GitHub Copilot
ChatGPT
Claude
Codex CLI
Cursor
opencode
Skill
Text
azure-ai-contentsafety-java
Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm.
Virus-scanned
Reviewed automatically before listing.
Download
microsoft-skills-.github_plugins_azure-sdk-java_skills_azure-ai-contentsafety-java-e58528d.zip · 6 KB
Install
skills CLI
npx skills add https://github.com/microsoft/skills/tree/main/.github/plugins/azure-sdk-java/skills/azure-ai-contentsafety-java
Claude Code
claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install microsoft-skills@llmmart
Git
git clone https://github.com/microsoft/skills.git
The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole microsoft/skills collection as a plugin from our marketplace. Git is the plain clone.
Skill manifest
Azure AI Content Safety SDK for Java
Build content moderation applications using the Azure AI Content Safety SDK for Java.
Installation
<dependency>
<groupId>com.azure</groupId>
<artifactId>azure-ai-contentsafety</artifactId>
<version>1.1.0-beta.1</version>
</dependency>
Client Creation
With API Key
import com.azure.ai.contentsafety.ContentSafetyClient;
import com.azure.ai.contentsafety.ContentSafetyClientBuilder;
import com.azure.ai.contentsafety.BlocklistClient;
import com.azure.ai.contentsafety.BlocklistClientBuilder;
import com.azure.core.credential.KeyCredential;
String endpoint = System.getenv("CONTENT_SAFETY_ENDPOINT");
String key = System.getenv("CONTENT_SAFETY_KEY");
ContentSafetyClient contentSafetyClient = new ContentSafetyClientBuilder()
.credential(new KeyCredential(key))
.endpoint(endpoint)
.buildClient();
BlocklistClient blocklistClient = new BlocklistClientBuilder()
.credential(new KeyCredential(key))
.endpoint(endpoint)
.buildClient();
With DefaultAzureCredential
import com.azure.core.credential.TokenCredential;
import com.azure.identity.AzureIdentityEnvVars;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.azure.identity.ManagedIdentityCredentialBuilder;
TokenCredential credential = new DefaultAzureCredentialBuilder()
.requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS)
.build();
// Or use a specific credential directly in production:
// See https://learn.microsoft.com/java/api/overview/azure/identity-readme?view=azure-java-stable#credential-classes
// TokenCredential credential = new ManagedIdentityCredentialBuilder().build();
ContentSafetyClient client = new ContentSafetyClientBuilder()
.credential(credential)
.endpoint(endpoint)
.buildClient();
Key Concepts
Harm Categories
| Category | Description |
|---|---|
| Hate | Discriminatory language based on identity groups |
| Sexual | Sexual content, relationships, acts |
| Violence | Physical harm, weapons, injury |
| Self-harm | Self-injury, suicide-related content |
Severity Levels
- Text: 0-7 scale (default outputs 0, 2, 4, 6)
- Image: 0, 2, 4, 6 (trimmed scale)
Core Patterns
Analyze Text
import com.azure.ai.contentsafety.models.*;
AnalyzeTextResult result = contentSafetyClient.analyzeText(
new AnalyzeTextOptions("This is text to analyze"));
for (TextCategoriesAnalysis category : result.getCategoriesAnalysis()) {
System.out.printf("Category: %s, Severity: %d%n",
category.getCategory(),
category.getSeverity());
}
Analyze Text with Options
AnalyzeTextOptions options = new AnalyzeTextOptions("Text to analyze")
.setCategories(Arrays.asList(
TextCategory.HATE,
TextCategory.VIOLENCE))
.setOutputType(AnalyzeTextOutputType.EIGHT_SEVERITY_LEVELS);
AnalyzeTextResult result = contentSafetyClient.analyzeText(options);
Analyze Text with Blocklist
AnalyzeTextOptions options = new AnalyzeTextOptions("I h*te you and want to k*ll you")
.setBlocklistNames(Arrays.asList("my-blocklist"))
.setHaltOnBlocklistHit(true);
AnalyzeTextResult result = contentSafetyClient.analyzeText(options);
if (result.getBlocklistsMatch() != null) {
for (TextBlocklistMatch match : result.getBlocklistsMatch()) {
System.out.printf("Blocklist: %s, Item: %s, Text: %s%n",
match.getBlocklistName(),
