ChatGroq

这将帮助您开始使用 Groq 的聊天模型。有关所有 ChatGroq 功能和配置的详细文档，请参阅API 参考。要查看所有 Groq 模型的列表，请访问此链接。

概述

集成详情

类别	包	本地	可序列化	JS 支持	包下载量	最新包版本
ChatGroq	langchain-groq	❌	测试版	✅

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 Groq 模型，您需要创建一个 Groq 账户，获取 API 密钥，并安装 langchain-groq 集成包。

凭证

前往 Groq 控制台注册 Groq 并生成 API 密钥。完成后，设置 GROQ_API_KEY 环境变量。

import getpass
import os

if "GROQ_API_KEY" not in os.environ:
    os.environ["GROQ_API_KEY"] = getpass.getpass("Enter your Groq 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_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"

安装

LangChain Groq 集成位于 langchain-groq 包中。

%pip install -qU langchain-groq

实例化

现在我们可以实例化模型对象并生成聊天补全。

推理格式

如果您选择设置 reasoning_format，您必须确保您使用的模型支持它。您可以在 Groq 文档中找到支持模型的列表。

from langchain_groq import ChatGroq

llm = ChatGroq(
    model="deepseek-r1-distill-llama-70b",
    temperature=0,
    max_tokens=None,
    reasoning_format="parsed",
    timeout=None,
    max_retries=2,
    # other params...
)

API 参考：ChatGroq

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

AIMessage(content="J'aime la programmation.", additional_kwargs={'reasoning_content': 'Okay, so I need to translate the sentence "I love programming." into French. Let me think about how to approach this. \n\nFirst, I know that "I" in French is "Je." That\'s straightforward. Now, the verb "love" in French is "aime" when referring to oneself. So, "I love" would be "J\'aime." \n\nNext, the word "programming." In French, programming is "la programmation." But wait, in French, when you talk about loving an activity, you often use the definite article. So, it would be "la programmation." \n\nPutting it all together, "I love programming" becomes "J\'aime la programmation." That sounds right. I think that\'s the correct translation. \n\nI should double-check to make sure I\'m not missing anything. Maybe I can think of similar phrases. For example, "I love reading" is "J\'aime lire," but when it\'s a noun, like "I love music," it\'s "J\'aime la musique." So, yes, using "la programmation" makes sense here. \n\nI don\'t think I need to change anything else. The sentence structure in French is Subject-Verb-Object, just like in English, so "J\'aime la programmation" should be correct. \n\nI guess another way to say it could be "J\'adore la programmation," using "adore" instead of "aime," but "aime" is more commonly used in this context. So, sticking with "J\'aime la programmation" is probably the best choice.\n'}, response_metadata={'token_usage': {'completion_tokens': 346, 'prompt_tokens': 23, 'total_tokens': 369, 'completion_time': 1.447541218, 'prompt_time': 0.000983386, 'queue_time': 0.009673684, 'total_time': 1.448524604}, 'model_name': 'deepseek-r1-distill-llama-70b', 'system_fingerprint': 'fp_e98d30d035', 'finish_reason': 'stop', 'logprobs': None}, id='run--5679ae4f-f4e8-4931-bcd5-7304223832c0-0', usage_metadata={'input_tokens': 23, 'output_tokens': 346, 'total_tokens': 369})

print(ai_msg.content)

J'aime 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.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

AIMessage(content='The translation of "I love programming" into German is "Ich liebe das Programmieren." \n\n**Step-by-Step Explanation:**\n\n1. **Subject Pronoun:** "I" translates to "Ich."\n2. **Verb Conjugation:** "Love" becomes "liebe" (first person singular of "lieben").\n3. **Gerund Translation:** "Programming" is translated using the infinitive noun "Programmieren."\n4. **Article Usage:** The definite article "das" is included before the infinitive noun for natural phrasing.\n\nThus, the complete and natural translation is:\n\n**Ich liebe das Programmieren.**', additional_kwargs={'reasoning_content': 'Okay, so I need to translate the sentence "I love programming." into German. Hmm, let\'s break this down. \n\nFirst, "I" in German is "Ich." That\'s straightforward. Now, "love" translates to "liebe." Wait, but in German, the verb conjugation depends on the subject. Since it\'s "I," the verb would be "liebe" because "lieben" is the infinitive, and for first person singular, it\'s "liebe." \n\nNext, "programming" is a gerund in English, which is the -ing form. In German, the equivalent would be the present participle, which is "programmierend." But wait, sometimes in German, they use the noun form instead of the gerund. So maybe it\'s better to say "Ich liebe das Programmieren." Because "Programmieren" is the infinitive noun form, and it\'s commonly used in such contexts. \n\nLet me think again. "I love programming" could be directly translated as "Ich liebe Programmieren," but I\'ve heard both "Programmieren" and "programmierend" used. However, "Ich liebe das Programmieren" sounds more natural because it uses the definite article "das" before the infinitive noun. \n\nAlternatively, if I use "programmieren" without the article, it\'s still correct but maybe a bit less common. So, to make it sound more natural and fluent, including the article "das" would be better. \n\nTherefore, the correct translation should be "Ich liebe das Programmieren." That makes sense because it\'s similar to saying "I love (the act of) programming." \n\nI think that\'s the most accurate and natural way to express it in German. Let me double-check some examples. If someone says "I love reading," in German it\'s "Ich liebe das Lesen." So yes, using "das" before the infinitive noun is the correct structure. \n\nSo, putting it all together, "I love programming" becomes "Ich liebe das Programmieren." That should be the right translation.\n'}, response_metadata={'token_usage': {'completion_tokens': 569, 'prompt_tokens': 18, 'total_tokens': 587, 'completion_time': 2.511255685, 'prompt_time': 0.001466702, 'queue_time': 0.009628211, 'total_time': 2.512722387}, 'model_name': 'deepseek-r1-distill-llama-70b', 'system_fingerprint': 'fp_87eae35036', 'finish_reason': 'stop', 'logprobs': None}, id='run--4d5ee86d-5eec-495c-9c4e-261526cf6e3d-0', usage_metadata={'input_tokens': 18, 'output_tokens': 569, 'total_tokens': 587})

API 参考

有关所有 ChatGroq 功能和配置的详细文档，请参阅API 参考。

相关

• 聊天模型概念指南
• 聊天模型操作指南