Azure AI 服务工具包
此工具包用于与Azure AI Services API
交互以实现一些多模态功能。
目前此工具包捆绑了五个工具
- AzureAiServicesImageAnalysisTool:用于从图像中提取标题、对象、标签和文本。
- AzureAiServicesDocumentIntelligenceTool:用于从文档中提取文本、表格和键值对。
- AzureAiServicesSpeechToTextTool:用于将语音转录为文本。
- AzureAiServicesTextToSpeechTool:用于将文本合成语音。
- AzureAiServicesTextAnalyticsForHealthTool:用于提取医疗保健实体。
首先,您需要设置 Azure 帐户并创建 AI 服务资源。您可以按照此处的说明创建资源。
然后,您需要获取资源的终结点、密钥和区域,并将它们设置为环境变量。您可以在资源的“密钥和终结点”页面中找到它们。
%pip install --upgrade --quiet azure-ai-formrecognizer > /dev/null
%pip install --upgrade --quiet azure-cognitiveservices-speech > /dev/null
%pip install --upgrade --quiet azure-ai-textanalytics > /dev/null
%pip install --upgrade --quiet azure-ai-vision-imageanalysis > /dev/null
%pip install -qU langchain-community
import os
os.environ["OPENAI_API_KEY"] = "sk-"
os.environ["AZURE_AI_SERVICES_KEY"] = ""
os.environ["AZURE_AI_SERVICES_ENDPOINT"] = ""
os.environ["AZURE_AI_SERVICES_REGION"] = ""
创建工具包
from langchain_community.agent_toolkits import AzureAiServicesToolkit
toolkit = AzureAiServicesToolkit()
API 参考:AzureAiServicesToolkit
[tool.name for tool in toolkit.get_tools()]
['azure_ai_services_document_intelligence',
'azure_ai_services_image_analysis',
'azure_ai_services_speech_to_text',
'azure_ai_services_text_to_speech',
'azure_ai_services_text_analytics_for_health']
在代理中使用
from langchain import hub
from langchain.agents import AgentExecutor, create_structured_chat_agent
from langchain_openai import OpenAI
llm = OpenAI(temperature=0)
tools = toolkit.get_tools()
prompt = hub.pull("hwchase17/structured-chat-agent")
agent = create_structured_chat_agent(llm, tools, prompt)
agent_executor = AgentExecutor(
agent=agent, tools=tools, verbose=True, handle_parsing_errors=True
)
agent_executor.invoke(
{
"input": "What can I make with these ingredients? "
+ "https://images.openai.com/blob/9ad5a2ab-041f-475f-ad6a-b51899c50182/ingredients.png"
}
)
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Thought: I need to use the azure_ai_services_image_analysis tool to analyze the image of the ingredients.
Action:
\`\`\`
{
"action": "azure_ai_services_image_analysis",
"action_input": "https://images.openai.com/blob/9ad5a2ab-041f-475f-ad6a-b51899c50182/ingredients.png"
}
\`\`\`
[0m[33;1m[1;3mCaption: a group of eggs and flour in bowls
Objects: Egg, Egg, Food
Tags: dairy, ingredient, indoor, thickening agent, food, mixing bowl, powder, flour, egg, bowl[0m[32;1m[1;3m
Action:
\`\`\`
{
"action": "Final Answer",
"action_input": "You can make a cake or other baked goods with these ingredients."
}
\`\`\`
[0m
[1m> Finished chain.[0m
{'input': 'What can I make with these ingredients? https://images.openai.com/blob/9ad5a2ab-041f-475f-ad6a-b51899c50182/ingredients.png',
'output': 'You can make a cake or other baked goods with these ingredients.'}
tts_result = agent_executor.invoke({"input": "Tell me a joke and read it out for me."})
audio_file = tts_result.get("output")
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Thought: I can use the Azure AI Services Text to Speech API to convert text to speech.
Action:
\`\`\`
{
"action": "azure_ai_services_text_to_speech",
"action_input": "Why don't scientists trust atoms? Because they make up everything."
}
\`\`\`
[0m[36;1m[1;3m/tmp/tmpe48vamz0.wav[0m
[32;1m[1;3m[0m
[1m> Finished chain.[0m
from IPython import display
audio = display.Audio(data=audio_file, autoplay=True, rate=22050)
display.display(audio)
sample_input = """
The patient is a 54-year-old gentleman with a history of progressive angina over the past several months.
The patient had a cardiac catheterization in July of this year revealing total occlusion of the RCA and 50% left main disease ,
with a strong family history of coronary artery disease with a brother dying at the age of 52 from a myocardial infarction and
another brother who is status post coronary artery bypass grafting. The patient had a stress echocardiogram done on July , 2001 ,
which showed no wall motion abnormalities , but this was a difficult study due to body habitus. The patient went for six minutes with
minimal ST depressions in the anterior lateral leads , thought due to fatigue and wrist pain , his anginal equivalent. Due to the patient's
increased symptoms and family history and history left main disease with total occasional of his RCA was referred for revascularization with open heart surgery.