match.getBlocklistItemId(),
match.getBlocklistItemText());
}
}
Analyze Image
import com.azure.ai.contentsafety.models.*;
import com.azure.core.util.BinaryData;
import java.nio.file.Files;
import java.nio.file.Paths;
// From file
byte[] imageBytes = Files.readAllBytes(Paths.get("image.png"));
ContentSafetyImageData imageData = new ContentSafetyImageData()
.setContent(BinaryData.fromBytes(imageBytes));
AnalyzeImageResult result = contentSafetyClient.analyzeImage(
new AnalyzeImageOptions(imageData));
for (ImageCategoriesAnalysis category : result.getCategoriesAnalysis()) {
System.out.printf("Category: %s, Severity: %d%n",
category.getCategory(),
category.getSeverity());
}
Analyze Image from URL
ContentSafetyImageData imageData = new ContentSafetyImageData()
.setBlobUrl("https://example.com/image.jpg");
AnalyzeImageResult result = contentSafetyClient.analyzeImage(
new AnalyzeImageOptions(imageData));
Blocklist Management
Create or Update Blocklist
import com.azure.core.http.rest.RequestOptions;
import com.azure.core.http.rest.Response;
import com.azure.core.util.BinaryData;
import java.util.Map;
Map<String, String> description = Map.of("description", "Custom blocklist");
BinaryData resource = BinaryData.fromObject(description);
Response<BinaryData> response = blocklistClient.createOrUpdateTextBlocklistWithResponse(
"my-blocklist", resource, new RequestOptions());
if (response.getStatusCode() == 201) {
System.out.println("Blocklist created");
} else if (response.getStatusCode() == 200) {
System.out.println("Blocklist updated");
}
Add Block Items
import com.azure.ai.contentsafety.models.*;
import java.util.Arrays;
List<TextBlocklistItem> items = Arrays.asList(
new TextBlocklistItem("badword1").setDescription("Offensive term"),
new TextBlocklistItem("badword2").setDescription("Another term")
);
AddOrUpdateTextBlocklistItemsResult result = blocklistClient.addOrUpdateBlocklistItems(
"my-blocklist",
new AddOrUpdateTextBlocklistItemsOptions(items));
for (TextBlocklistItem item : result.getBlocklistItems()) {
System.out.printf("Added: %s (ID: %s)%n",
item.getText(),
item.getBlocklistItemId());
}
List Blocklists
PagedIterable<TextBlocklist> blocklists = blocklistClient.listTextBlocklists();
for (TextBlocklist blocklist : blocklists) {
System.out.printf("Blocklist: %s, Description: %s%n",
blocklist.getName(),
blocklist.getDescription());
}
Get Blocklist
TextBlocklist blocklist = blocklistClient.getTextBlocklist("my-blocklist");
System.out.println("Name: " + blocklist.getName());
List Block Items
PagedIterable<TextBlocklistItem> items =
blocklistClient.listTextBlocklistItems("my-blocklist");
for (TextBlocklistItem item : items) {
System.out.printf("ID: %s, Text: %s%n",
item.getBlocklistItemId(),
item.getText());
}
Remove Block Items
List<String> itemIds = Arrays.asList("item-id-1", "item-id-2");
blocklistClient.removeBlocklistItems(
"my-blocklist",
new RemoveTextBlocklistItemsOptions(itemIds));
Delete Blocklist
blocklistClient.deleteTextBlocklist("my-blocklist");
Error Handling
import com.azure.core.exception.HttpResponseException;
try {
contentSafetyClient.analyzeText(new AnalyzeTextOptions("test"));
} catch (HttpResponseException e) {
System.out.println("Status: " + e.getResponse().getStatusCode());
System.out.println("Error: " + e.getMessage());
// Common codes: InvalidRequestBody, ResourceNotFound, TooManyRequests
}
Environment Variables
CONTENT_SAFETY_ENDPOINT=https://<resource>.cognitiveservices.azure.com/ # Required for all auth methods
CONTENT_SAFETY_KEY=<your-api-key> # Only required for AzureKeyCredential auth
AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production
Best Practices
- Blocklist Delay: Changes take ~5 minutes to take effect
- Category Selection: Only request needed categories to reduce latency
- Severity Thresholds: Typically block severity >= 4 for strict moderation
- Batch Processing: Process multiple items in parallel for throughput
