Lab files for Azure AI Language modules
Home Page: https://microsoftlearning.github.io/mslearn-ai-language/
License: MIT License
In several parts of the instructions, the folder referenced is text-analytics, when the folder is actually called text-analysis. Other parts of the instructions refer to the correct name.
Learner had to make the entity as prebuild Geography.Location for it to work. Just with the three examples given it was not consistent identifying it.
Hello, How do I solve these issues:
1)Problem in .py file: Rename this local variable "detectedLanguage" to match the regular expression ^[a-z][a-z0-9]*$.
2)I have checked the key/endpoint. When I attempt to dectect language by reruning the .py file in the Terminal, this error appears:
(401) Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.Code: 401 Message: Access denied due to invalid subscription key or wrong API endpoint. Make sure to provide a valid key for an active subscription and use a correct regional API endpoint for your resource.
Recently started using the repo and notice each time i clone it to my local machine, i start seeing a lot of errors for the Microsoft C# extension.
Here are just some. Literally every project for C# won't load.
c:\Users\ssgil\melearnai\mslearn-ai-language\Labfiles\07-speech\C-Sharp\speaking-clock\speaking-clock.csproj: Unable to find package Newtonsoft.Json with version (>= 12.0.3)
Hey team,
Seems like the product team now mandates using an Azure Search instance when using custom question answering projects (might be true for other types too). We should add the instructions to create the search instance at the beginning of the project creation.
The Python version of the 01-analyze-text exercise requires the dotenv package which is missing from the base Python environment on Azure.
Error occurs at Step 6 in section "Prepare to use the Azure AI Language SDK for text analytics" of 01-analyze-text.md.
Add pip install python-dotenv to above file.
Description:
The text in step 4 in "Edit the knowledge base" section looks incorrect. While doing the exercise was not able to find the "What is Microsoft certification?" question.
Expected Behavior:
The text should be "What are Microsoft credentials?"
Actual Behavior:
Right now, the text is "What is Microsoft certification?" which is quite confusing.
At my python 3.12 environment, it has occurred this warning lab 03 python:
DeprecationWarning: datetime.datetime.utcnow() is deprecated and scheduled for removal in a future version. Use timezone-aware objects to represent datetimes in UTC: datetime.datetime.now(datetime.UTC).
There are datetime.datetime.utcnow() which is deprecated since python 3.12. See https://docs.python.org/3/library/datetime.html#datetime.datetime.utcnow .
For the lab: 05-custom-entity-recognition/extract-entities.ps1, it seems the request URI and the request is not aligned with the schema. Suggested code is provided as follows:
# Update these with your service and deployment values
$key="<YOUR-KEY>"
$endpoint="<YOUR-ENDPOINT>"
$projectName = "customNERLab"
$deploymentName = "customExtractAds"
$verbose = $false
# Set up headers for API call
$headers = @{}
$headers.add("Ocp-Apim-Subscription-Key", $key)
$headers.add("Content-Type","application/json")
# Get text to extract entities from
$text_file = "test1.txt"
if ($args.count -gt 0)
{
$text_file = $args[0]
}
try {
$contents = get-content $text_file -raw -ErrorAction Stop
}
catch {
Write-Host "`nError reading provided file, please verify file exists`n"
Exit
}
$data = @{
"displayName" = "Extracting entities"
"tasks" = @(
@{
"kind" = "CustomEntityRecognition"
"taskName" = "Entity Recognition"
"parameters"= @{
"projectName" = $projectName
"deploymentName" = $deploymentName
}
}
)
"analysisInput" = @{
"documents" = @(
@{
"id" = "document_extractEntities"
"language" = "en-us"
"text" = $contents
}
)
}
} | ConvertTo-Json -Depth 10
# Post text for entity recognition
Write-Host("`nSubmitting entity recognition task`n")
$response = Invoke-WebRequest -Method Post `
-Uri "$($endpoint)language/analyze-text/jobs?api-version=2022-10-01-preview" `
-Headers $headers `
-Body $data
# Output response if desired
if ($verbose) {
Write-Host("`nResponse header:$($response.Headers['Operation-Location'])`n")
}
# Extract the URL from the response
# to call the API to getting the analysis results
$resultUrl = $($response.Headers['Operation-Location'])
# Create the header for the REST GET with only the subscription key
$resultHeaders = @{}
$resultHeaders.Add( "Ocp-Apim-Subscription-Key", $key )
# Get the results
# Continue to request results until the analysis is "succeeded"
Write-Host "Getting results..."
