 功能、变体等)均可通过主 goodfire 包获取。此集成是 Goodfire SDK 的一个包装器。

概述

集成详情

类别本地可序列化JS 支持包下载量最新包版本
ChatGoodfirelangchain-goodfirePyPI - DownloadsPyPI - Version

模型特性

工具调用结构化输出JSON 模式图片输入音频输入视频输入逐令牌流式传输原生异步令牌使用量对数概率

设置

要访问 Goodfire 模型,您需要创建一个 Goodfire 账户,获取 API 密钥,并安装 langchain-goodfire 集成包。

凭证

请访问 Goodfire 设置 以注册 Goodfire 并生成 API 密钥。完成后,请设置 GOODFIRE_API_KEY 环境变量。

import getpass
import os

if not os.getenv("GOODFIRE_API_KEY"):
os.environ["GOODFIRE_API_KEY"] = getpass.getpass("Enter your Goodfire API key: ")

要启用模型调用的自动跟踪,请设置您的 LangSmith API 密钥

# os.environ["LANGSMITH_TRACING"] = "true"
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")

安装

LangChain Goodfire 集成位于 langchain-goodfire 包中

%pip install -qU langchain-goodfire
Note: you may need to restart the kernel to use updated packages.

实例化

现在我们可以实例化模型对象并生成聊天补全

import goodfire
from langchain_goodfire import ChatGoodfire

base_variant = goodfire.Variant("meta-llama/Llama-3.3-70B-Instruct")

llm = ChatGoodfire(
model=base_variant,
temperature=0,
max_completion_tokens=1000,
seed=42,
)
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.

调用

messages = [
(
"system",
"You are a helpful assistant that translates English to French. Translate the user sentence.",
),
("human", "I love programming."),
]
ai_msg = await llm.ainvoke(messages)
ai_msg
AIMessage(content="J'adore la programmation.", additional_kwargs={}, response_metadata={}, id='run-8d43cf35-bce8-4827-8935-c64f8fb78cd0-0', usage_metadata={'input_tokens': 51, 'output_tokens': 39, 'total_tokens': 90})
print(ai_msg.content)
J'adore la programmation.

链式调用

我们可以像这样将模型与提示模板链式连接起来

from langchain_core.prompts import ChatPromptTemplate

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

chain = prompt | llm
await chain.ainvoke(
{
"input_language": "English",
"output_language": "German",
"input": "I love programming.",
}
)
API 参考:ChatPromptTemplate
AIMessage(content='Ich liebe das Programmieren. How can I help you with programming today?', additional_kwargs={}, response_metadata={}, id='run-03d1a585-8234-46f1-a8df-bf9143fe3309-0', usage_metadata={'input_tokens': 46, 'output_tokens': 46, 'total_tokens': 92})

Goodfire 特定功能

要使用 Goodfire 特定功能,例如 SAE 功能和变体,您可以直接使用 goodfire 包。

client = goodfire.Client(api_key=os.environ["GOODFIRE_API_KEY"])

pirate_features = client.features.search(
"assistant should roleplay as a pirate", base_variant
)
pirate_features
FeatureGroup([
0: "The assistant should adopt the persona of a pirate",
1: "The assistant should roleplay as a pirate",
2: "The assistant should engage with pirate-themed content or roleplay as a pirate",
3: "The assistant should roleplay as a character",
4: "The assistant should roleplay as a specific character",
5: "The assistant should roleplay as a game character or NPC",
6: "The assistant should roleplay as a human character",
7: "Requests for the assistant to roleplay or pretend to be something else",
8: "Requests for the assistant to roleplay or pretend to be something",
9: "The assistant is being assigned a role or persona to roleplay"
])
pirate_variant = goodfire.Variant("meta-llama/Llama-3.3-70B-Instruct")

pirate_variant.set(pirate_features[0], 0.4)
pirate_variant.set(pirate_features[1], 0.3)

await llm.ainvoke("Tell me a joke", model=pirate_variant)
AIMessage(content='Why did the scarecrow win an award? Because he was outstanding in his field! Arrr! Hope that made ye laugh, matey!', additional_kwargs={}, response_metadata={}, id='run-7d8bd30f-7f80-41cb-bdb6-25c29c22a7ce-0', usage_metadata={'input_tokens': 35, 'output_tokens': 60, 'total_tokens': 95})

API 参考

有关所有 ChatGoodfire 功能和配置的详细文档,请查阅 API 参考