- Caching: Cache blocklist results where appropriate
Trigger Phrases
- "content safety Java"
- "content moderation Azure"
- "analyze text safety"
- "image moderation Java"
- "blocklist management"
- "hate speech detection"
- "harmful content filter"
Files (skills)
-
references
-
examples.md 17 KB
# Azure AI Content Safety SDK for Java - Examples Comprehensive code examples for the Azure AI Content Safety SDK for Java. ## Table of Contents - [Maven Dependency](#maven-dependency) - [Client Creation](#client-creation) - [Analyzing Text Content](#analyzing-text-content) - [Analyzing Image Content](#analyzing-image-content) - [Handling Analysis Results](#handling-analysis-results) - [Blocklist Management](#blocklist-management) - [Async Client Patterns](#async-client-patterns) - [Error Handling](#error-handling) ## Maven Dependency ```xml <dependency> <groupId>com.azure</groupId> <artifactId>azure-ai-contentsafety</artifactId> <version>1.0.16</version> </dependency> <!-- For DefaultAzureCredential authentication --> <dependency> <groupId>com.azure</groupId> <artifactId>azure-identity</artifactId> <version>1.14.2</version> </dependency> ``` ## Client Creation ### With API Key Credential ```java import com.azure.ai.contentsafety.ContentSafetyClient; import com.azure.ai.contentsafety.ContentSafetyClientBuilder; import com.azure.ai.contentsafety.BlocklistClient; import com.azure.ai.contentsafety.BlocklistClientBuilder; import com.azure.core.credential.KeyCredential; import com.azure.core.util.Configuration; String endpoint = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_ENDPOINT"); String key = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_KEY"); // Content Safety client ContentSafetyClient contentSafetyClient = new ContentSafetyClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildClient(); // Blocklist client BlocklistClient blocklistClient = new BlocklistClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildClient(); ``` ### With DefaultAzureCredential (Microsoft Entra ID) ```java import com.azure.identity.DefaultAzureCredentialBuilder; // Set environment variables: AZURE_CLIENT_ID, AZURE_TENANT_ID, AZURE_CLIENT_SECRET ContentSafetyClient contentSafetyClient = new ContentSafetyClientBuilder() .credential(new DefaultAzureCredentialBuilder().build()) .endpoint(endpoint) .buildClient(); BlocklistClient blocklistClient = new BlocklistClientBuilder() .credential(new DefaultAzureCredentialBuilder().build()) .endpoint(endpoint) .buildClient(); ``` ## Analyzing Text Content ```java import com.azure.ai.contentsafety.ContentSafetyClient; import com.azure.ai.contentsafety.ContentSafetyClientBuilder; import com.azure.ai.contentsafety.models.AnalyzeTextOptions; import com.azure.ai.contentsafety.models.AnalyzeTextResult; import com.azure.ai.contentsafety.models.TextCategoriesAnalysis; import com.azure.core.credential.KeyCredential; import com.azure.core.util.Configuration; public class AnalyzeText { public static void main(String[] args) { String endpoint = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_ENDPOINT"); String key = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_KEY"); ContentSafetyClient contentSafetyClient = new ContentSafetyClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildClient(); // Analyze text AnalyzeTextResult response = contentSafetyClient.analyzeText( new AnalyzeTextOptions("This is text example") ); // Process results - iterate through harm categories for (TextCategoriesAnalysis result : response.getCategoriesAnalysis()) { System.out.println(result.getCategory() + " severity: " + result.getSeverity()); } } } ``` ## Analyzing Image Content ```java import com.azure.ai.contentsafety.ContentSafetyClient; import com.azure.ai.contentsafety.ContentSafetyClientBuilder; import com.azure.ai.contentsafety.models.AnalyzeImageOptions; import com.azure.ai.contentsafety.models.AnalyzeImageResult; import com.azure.ai.contentsafety.models.ContentSafetyImageData; import