In the fast-paced world of cloud computing, the way we access and manage computing resources has transformed, and the integration of graphics processing units (GPUs) into cloud computing has significantly enhanced this revolution. GPUs are crucial for graphics-intensive workloads because they accelerate tasks that demand massive parallel processing power. They provide significant benefits across various sectors: for example, data scientists can expedite complex computations and large-scale data analysis, game designers can render high-quality graphics in real-time, and creative professionals enjoy faster processing speeds for tasks such as 3D modeling and video rendering.

We are happy to announce that GPU-enabled Cloud PCs are now generally available for Windows 365 Enterprise and Frontline editions. Users can now handle advanced workloads—that were traditionally limited by the constraints of local hardware—in the cloud with increased speed and efficiency. Sensitive data and high-value digital assets can be processed and stored securely in the cloud, mitigating the risks associated with local storage.

“The Windows 365 GPU Standard license provides an all-in-one, scalable desktop virtualization solution that was easy to scale, had low management overheads, and provided reliable access to GPU capabilities for advanced computational functions.”  –Peter Short, General Manager, Innovation and Technical Services, Penten

The following configurations are available today through Windows 365 Enterprise and Frontline editions:

Windows 365 GPU Standard
Windows 365 GPU Super
Windows 365 GPU Max

These GPU licenses can be purchased and assigned just like other Windows 365 licenses.

FAQs

Which editions of Windows 365 support GPU-enabled Cloud PCs?
GPU-enabled Cloud PCs are generally available for Windows 365 Enterprise and Frontline editions.

Is a GPU being offered as an add-on to existing Cloud PC licenses?
No, GPU capabilities are being offered as standalone GPU-enabled Cloud PCs.

Can a GPU be dynamically added and removed from the configuration that has already been enabled?
No, GPU-enabled Cloud PCs cannot be dynamically added and removed from the entitled configuration.

Are GPU-enabled Cloud PC trials available?
Trial subscriptions are available for qualified organizations and are subject to evaluation and charge. Please contact your Microsoft account representative for more information.

How much do the GPU-enabled Cloud PCs cost?
Please contact your Microsoft account team or Microsoft partner.

Which drivers are supported by GPU-enabled Cloud PCs?
GPU-enabled Cloud PCs will come pre-provisioned with the correct driver needed for the best experience. Approved NVIDIA drivers can be found here, and AMD drivers can be found here. The use of any external drivers, including those from NVIDIA or AMD websites, are not supported.

Can I run AI workloads on GPU-enabled Cloud PCs?
Yes, GPU-enabled Cloud PCs are compatible with and support AI functionalities in software applications like Microsoft Copilot. For AI development or tasks in AI Toolkit for Visual Studio Code that need intensive GPU processing, please use the Max GPU-enabled Cloud PCs.

Want to learn more? Read the Windows 365 GPU-enabled Cloud PC technical documentation.

To learn more about three years of enabling flexible work with Windows 365, read Windows 365 at three years: Customer-centric solutions for security, management, and productivity.

Continue the conversation. Find best practices. Bookmark the Windows 365 Community, then follow us @MSWindowsITPro on X and on LinkedIn.

​Microsoft Tech Community – Latest Blogs –Read More 

I am using Azure OpenAI gpt-35-turbo with langchain’s chains and agents, runnable-parallel methods. The application is for an agricultural usecase (eg: prediction of whether to irrigate or not given the current conditions the crop is in). All sensor and weather inputs are apis. Below is the code snippet for llm call.