Do {
$result = Invoke-RestMethod -Method Get `
-Uri $resultUrl `
-Headers $resultHeaders | ConvertTo-Json -Depth 10
$analysis = ($result | ConvertFrom-Json)
} while ($analysis.status -ne "succeeded")
Write-Host "...Done`n"
# Access the relevant fields from the analysis
$extraction = $result | ConvertFrom-Json
#$docs = $extraction.tasks.customEntityRecognitionTasks[0].results.documents
$docs = $extraction.tasks.items[0].results.documents
# Output response if desired
if ($verbose) {
Write-Host("GET JSON Response:`n$result`n")
}
for (($idx = 0); $idx -lt $docs.Length; $idx++) {
$item = $docs[$idx]
Write-Host ("Document #", ($idx+1))
$entities = $item.entities
foreach ($entity in $entities) {
Write-Host (" - Entity Category: $($entity.category)")
Write-Host (" - Entity Text: $($entity.text)")
Write-Host (" - Confidence: $($entity.confidenceScore)`n")
}
}
When going through the Add code to the application in Create a Question Answering Solution exercise, the variables ai_project_name and ai_deployment_name don't exist because in the given qna-app.py file the config variables are currently defined as project_name and deployment_name.
https://github.com/MicrosoftLearning/mslearn-ai-language/blob/main/Instructions/Exercises/02-qna.md
Need to update the config variables in the qna-app.py.
For the lab: 04-text-classification/classify-text.ps1, it seems the request URI and the request is not aligned with the schema. Suggested code is provided as follows:
$key="<YOUR-KEY>"
$endpoint="<YOUR-ENDPOINT>"
$projectName = "ClassifyLab"
$deploymentName = "articles"
$verbose = $true
# Set up headers for API call
$headers = @{}
$headers.add("Ocp-Apim-Subscription-Key", $key)
$headers.add("Content-Type","application/json")
# Get text to classify
$text_file = "test1.txt"
if ($args.count -gt 0)
{
$text_file = $args[0]
}
try {
$contents = get-content .\$text_file -raw -ErrorAction Stop
}
catch {
Write-Host "`nError reading provided file, please verify file exists`n"
Exit
}
# Build body of for API call
$data = @{
"displayName" = "Classifying documents"
"tasks" = @(
@{
"kind" = "CustomSingleLabelClassification"
"taskName" = "Single Classification Label"
"parameters"= @{
"projectName" = $projectName
"deploymentName" = $deploymentName
}
}
)
"analysisInput" = @{
"documents" = @(
@{
"id" = "document_singleClassification"
"language" = "en-us"
"text" = $contents
}
)
}
} | ConvertTo-Json -Depth 10
# Post text for classification
Write-Host("`n***Submitting text classification task***")
$response = Invoke-WebRequest -Method Post `
-Uri "$($endpoint)language/analyze-text/jobs?api-version=2022-05-01" `
-Headers $headers `
-Body $data
# Output response if desired
if ($verbose) {
Write-Host("`nResponse header:$($response.Headers['Operation-Location'])`n")
}
# Extract the URL from the response
# to call the API to getting the analysis results
$resultUrl = $($response.Headers['Operation-Location'])
# Create the header for the REST GET with only the subscription key
$resultHeaders = @{}
$resultHeaders.Add( "Ocp-Apim-Subscription-Key", $key )
# Get the results
# Continue to request results until the analysis is "succeeded"
Write-Host "Getting results..."
Do {
$result = Invoke-RestMethod -Method Get `
-Uri $resultUrl `
-Headers $resultHeaders | ConvertTo-Json -Depth 10
$analysis = ($result | ConvertFrom-Json)
} while ($analysis.status -ne "succeeded")
Write-Host "...Done`n"
# Access the relevant fields from the analysis
$classification = $result | ConvertFrom-Json
#$docs = $classification.tasks.customSingleClassificationTasks[0].results.documents
$docs = $classification.tasks.items[0].results.documents
# Output response if desired
if ($verbose) {
Write-Host("GET JSON Response:`n$result`n")
}
# Output response if desired
if ($verbose) {
Write-Host("GET JSON Response:`n$result`n")
}
for (($idx = 0); $idx -lt $docs.Length; $idx++) {
$item = $docs[$idx]
Write-Host ("Document #", ($idx+1))
Write-Host (" - Predicted Category: ", $($item.class.category))
Write-Host (" - Confidence: ",$($item.class.confidenceScore))
}
Can we please have an overview page for the lab exercises like for AI-3004:
We need a nice readable way to share these instructions with learners outside of the lab environment. In know it's there but it would be great to have that link to GitHub pages shared on the landing page.
I believe there's a small typo in the second question on the Knowledge Check of this section.
How might you determine
ofif this word
A screenshot for reference,
https://learn.microsoft.com/en-us/training/modules/analyze-text-ai-language/9-knowledge-check
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.