com.azure.ai.contentsafety.models.ImageCategoriesAnalysis; import com.azure.core.credential.KeyCredential; import com.azure.core.util.BinaryData; import com.azure.core.util.Configuration; import java.io.IOException; import java.nio.file.Files; import java.nio.file.Paths; public class AnalyzeImage { public static void main(String[] args) throws IOException { String endpoint = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_ENDPOINT"); String key = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_KEY"); ContentSafetyClient contentSafetyClient = new ContentSafetyClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildClient(); // Load image from file ContentSafetyImageData image = new ContentSafetyImageData(); String cwd = System.getProperty("user.dir"); String source = "/src/samples/resources/image.png"; image.setContent(BinaryData.fromBytes(Files.readAllBytes(Paths.get(cwd, source)))); // Analyze image AnalyzeImageResult response = contentSafetyClient.analyzeImage( new AnalyzeImageOptions(image) ); // Process results - iterate through harm categories for (ImageCategoriesAnalysis result : response.getCategoriesAnalysis()) { System.out.println(result.getCategory() + " severity: " + result.getSeverity()); } } } ``` ## Handling Analysis Results ### Severity Levels and Content Moderation ```java import com.azure.ai.contentsafety.ContentSafetyClient; import com.azure.ai.contentsafety.ContentSafetyClientBuilder; import com.azure.ai.contentsafety.models.*; import com.azure.core.credential.KeyCredential; import com.azure.core.util.Configuration; public class HandleAnalysisResults { // Severity thresholds for content moderation decisions private static final int SEVERITY_SAFE = 0; private static final int SEVERITY_LOW = 2; private static final int SEVERITY_MEDIUM = 4; private static final int SEVERITY_HIGH = 6; public static void main(String[] args) { String endpoint = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_ENDPOINT"); String key = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_KEY"); ContentSafetyClient client = new ContentSafetyClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildClient(); String textToAnalyze = "Sample text to analyze for harmful content"; AnalyzeTextResult result = client.analyzeText(new AnalyzeTextOptions(textToAnalyze)); // Process each harm category for (TextCategoriesAnalysis categoryResult : result.getCategoriesAnalysis()) { TextCategory category = categoryResult.getCategory(); Integer severity = categoryResult.getSeverity(); System.out.println("Category: " + category); System.out.println("Severity: " + severity); // Make moderation decisions based on severity // Categories: HATE, SEXUAL, VIOLENCE, SELF_HARM String action = determineModerationAction(severity); System.out.println("Recommended Action: " + action); System.out.println("---"); } // Check if content should be blocked boolean shouldBlock = shouldBlockContent(result); System.out.println("Block Content: " + shouldBlock); } private static String determineModerationAction(Integer severity) { if (severity == null) { return "UNKNOWN"; } if (severity <= SEVERITY_SAFE) { return "ALLOW - Content is safe"; } else if (severity <= SEVERITY_LOW) { return "REVIEW - Low severity, may need human review"; } else if (severity <= SEVERITY_MEDIUM) { return "FLAG - Medium severity, requires attention"; } else { return "BLOCK - High severity, should be blocked"; } } private static boolean shouldBlockContent(AnalyzeTextResult result) { for (TextCategoriesAnalysis categoryResult : result.getCategoriesAnalysis()) { Integer severity = categoryResult.getSeverity(); if (severity != null && severity >= SEVERITY_MEDIUM) { return true; } } return false; } } ``` ## Blocklist Management ### Create or Update Blocklist ```java import com.azure.ai.contentsafety.BlocklistClient; import com.azure.ai.contentsafety.BlocklistClientBuilder; import com.azure.core.credential.KeyCredential; import