“””
Vector DB
“””
db = Chroma(VECTOR_DB_COLLECTION_NAME, embedding_function=embeddings,
persist_directory=”./”+VECTOR_DB_COLLECTION_NAME)
printlg(“[-] Chroma Vector DB “+VECTOR_DB_COLLECTION_NAME+” Loaded”)
printDurFrom(st, “Chroma Loaded”, “lg”)
fs = LocalFileStore(“./”+VECTOR_DB_DOCSTORE_NAME)
store = create_kv_docstore(fs)
retriever = ParentDocumentRetriever(
vectorstore=db,
docstore=store,
child_splitter=child_splitter,
parent_splitter=parent_splitter
)

llm = AzureOpenAI(openai_api_key=return_chat_credentials()[“api-key”],
model_name=”gpt 3.5 turbo”, api_version=”2023-03-15-preview”, base_url=return_chat_credentials()[“api-url”], temperature=0.2)

“””
Tool Functions
“””

def soil_tool(input: str = “”):
“””
NPK-Moisture Extraction tool
“””
dat = fetch_last(“both”)
res = stringify(dat)
return res

def context_tool(input: str = “Best Practices for agriculture”):
“””
Vector Retrieval tool
“””
st = time.time()
context = “”
docs = retriever.invoke(input)
for doc in docs:
# Filter based on threshold score
context += doc.page_content + “n” + “—“*5 + “n”
printDurFrom(st, “Context Extracted”, ‘lg’)
return context

def weather_tool(loc: Literal[“<lat>,<long>”] = “,”):
“””
Weather Data Extraction tool
“””
st = time.time()
context = “”
lat, long = loc.split(“,”)
context = stringify(getRequiredWeatherData(lat, long), “weather”)
printDurFrom(st, “Weather API”, ‘lg’)
return “The Hourly and Daily Weather:n”+str(context)

“””
Tools
“””
context_agent = Tool(name=”Data Tool”,
description=”Use this tool to obtain agriculture related information like irrigation guidelines, fertilization guidelines, crop production guidelines and pest control mechanisms from agricultural books. Input to be passed is ‘<crop-name> <context-that-is-needed>’.”,
func=context_tool)

soil_agent = Tool(name=”Soil Tool”,
description=”Use this agent to get current soil condition data. Input should be ‘both’.”,
func=soil_tool)

weather_agent = Tool(name=”Weather Tool”,
description=”Use this agent to get current weather condition data. Input should be <lat>,<long>.”,
func=weather_tool)

def createAgent(agentName: Literal[“irrigation”, “pesticide”, “fertilization”], agentSpecificPromptPart: str):
“””
Creates KPI specific Agents
“””
st = time.time()
tools = [weather_agent, soil_agent, context_agent]
agent_chain = initialize_agent(
tools=tools, llm=llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=False, max_iterations=15, max_new_tokens=4000, handle_parsing_errors=True
)
printDurFrom(st, agentName.capitalize()+” Agent Initialized”, “lg”)
sysmsg = SystemMessage(content=”You are an Agricultural Assitant. You have access to tools that have all the contextual information and the live data like weather and soil nutrition values you need. Humans don’t have any knowledge about the tools you have access to and you dont have to tell them.”)
hummsg = HumanMessage(content=f”””
Here are the basic information about the crop i’ve sown and the agricultural land you need,
CropName: {Farmer.CROP_TYPE}
Variety: {Farmer.VARIETY}
SoilType: {Farmer.SOIL_TYPE}
Location: {Farmer.LOCATION}
Lat: {Farmer.LAT}
Long: {Farmer.LONG}
SownIn: {Farmer.SOWN_IN}
Phase: {Farmer.STAGE}
TodayDate: {datetime.now().strftime(“%d-%m-%Y”)} [dd-mm-yyyy]

{agentSpecificPromptPart}

Only answer to the given question with its short reason. Do not leave sentences incomplete.
“””)
prompt = ChatPromptTemplate.from_messages([
sysmsg,
hummsg,
])
ret = None
try:
ret = agent_chain.ainvoke, prompt
except:
print(“[!] Error in AgentChain”)
return ret

def chainCall(mode: Literal[“irrigation”, “pesticide”, “fertilization”]):
“””
Creates and returns the specific chains
“””
if mode == “irrigation”:
prmpt = “””
Consider “precipitationProbability” from weather tool and “moisture” from MoistureSensor of soil tool. And answer the following questions.
– Is this the right time to irrigate?
“””
return createAgent(mode, prmpt)

