跳到主要内容
Open In ColabOpen on GitHub

IBM watsonx.ai

WatsonxLLM 是 IBM watsonx.ai 基础模型的封装器。

此示例展示了如何使用 LangChainwatsonx.ai 模型进行通信。

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
WatsonxLLMlangchain-ibmPyPI - DownloadsPyPI - Version

设置

要访问 IBM watsonx.ai 模型,您需要创建一个 IBM watsonx.ai 账户,获取 API 密钥,并安装 langchain-ibm 集成包。

凭证

以下单元格定义了使用 watsonx 基础模型推理所需的凭据。

操作:提供 IBM Cloud 用户 API 密钥。有关详细信息,请参阅管理用户 API 密钥

import os
from getpass import getpass

watsonx_api_key = getpass()
os.environ["WATSONX_APIKEY"] = watsonx_api_key

此外,您还可以将其他密钥作为环境变量传递。

import os

os.environ["WATSONX_URL"] = "your service instance url"
os.environ["WATSONX_TOKEN"] = "your token for accessing the CPD cluster"
os.environ["WATSONX_PASSWORD"] = "your password for accessing the CPD cluster"
os.environ["WATSONX_USERNAME"] = "your username for accessing the CPD cluster"
os.environ["WATSONX_INSTANCE_ID"] = "your instance_id for accessing the CPD cluster"

安装

LangChain IBM 集成位于 langchain-ibm 包中。

!pip install -qU langchain-ibm

实例化

您可能需要为不同的模型或任务调整模型 参数。有关详细信息,请参阅文档

parameters = {
"decoding_method": "sample",
"max_new_tokens": 100,
"min_new_tokens": 1,
"temperature": 0.5,
"top_k": 50,
"top_p": 1,
}

使用先前设置的参数初始化 WatsonxLLM 类。

注意:

  • 为了提供 API 调用的上下文,您必须添加 project_idspace_id。更多信息请参见文档
  • 根据您预置的服务实例所在的区域,使用 此处 描述的其中一个 URL。

在此示例中,我们将使用 project_id 和达拉斯 URL。

您需要指定将用于推理的 model_id。所有可用模型都可以在文档中找到。

from langchain_ibm import WatsonxLLM

watsonx_llm = WatsonxLLM(
model_id="ibm/granite-13b-instruct-v2",
url="https://us-south.ml.cloud.ibm.com",
project_id="PASTE YOUR PROJECT_ID HERE",
params=parameters,
)
API 参考:WatsonxLLM

或者,您可以使用 Cloud Pak for Data 凭据。有关详细信息,请参阅文档

watsonx_llm = WatsonxLLM(
model_id="ibm/granite-13b-instruct-v2",
url="PASTE YOUR URL HERE",
username="PASTE YOUR USERNAME HERE",
password="PASTE YOUR PASSWORD HERE",
instance_id="openshift",
version="4.8",
project_id="PASTE YOUR PROJECT_ID HERE",
params=parameters,
)

除了 model_id,您还可以传递先前已调优模型的 deployment_id。整个模型调优工作流程在使用 TuneExperiment 和 PromptTuner中进行了描述。

watsonx_llm = WatsonxLLM(
deployment_id="PASTE YOUR DEPLOYMENT_ID HERE",
url="https://us-south.ml.cloud.ibm.com",
project_id="PASTE YOUR PROJECT_ID HERE",
params=parameters,
)

对于某些要求,可以选择将 IBM 的 APIClient 对象传递到 WatsonxLLM 类中。

from ibm_watsonx_ai import APIClient

api_client = APIClient(...)

watsonx_llm = WatsonxLLM(
model_id="ibm/granite-13b-instruct-v2",
watsonx_client=api_client,
)

您还可以将 IBM 的 ModelInference 对象传递到 WatsonxLLM 类中。

from ibm_watsonx_ai.foundation_models import ModelInference

model = ModelInference(...)

watsonx_llm = WatsonxLLM(watsonx_model=model)

调用

要获取补全,您可以直接使用字符串提示调用模型。

# Calling a single prompt

watsonx_llm.invoke("Who is man's best friend?")
"Man's best friend is his dog. Dogs are man's best friend because they are always there for you, they never judge you, and they love you unconditionally. Dogs are also great companions and can help reduce stress levels. "
# Calling multiple prompts

watsonx_llm.generate(
[
"The fastest dog in the world?",
"Describe your chosen dog breed",
]
)
LLMResult(generations=[[Generation(text='The fastest dog in the world is the greyhound. Greyhounds can run up to 45 mph, which is about the same speed as a Usain Bolt.', generation_info={'finish_reason': 'eos_token'})], [Generation(text='The Labrador Retriever is a breed of retriever that was bred for hunting. They are a very smart breed and are very easy to train. They are also very loyal and will make great companions. ', generation_info={'finish_reason': 'eos_token'})]], llm_output={'token_usage': {'generated_token_count': 82, 'input_token_count': 13}, 'model_id': 'ibm/granite-13b-instruct-v2', 'deployment_id': None}, run=[RunInfo(run_id=UUID('750b8a0f-8846-456d-93d0-e039e95b1276')), RunInfo(run_id=UUID('aa4c2a1c-5b08-4fcf-87aa-50228de46db5'))], type='LLMResult')

流式传输模型输出

您可以流式传输模型输出。

for chunk in watsonx_llm.stream(
"Describe your favorite breed of dog and why it is your favorite."
):
print(chunk, end="")
My favorite breed of dog is a Labrador Retriever. They are my favorite breed because they are my favorite color, yellow. They are also very smart and easy to train.

链式调用

创建 PromptTemplate 对象,这些对象将负责生成随机问题。

from langchain_core.prompts import PromptTemplate

template = "Generate a random question about {topic}: Question: "

prompt = PromptTemplate.from_template(template)
API 参考:PromptTemplate

提供一个主题并运行链。

llm_chain = prompt | watsonx_llm

topic = "dog"

llm_chain.invoke(topic)
'What is the origin of the name "Pomeranian"?'

API 参考

有关 WatsonxLLM 所有功能和配置的详细文档,请查阅 API 参考