com.azure.core.http.rest.RequestOptions; import com.azure.core.http.rest.Response; import com.azure.core.util.BinaryData; import com.azure.core.util.Configuration; import java.util.HashMap; import java.util.Map; String endpoint = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_ENDPOINT"); String key = Configuration.getGlobalConfiguration().get("CONTENT_SAFETY_KEY"); BlocklistClient blocklistClient = new BlocklistClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildClient(); // Create or update blocklist String blocklistName = "TestBlocklist"; Map<String, String> description = new HashMap<>(); description.put("description", "Test Blocklist"); BinaryData resource = BinaryData.fromObject(description); RequestOptions requestOptions = new RequestOptions(); Response<BinaryData> response = blocklistClient .createOrUpdateTextBlocklistWithResponse(blocklistName, resource, requestOptions); if (response.getStatusCode() == 201) { System.out.println("Blocklist " + blocklistName + " created."); } else if (response.getStatusCode() == 200) { System.out.println("Blocklist " + blocklistName + " updated."); } ``` ### Add Blocklist Items ```java import com.azure.ai.contentsafety.models.AddOrUpdateTextBlocklistItemsOptions; import com.azure.ai.contentsafety.models.AddOrUpdateTextBlocklistItemsResult; import com.azure.ai.contentsafety.models.TextBlocklistItem; import java.util.Arrays; import java.util.List; String blockItemText1 = "k*ll"; String blockItemText2 = "h*te"; List<TextBlocklistItem> blockItems = Arrays.asList( new TextBlocklistItem(blockItemText1).setDescription("Kill word"), new TextBlocklistItem(blockItemText2).setDescription("Hate word") ); AddOrUpdateTextBlocklistItemsResult addedBlockItems = blocklistClient.addOrUpdateBlocklistItems( blocklistName, new AddOrUpdateTextBlocklistItemsOptions(blockItems) ); if (addedBlockItems != null && addedBlockItems.getBlocklistItems() != null) { System.out.println("BlockItems added:"); for (TextBlocklistItem addedBlockItem : addedBlockItems.getBlocklistItems()) { System.out.println("BlockItemId: " + addedBlockItem.getBlocklistItemId() + ", Text: " + addedBlockItem.getText() + ", Description: " + addedBlockItem.getDescription()); } } ``` ### Analyze Text with Blocklist ```java import com.azure.ai.contentsafety.ContentSafetyClient; import com.azure.ai.contentsafety.models.AnalyzeTextOptions; import com.azure.ai.contentsafety.models.AnalyzeTextResult; import com.azure.ai.contentsafety.models.TextBlocklistMatch; import java.util.Arrays; // Note: After editing blocklist, wait ~5 minutes for changes to take effect AnalyzeTextOptions request = new AnalyzeTextOptions("I h*te you and I want to k*ll you"); request.setBlocklistNames(Arrays.asList(blocklistName)); request.setHaltOnBlocklistHit(true); // Stop analysis on first blocklist match AnalyzeTextResult analyzeTextResult = contentSafetyClient.analyzeText(request); // Check for blocklist matches if (analyzeTextResult.getBlocklistsMatch() != null) { System.out.println("Blocklist matches found:"); for (TextBlocklistMatch match : analyzeTextResult.getBlocklistsMatch()) { System.out.println("BlocklistName: " + match.getBlocklistName()); System.out.println("BlocklistItemId: " + match.getBlocklistItemId()); System.out.println("BlocklistItemText: " + match.getBlocklistItemText()); } } ``` ### Remove Blocklist Items ```java import com.azure.ai.contentsafety.models.RemoveTextBlocklistItemsOptions; import java.util.Arrays; import java.util.List; List<String> blocklistItemIdsToRemove = Arrays.asList( "blocklistItemId1", "blocklistItemId2" ); blocklistClient.removeBlocklistItems( blocklistName, new RemoveTextBlocklistItemsOptions(blocklistItemIdsToRemove) ); System.out.println("Blocklist items removed."); ``` ### List Blocklists and Items ```java import com.azure.ai.contentsafety.models.TextBlocklist; import com.azure.ai.contentsafety.models.TextBlocklistItem; import com.azure.core.http.rest.PagedIterable; // List all blocklists