elif mode == “pesticide”:
prmpt = “””
Consider “precipitationProbability” and “windSpeed” from weather tool and “moisture” from MoistureSensor of soil tool. And answer the following questions.
– Is this the right time to spray pesticides?
– Which pesticide to use?
– How much to spray?
“””
return createAgent(mode, prmpt)

elif mode == “fertilization”:
prmpt = “””
Consider “precipitationProbability” and “windSpeed” from weather tool and “moisture” from MoistureSensor and “nitrogen”, “phosporous” and “potassium” from soilProbeSensor of soil tool. And answer the following questions.
– Is this the right time to spray fertilizer?
– Which fertilizer to use?
– How much to spray?
“””
return createAgent(mode, prmpt)
else:
raise ValueError(“Invalid ‘mode'”)

def lambdaFuncGen(model, prompt: str):
“””
Lambda Function Generator for Main Chain
“””
async def lambdaFunc(dummy: None):
“””
Lambda Function that returns result of Agent Chain
“””
return await model(prompt)
return lambdaFunc

async def mainCall(modes: list):
“””
Creates and invokes Main Chain asynchronously
“””
chainDic = {}
prmptDic = {}
for mode in modes:
model, prmpt = chainCall(mode)
chainDic[mode] = RunnableLambda(lambdaFuncGen(model, prmpt))
prmptDic[mode] = prmpt.format()
parallelChain = RunnableParallel(chainDic)
results = await parallelChain.ainvoke(“”)
return results

This code gives very idiotic responses. like “Yes, irrigation must be done. The soil moisture level is 97.5436% and heavy rain is predicted for the next few hours.” or “No, irrigation should not be done. The soil moisture level is 10% which is below required moisture level and the no rain is predicted.”. Out of 10 responses for same inputs only 2 or 3 comes out to be acceptable (sometimes all 10 go wrong).

But when a small prompt with all static duplicate data is passed to the llm through a simple LLMChain the response is very verbose making it feel like quite a general response but it has the correct answers within. Like every single time! ( Really sorry I’m unable to post this code snippet now, I will probably in a future edit or below in the thread as soon as I get access to it ).

My usecase cant be done statically in that simple format. What am I doing wrong here? Is it the prompt? Or Is it the approach? Or Is it the LLM model or its version? ( Then why did the simple prompt did the job :confused: ). It would be really appreciable if someone help me sort this issue out. I’m a rookie here ( both to community and gen ai ). Even small point outs in the right direction will mean a lot. Thanx!!!

​I am using Azure OpenAI gpt-35-turbo with langchain’s chains and agents, runnable-parallel methods. The application is for an agricultural usecase (eg: prediction of whether to irrigate or not given the current conditions the crop is in). All sensor and weather inputs are apis. Below is the code snippet for llm call.”””
Vector DB
“””
db = Chroma(VECTOR_DB_COLLECTION_NAME, embedding_function=embeddings,
persist_directory=”./”+VECTOR_DB_COLLECTION_NAME)
printlg(“[-] Chroma Vector DB “+VECTOR_DB_COLLECTION_NAME+” Loaded”)
printDurFrom(st, “Chroma Loaded”, “lg”)
fs = LocalFileStore(“./”+VECTOR_DB_DOCSTORE_NAME)
store = create_kv_docstore(fs)
retriever = ParentDocumentRetriever(
vectorstore=db,
docstore=store,
child_splitter=child_splitter,
parent_splitter=parent_splitter
)

llm = AzureOpenAI(openai_api_key=return_chat_credentials()[“api-key”],
model_name=”gpt 3.5 turbo”, api_version=”2023-03-15-preview”, base_url=return_chat_credentials()[“api-url”], temperature=0.2)