List all the diagnoses.
"""
agent_executor.invoke({"input": sample_input})
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Thought: The patient has a history of progressive angina, a strong family history of coronary artery disease, and a previous cardiac catheterization revealing total occlusion of the RCA and 50% left main disease.
Action:
\`\`\`
{
"action": "azure_ai_services_text_analytics_for_health",
"action_input": "The patient is a 54-year-old gentleman with a history of progressive angina over the past several months. The patient had a cardiac catheterization in July of this year revealing total occlusion of the RCA and 50% left main disease, with a strong family history of coronary artery disease with a brother dying at the age of 52 from a myocardial infarction and another brother who is status post coronary artery bypass grafting. The patient had a stress echocardiogram done on July, 2001, which showed no wall motion abnormalities, but this was a difficult study due to body habitus. The patient went for six minutes with minimal ST depressions in the anterior lateral leads, thought due to fatigue and wrist pain, his anginal equivalent. Due to the patient's increased symptoms and family history and history left main disease with total occasional of his RCA was referred for revascularization with open heart surgery."
[0m[33;1m[1;3mThe text contains the following healthcare entities: 54-year-old is a healthcare entity of type Age, gentleman is a healthcare entity of type Gender, progressive angina is a healthcare entity of type Diagnosis, past several months is a healthcare entity of type Time, cardiac catheterization is a healthcare entity of type ExaminationName, July of this year is a healthcare entity of type Time, total is a healthcare entity of type ConditionQualifier, occlusion is a healthcare entity of type SymptomOrSign, RCA is a healthcare entity of type BodyStructure, 50 is a healthcare entity of type MeasurementValue, % is a healthcare entity of type MeasurementUnit, left main disease is a healthcare entity of type Diagnosis, family is a healthcare entity of type FamilyRelation, coronary artery disease is a healthcare entity of type Diagnosis, brother is a healthcare entity of type FamilyRelation, dying is a healthcare entity of type Diagnosis, 52 is a healthcare entity of type Age, myocardial infarction is a healthcare entity of type Diagnosis, brother is a healthcare entity of type FamilyRelation, coronary artery bypass grafting is a healthcare entity of type TreatmentName, stress echocardiogram is a healthcare entity of type ExaminationName, July, 2001 is a healthcare entity of type Time, wall motion abnormalities is a healthcare entity of type SymptomOrSign, body habitus is a healthcare entity of type SymptomOrSign, six minutes is a healthcare entity of type Time, minimal is a healthcare entity of type ConditionQualifier, ST depressions in the anterior lateral leads is a healthcare entity of type SymptomOrSign, fatigue is a healthcare entity of type SymptomOrSign, wrist pain is a healthcare entity of type SymptomOrSign, anginal is a healthcare entity of type SymptomOrSign, increased is a healthcare entity of type Course, symptoms is a healthcare entity of type SymptomOrSign, family is a healthcare entity of type FamilyRelation, left main disease is a healthcare entity of type Diagnosis, occasional is a healthcare entity of type Course, RCA is a healthcare entity of type BodyStructure, revascularization is a healthcare entity of type TreatmentName, open heart surgery is a healthcare entity of type TreatmentName[0m[32;1m[1;3m
Action:
\`\`\`
{
"action": "Final Answer",
"action_input": "The patient's diagnoses include progressive angina, total occlusion of the RCA, 50% left main disease, coronary artery disease, myocardial infarction, and a family history of coronary artery disease."
}
[0m
[1m> Finished chain.[0m
{'input': "\nThe patient is a 54-year-old gentleman with a history of progressive angina over the past several months.\nThe patient had a cardiac catheterization in July of this year revealing total occlusion of the RCA and 50% left main disease ,\nwith a strong family history of coronary artery disease with a brother dying at the age of 52 from a myocardial infarction and\nanother brother who is status post coronary artery bypass grafting. The patient had a stress echocardiogram done on July , 2001 ,\nwhich showed no wall motion abnormalities , but this was a difficult study due to body habitus. The patient went for six minutes with\nminimal ST depressions in the anterior lateral leads , thought due to fatigue and wrist pain , his anginal equivalent. Due to the patient's\nincreased symptoms and family history and history left main disease with total occasional of his RCA was referred for revascularization with open heart surgery.\n\nList all the diagnoses.\n",
'output': "The patient's diagnoses include progressive angina, total occlusion of the RCA, 50% left main disease, coronary artery disease, myocardial infarction, and a family history of coronary artery disease."}