PagedIterable<TextBlocklist> blocklists = blocklistClient.listTextBlocklists(); for (TextBlocklist blocklist : blocklists) { System.out.println("Blocklist: " + blocklist.getName()); System.out.println("Description: " + blocklist.getDescription()); } // List items in a blocklist PagedIterable<TextBlocklistItem> items = blocklistClient.listTextBlocklistItems(blocklistName); for (TextBlocklistItem item : items) { System.out.println("Item ID: " + item.getBlocklistItemId()); System.out.println("Text: " + item.getText()); System.out.println("Description: " + item.getDescription()); } ``` ### Delete Blocklist ```java blocklistClient.deleteTextBlocklist(blocklistName); System.out.println("Blocklist " + blocklistName + " deleted."); ``` ## Async Client Patterns ### Async Content Safety Client ```java import com.azure.ai.contentsafety.ContentSafetyAsyncClient; import com.azure.ai.contentsafety.ContentSafetyClientBuilder; import com.azure.ai.contentsafety.models.AnalyzeTextOptions; import com.azure.core.credential.KeyCredential; ContentSafetyAsyncClient asyncClient = new ContentSafetyClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildAsyncClient(); // Async text analysis asyncClient.analyzeText(new AnalyzeTextOptions("Text to analyze")) .subscribe( result -> { result.getCategoriesAnalysis().forEach(category -> { System.out.println(category.getCategory() + ": " + category.getSeverity()); }); }, error -> System.err.println("Error: " + error.getMessage()), () -> System.out.println("Analysis completed") ); ``` ### Async Blocklist Client ```java import com.azure.ai.contentsafety.BlocklistAsyncClient; import com.azure.ai.contentsafety.BlocklistClientBuilder; BlocklistAsyncClient asyncBlocklistClient = new BlocklistClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildAsyncClient(); // Async list blocklists asyncBlocklistClient.listTextBlocklists() .subscribe( blocklist -> System.out.println("Found blocklist: " + blocklist.getName()), error -> System.err.println("Error: " + error.getMessage()) ); ``` ## Error Handling ```java import com.azure.core.exception.HttpResponseException; import com.azure.ai.contentsafety.models.AnalyzeTextOptions; public class ContentSafetyErrorHandling { public static void analyzeWithErrorHandling(ContentSafetyClient client, String text) { try { var result = client.analyzeText(new AnalyzeTextOptions(text)); // Process result result.getCategoriesAnalysis().forEach(category -> { System.out.println(category.getCategory() + ": " + category.getSeverity()); }); } catch (HttpResponseException e) { int statusCode = e.getResponse().getStatusCode(); System.err.println("HTTP Status: " + statusCode); System.err.println("Error: " + e.getMessage()); switch (statusCode) { case 400: System.err.println("Bad request - check input parameters"); break; case 401: System.err.println("Unauthorized - check API key"); break; case 403: System.err.println("Forbidden - check permissions"); break; case 404: System.err.println("Resource not found"); break; case 429: System.err.println("Rate limited - slow down requests"); break; default: if (statusCode >= 500) { System.err.println("Server error - retry later"); } } } catch (Exception e) { System.err.println("Unexpected error: " + e.getMessage()); } } } ``` ### Async Error Handling ```java asyncClient.analyzeText(new AnalyzeTextOptions(text)) .subscribe( result -> { // Process result }, error -> { if (error instanceof HttpResponseException) { HttpResponseException httpError = (HttpResponseException) error; System.err.println("HTTP error: " + httpError.getResponse().getStatusCode()); } else { System.err.println("Error: " + error.getMessage()); } } ); ```
-
-
SKILL.md 8.3 KB