“””
Tool Functions
“””

def soil_tool(input: str = “”):
“””
NPK-Moisture Extraction tool
“””
dat = fetch_last(“both”)
res = stringify(dat)
return res

def context_tool(input: str = “Best Practices for agriculture”):
“””
Vector Retrieval tool
“””
st = time.time()
context = “”
docs = retriever.invoke(input)
for doc in docs:
# Filter based on threshold score
context += doc.page_content + “n” + “—“*5 + “n”
printDurFrom(st, “Context Extracted”, ‘lg’)
return context

def weather_tool(loc: Literal[“<lat>,<long>”] = “,”):
“””
Weather Data Extraction tool
“””
st = time.time()
context = “”
lat, long = loc.split(“,”)
context = stringify(getRequiredWeatherData(lat, long), “weather”)
printDurFrom(st, “Weather API”, ‘lg’)
return “The Hourly and Daily Weather:n”+str(context)

“””
Tools
“””
context_agent = Tool(name=”Data Tool”,
description=”Use this tool to obtain agriculture related information like irrigation guidelines, fertilization guidelines, crop production guidelines and pest control mechanisms from agricultural books. Input to be passed is ‘<crop-name> <context-that-is-needed>’.”,
func=context_tool)

soil_agent = Tool(name=”Soil Tool”,
description=”Use this agent to get current soil condition data. Input should be ‘both’.”,
func=soil_tool)

weather_agent = Tool(name=”Weather Tool”,
description=”Use this agent to get current weather condition data. Input should be <lat>,<long>.”,
func=weather_tool)

def createAgent(agentName: Literal[“irrigation”, “pesticide”, “fertilization”], agentSpecificPromptPart: str):
“””
Creates KPI specific Agents
“””
st = time.time()
tools = [weather_agent, soil_agent, context_agent]
agent_chain = initialize_agent(
tools=tools, llm=llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=False, max_iterations=15, max_new_tokens=4000, handle_parsing_errors=True
)
printDurFrom(st, agentName.capitalize()+” Agent Initialized”, “lg”)
sysmsg = SystemMessage(content=”You are an Agricultural Assitant. You have access to tools that have all the contextual information and the live data like weather and soil nutrition values you need. Humans don’t have any knowledge about the tools you have access to and you dont have to tell them.”)
hummsg = HumanMessage(content=f”””
Here are the basic information about the crop i’ve sown and the agricultural land you need,
CropName: {Farmer.CROP_TYPE}
Variety: {Farmer.VARIETY}
SoilType: {Farmer.SOIL_TYPE}
Location: {Farmer.LOCATION}
Lat: {Farmer.LAT}
Long: {Farmer.LONG}
SownIn: {Farmer.SOWN_IN}
Phase: {Farmer.STAGE}
TodayDate: {datetime.now().strftime(“%d-%m-%Y”)} [dd-mm-yyyy]

{agentSpecificPromptPart}

Only answer to the given question with its short reason. Do not leave sentences incomplete.
“””)
prompt = ChatPromptTemplate.from_messages([
sysmsg,
hummsg,
])
ret = None
try:
ret = agent_chain.ainvoke, prompt
except:
print(“[!] Error in AgentChain”)
return ret

def chainCall(mode: Literal[“irrigation”, “pesticide”, “fertilization”]):
“””
Creates and returns the specific chains
“””
if mode == “irrigation”:
prmpt = “””
Consider “precipitationProbability” from weather tool and “moisture” from MoistureSensor of soil tool. And answer the following questions.
– Is this the right time to irrigate?
“””
return createAgent(mode, prmpt)

elif mode == “pesticide”:
prmpt = “””
Consider “precipitationProbability” and “windSpeed” from weather tool and “moisture” from MoistureSensor of soil tool. And answer the following questions.
– Is this the right time to spray pesticides?
– Which pesticide to use?
– How much to spray?
“””
return createAgent(mode, prmpt)

elif mode == “fertilization”:
prmpt = “””
Consider “precipitationProbability” and “windSpeed” from weather tool and “moisture” from MoistureSensor and “nitrogen”, “phosporous” and “potassium” from soilProbeSensor of soil tool. And answer the following questions.
– Is this the right time to spray fertilizer?
– Which fertilizer to use?
– How much to spray?
“””
return createAgent(mode, prmpt)
else:
raise ValueError(“Invalid ‘mode'”)