--- name: azure-ai-contentsafety-java description: Build content moderation applications with Azure AI Content Safety SDK for Java. Use when implementing text/image analysis, blocklist management, or harm detection for hate, violence, sexual content, and self-harm. license: MIT metadata: author: Microsoft version: "1.0.0" package: com.azure:azure-ai-contentsafety --- # Azure AI Content Safety SDK for Java Build content moderation applications using the Azure AI Content Safety SDK for Java. ## Installation ```xml <dependency> <groupId>com.azure</groupId> <artifactId>azure-ai-contentsafety</artifactId> <version>1.1.0-beta.1</version> </dependency> ``` ## Client Creation ### With API Key ```java import com.azure.ai.contentsafety.ContentSafetyClient; import com.azure.ai.contentsafety.ContentSafetyClientBuilder; import com.azure.ai.contentsafety.BlocklistClient; import com.azure.ai.contentsafety.BlocklistClientBuilder; import com.azure.core.credential.KeyCredential; String endpoint = System.getenv("CONTENT_SAFETY_ENDPOINT"); String key = System.getenv("CONTENT_SAFETY_KEY"); ContentSafetyClient contentSafetyClient = new ContentSafetyClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildClient(); BlocklistClient blocklistClient = new BlocklistClientBuilder() .credential(new KeyCredential(key)) .endpoint(endpoint) .buildClient(); ``` ### With DefaultAzureCredential ```java import com.azure.core.credential.TokenCredential; import com.azure.identity.AzureIdentityEnvVars; import com.azure.identity.DefaultAzureCredentialBuilder; import com.azure.identity.ManagedIdentityCredentialBuilder; TokenCredential credential = new DefaultAzureCredentialBuilder() .requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS) .build(); // Or use a specific credential directly in production: // See https://learn.microsoft.com/java/api/overview/azure/identity-readme?view=azure-java-stable#credential-classes // TokenCredential credential = new ManagedIdentityCredentialBuilder().build(); ContentSafetyClient client = new ContentSafetyClientBuilder() .credential(credential) .endpoint(endpoint) .buildClient(); ``` ## Key Concepts ### Harm Categories | Category | Description | |----------|-------------| | Hate | Discriminatory language based on identity groups | | Sexual | Sexual content, relationships, acts | | Violence | Physical harm, weapons, injury | | Self-harm | Self-injury, suicide-related content | ### Severity Levels - Text: 0-7 scale (default outputs 0, 2, 4, 6) - Image: 0, 2, 4, 6 (trimmed scale) ## Core Patterns ### Analyze Text ```java import com.azure.ai.contentsafety.models.*; AnalyzeTextResult result = contentSafetyClient.analyzeText( new AnalyzeTextOptions("This is text to analyze")); for (TextCategoriesAnalysis category : result.getCategoriesAnalysis()) { System.out.printf("Category: %s, Severity: %d%n", category.getCategory(), category.getSeverity()); } ``` ### Analyze Text with Options ```java AnalyzeTextOptions options = new AnalyzeTextOptions("Text to analyze") .setCategories(Arrays.asList( TextCategory.HATE, TextCategory.VIOLENCE)) .setOutputType(AnalyzeTextOutputType.EIGHT_SEVERITY_LEVELS); AnalyzeTextResult result = contentSafetyClient.analyzeText(options); ``` ### Analyze Text with Blocklist ```java AnalyzeTextOptions options = new AnalyzeTextOptions("I h*te you and want to k*ll you") .setBlocklistNames(Arrays.asList("my-blocklist")) .setHaltOnBlocklistHit(true); AnalyzeTextResult result = contentSafetyClient.analyzeText(options); if (result.getBlocklistsMatch() != null) { for (TextBlocklistMatch match : result.getBlocklistsMatch()) { System.out.printf("Blocklist: %s, Item: %s, Text: %s%n", match.getBlocklistName(), match.getBlocklistItemId(), match.getBlocklistItemText()); } } ``` ### Analyze Image ```java import com.azure.ai.contentsafety.models.