def lambdaFuncGen(model, prompt: str):
“””
Lambda Function Generator for Main Chain
“””
async def lambdaFunc(dummy: None):
“””
Lambda Function that returns result of Agent Chain
“””
return await model(prompt)
return lambdaFunc

async def mainCall(modes: list):
“””
Creates and invokes Main Chain asynchronously
“””
chainDic = {}
prmptDic = {}
for mode in modes:
model, prmpt = chainCall(mode)
chainDic[mode] = RunnableLambda(lambdaFuncGen(model, prmpt))
prmptDic[mode] = prmpt.format()
parallelChain = RunnableParallel(chainDic)
results = await parallelChain.ainvoke(“”)
return resultsThis code gives very idiotic responses. like “Yes, irrigation must be done. The soil moisture level is 97.5436% and heavy rain is predicted for the next few hours.” or “No, irrigation should not be done. The soil moisture level is 10% which is below required moisture level and the no rain is predicted.”. Out of 10 responses for same inputs only 2 or 3 comes out to be acceptable (sometimes all 10 go wrong).But when a small prompt with all static duplicate data is passed to the llm through a simple LLMChain the response is very verbose making it feel like quite a general response but it has the correct answers within. Like every single time! ( Really sorry I’m unable to post this code snippet now, I will probably in a future edit or below in the thread as soon as I get access to it ).My usecase cant be done statically in that simple format. What am I doing wrong here? Is it the prompt? Or Is it the approach? Or Is it the LLM model or its version? ( Then why did the simple prompt did the job :confused: ). It would be really appreciable if someone help me sort this issue out. I’m a rookie here ( both to community and gen ai ). Even small point outs in the right direction will mean a lot. Thanx!!!  Read More

​

Hello everyone, I have encountered a challenge and would appreciate your assistance. I own an external hard drive formatted as NTFS, which functions well on Windows systems. However, upon connecting it to my Mac, I am only able to access files without the ability to modify or write to them.

Upon inspecting the hard drive details using the Mac’s “Disk Utility,” it indicated a read-only status. Despite researching potential solutions online, none have proven effective. Could someone provide a detailed explanation as to why Mac systems are unable to write to NTFS hard drives? Additionally, I am seeking a straightforward method to enable me to use this hard drive seamlessly on my Mac for both reading and writing purposes.

I am grateful for any insights and assistance you can provide.

​Hello everyone, I have encountered a challenge and would appreciate your assistance. I own an external hard drive formatted as NTFS, which functions well on Windows systems. However, upon connecting it to my Mac, I am only able to access files without the ability to modify or write to them. Upon inspecting the hard drive details using the Mac’s “Disk Utility,” it indicated a read-only status. Despite researching potential solutions online, none have proven effective. Could someone provide a detailed explanation as to why Mac systems are unable to write to NTFS hard drives? Additionally, I am seeking a straightforward method to enable me to use this hard drive seamlessly on my Mac for both reading and writing purposes. I am grateful for any insights and assistance you can provide.  Read More

​

I am currently in the process of familiarizing myself with Windows 11, so I kindly ask for your patience. I recently watched an online tutorial that guided me on modifying the default download locations. Although I set my downloads to go to the Desktop, I am still encountering difficulties locating them. It can be quite frustrating when you download something and then frantically search for it, leading to phrases like “where did that go?” Perhaps my reaction isn’t exactly like that, but frustration tends to bring out my expressive side, especially as I get older. Any advice or assistance in this matter would be greatly appreciated. Thank you, Dave.

​I am currently in the process of familiarizing myself with Windows 11, so I kindly ask for your patience. I recently watched an online tutorial that guided me on modifying the default download locations. Although I set my downloads to go to the Desktop, I am still encountering difficulties locating them. It can be quite frustrating when you download something and then frantically search for it, leading to phrases like “where did that go?” Perhaps my reaction isn’t exactly like that, but frustration tends to bring out my expressive side, especially as I get older. Any advice or assistance in this matter would be greatly appreciated. Thank you, Dave.  Read More

​