*; import com.azure.core.util.BinaryData; import java.nio.file.Files; import java.nio.file.Paths; // From file byte[] imageBytes = Files.readAllBytes(Paths.get("image.png")); ContentSafetyImageData imageData = new ContentSafetyImageData() .setContent(BinaryData.fromBytes(imageBytes)); AnalyzeImageResult result = contentSafetyClient.analyzeImage( new AnalyzeImageOptions(imageData)); for (ImageCategoriesAnalysis category : result.getCategoriesAnalysis()) { System.out.printf("Category: %s, Severity: %d%n", category.getCategory(), category.getSeverity()); } ``` ### Analyze Image from URL ```java ContentSafetyImageData imageData = new ContentSafetyImageData() .setBlobUrl("https://example.com/image.jpg"); AnalyzeImageResult result = contentSafetyClient.analyzeImage( new AnalyzeImageOptions(imageData)); ``` ## Blocklist Management ### Create or Update Blocklist ```java import com.azure.core.http.rest.RequestOptions; import com.azure.core.http.rest.Response; import com.azure.core.util.BinaryData; import java.util.Map; Map<String, String> description = Map.of("description", "Custom blocklist"); BinaryData resource = BinaryData.fromObject(description); Response<BinaryData> response = blocklistClient.createOrUpdateTextBlocklistWithResponse( "my-blocklist", resource, new RequestOptions()); if (response.getStatusCode() == 201) { System.out.println("Blocklist created"); } else if (response.getStatusCode() == 200) { System.out.println("Blocklist updated"); } ``` ### Add Block Items ```java import com.azure.ai.contentsafety.models.*; import java.util.Arrays; List<TextBlocklistItem> items = Arrays.asList( new TextBlocklistItem("badword1").setDescription("Offensive term"), new TextBlocklistItem("badword2").setDescription("Another term") ); AddOrUpdateTextBlocklistItemsResult result = blocklistClient.addOrUpdateBlocklistItems( "my-blocklist", new AddOrUpdateTextBlocklistItemsOptions(items)); for (TextBlocklistItem item : result.getBlocklistItems()) { System.out.printf("Added: %s (ID: %s)%n", item.getText(), item.getBlocklistItemId()); } ``` ### List Blocklists ```java PagedIterable<TextBlocklist> blocklists = blocklistClient.listTextBlocklists(); for (TextBlocklist blocklist : blocklists) { System.out.printf("Blocklist: %s, Description: %s%n", blocklist.getName(), blocklist.getDescription()); } ``` ### Get Blocklist ```java TextBlocklist blocklist = blocklistClient.getTextBlocklist("my-blocklist"); System.out.println("Name: " + blocklist.getName()); ``` ### List Block Items ```java PagedIterable<TextBlocklistItem> items = blocklistClient.listTextBlocklistItems("my-blocklist"); for (TextBlocklistItem item : items) { System.out.printf("ID: %s, Text: %s%n", item.getBlocklistItemId(), item.getText()); } ``` ### Remove Block Items ```java List<String> itemIds = Arrays.asList("item-id-1", "item-id-2"); blocklistClient.removeBlocklistItems( "my-blocklist", new RemoveTextBlocklistItemsOptions(itemIds)); ``` ### Delete Blocklist ```java blocklistClient.deleteTextBlocklist("my-blocklist"); ``` ## Error Handling ```java import com.azure.core.exception.HttpResponseException; try { contentSafetyClient.analyzeText(new AnalyzeTextOptions("test")); } catch (HttpResponseException e) { System.out.println("Status: " + e.getResponse().getStatusCode()); System.out.println("Error: " + e.getMessage()); // Common codes: InvalidRequestBody, ResourceNotFound, TooManyRequests } ``` ## Environment Variables ```bash CONTENT_SAFETY_ENDPOINT=https://<resource>.cognitiveservices.azure.com/ # Required for all auth methods CONTENT_SAFETY_KEY=<your-api-key> # Only required for AzureKeyCredential auth AZURE_TOKEN_CREDENTIALS=prod # Required only if DefaultAzureCredential is used in production ``` ## Best Practices 1. **Blocklist Delay**: Changes take ~5 minutes to take effect 2. **Category Selection**: Only request needed categories to reduce latency 3. **Severity Thresholds**: Typically block severity >= 4 for strict moderation 4. **Batch Processing**: Process multiple items in parallel for throughput 5. **Caching**: Cache blocklist results where appropriate ## Trigger Phrases - "content safety Java" - "content moderation Azure" - "analyze text safety" - "image moderation Java" - "blocklist management" - "hate speech detection" - "harmful content filter"
Comments (0)
Sign in to join the conversation.
Reviews (0)
No reviews yet.
No comments yet.