@azure/ai-projects 2.0.0-beta.4 → 2.0.0

package/README.md

@@ -5,39 +5,39 @@ resources in your Microsoft Foundry Project. Use it to:
 
 - **Create and run Agents** using the `.agents` property on the client.
 * **Enhance Agents with specialized tools**:
-  * Agent Memory Search
-  * Agent-to-Agent (A2A)
+  * Agent Memory Search (Preview)
+  * Agent-to-Agent (A2A) (Preview)
   * Azure AI Search
-  * Bing Custom Search
+  * Bing Custom Search (Preview)
   * Bing Grounding
-  * Browser Automation
+  * Browser Automation (Preview)
   * Code Interpreter
-  * Computer Use
+  * Computer Use (Preview)
   * File Search
   * Function Tool
   * Image Generation
-  * Microsoft Fabric
+  * Microsoft Fabric (Preview)
   * Model Context Protocol (MCP)
   * OpenAPI
-  * SharePoint
-  * Web Search
+  * Microsoft SharePoint (Preview)
+  * Web Search (Preview)
 - **Get an OpenAI client** using the `.getOpenAIClient.` method to run Responses, Conversations, Evals and FineTuning operations with your Agent.
-* **Manage memory stores** for Agent conversations, using the `.memoryStores` operations.
-* **Explore additional evaluation tools** to assess the performance of your generative AI application, using the `.evaluationRules`,
-`.evaluationTaxonomies`, `.evaluators`, `.insights`, and `.schedules` operations.
-* **Run Red Team scans** to identify risks associated with your generative AI application, using the ".redTeams" operations.
+* **Manage memory stores (preview)** for Agent conversations, using the `.beta.memoryStores` operations.
+* **Explore additional evaluation tools (some in preview)** to assess the performance of your generative AI application, using the `.evaluationRules`,
+`.beta.evaluationTaxonomies`, `.beta.evaluators`, `.beta.insights`, and `.beta.schedules` operations.
+* **Run Red Team scans (preview)** to identify risks associated with your generative AI application, using the `.beta.redTeams` operations.
 * **Fine tune** AI Models on your data.
 - **Enumerate AI Models** deployed to your Foundry Project using the `.deployments` operations.
 - **Enumerate connected Azure resources** in your Foundry project using the `.connections` operations.
 - **Upload documents and create Datasets** to reference them using the `.datasets` operations.
 - **Create and enumerate Search Indexes** using the `.indexes` operations.
 
-The client library uses version `2025-11-15-preview` of the Microsoft Foundry [data plane REST APIs](https://aka.ms/azsdk/azure-ai-projects-v2/api-reference-2025-11-15-preview).
+The client library uses version `v1` of the Microsoft Foundry [data plane REST APIs](https://aka.ms/azsdk/azure-ai-projects-v2/api-reference-v1).
 
 [Product documentation](https://aka.ms/azsdk/azure-ai-projects-v2/product-doc)
 | [Samples](https://github.com/Azure/azure-sdk-for-js/tree/main/sdk/ai/ai-projects/samples)
 | [Package (npm)](https://www.npmjs.com/package/@azure/ai-projects)
-| [API reference documentation](https://learn.microsoft.com/javascript/api/overview/azure/ai-projects-readme?view=azure-node-v1)
+| [API reference documentation](https://learn.microsoft.com/javascript/api/overview/azure/ai-projects-readme?view=azure-node-preview)
 | [SDK source code](https://github.com/Azure/azure-sdk-for-js/tree/main/sdk/ai/ai-projects)
 
 ## Table of contents
@@ -48,6 +48,7 @@ The client library uses version `2025-11-15-preview` of the Microsoft Foundry [d
   - [Install the package](#install-the-package)
 - [Key concepts](#key-concepts)
   - [Create and authenticate the client](#create-and-authenticate-the-client)
+  - [Preview operation groups and opt-in feature flags](#preview-operation-groups-and-opt-in-feature-flags)
 - [Examples](#examples)
   - [Performing Responses operations using OpenAI client](#performing-responses-operations-using-openai-client)
   - [Performing Agent operations](#performing-agent-operations)
@@ -76,13 +77,13 @@ The client library uses version `2025-11-15-preview` of the Microsoft Foundry [d
 
 - [LTS versions of Node.js](https://github.com/nodejs/release#release-schedule)
 - An [Azure subscription][azure_sub].
-- A [project in Microsoft Foundry](https://learn.microsoft.com/azure/ai-studio/how-to/create-projects?tabs=ai-studio).
+- A [project in Microsoft Foundry](https://learn.microsoft.com/azure/ai-studio/how-to/create-projects).
 - The project endpoint URL of the form `https://your-ai-services-account-name.services.ai.azure.com/api/projects/your-project-name`. It can be found in your Microsoft Foundry Project overview page. Below we will assume the environment variable `AZURE_AI_PROJECT_ENDPOINT` was defined to hold this value.
 
 ### Authorization
 
-- [Entra ID][entra_id] is needed to authenticate the client. Your application needs an object that implements the [TokenCredential](https://learn.microsoft.com/javascript/api/@azure/core-auth/tokencredential) interface. Code samples here use [DefaultAzureCredential][default_azure_credential]. To get that working, you will need:
-  - An appropriate role assignment. see [Role-based access control in Microsoft Foundry portal](https://learn.microsoft.com/azure/ai-foundry/concepts/rbac-ai-foundry). Role assigned can be done via the "Access Control (IAM)" tab of your Azure AI Project resource in the Azure portal.
+- An Entra ID is needed to authenticate the client. Your application needs an object that implements the [TokenCredential](https://learn.microsoft.com/javascript/api/@azure/core-auth/tokencredential) interface. Code samples here use [DefaultAzureCredential][default_azure_credential]. To get that working, you will need:
+  - An appropriate role assignment. see [Role-based access control in Microsoft Foundry portal](https://learn.microsoft.com/azure/ai-foundry/concepts/rbac-foundry?view=foundry). Role assigned can be done via the "Access Control (IAM)" tab of your Azure AI Project resource in the Azure portal.
   - [Azure CLI](https://learn.microsoft.com/cli/azure/install-azure-cli) installed.
   - You are logged into your Azure account by running `az login`.
   - Note that if you have multiple Azure subscriptions, the subscription that contains your Azure AI Project resource must be your default subscription. Run `az account list --output table` to list all your subscription and see which one is the default. Run `az account set --subscription "Your Subscription ID or Name"` to change your default subscription.
@@ -90,7 +91,7 @@ The client library uses version `2025-11-15-preview` of the Microsoft Foundry [d
 ### Install the package
 
 ```bash
-npm install @azure/ai-projects @azure/identity dotenv
+npm install @azure/ai-projects dotenv
 ```
 
 ## Key concepts
@@ -106,9 +107,28 @@ import { AIProjectClient } from "@azure/ai-projects";
 import { DefaultAzureCredential } from "@azure/identity";
 
 const projectEndpoint = process.env["AZURE_AI_PROJECT_ENDPOINT"] || "<project endpoint string>";
-const client = new AIProjectClient(projectEndpoint, new DefaultAzureCredential());
+project = new AIProjectClient(projectEndpoint, new DefaultAzureCredential());
 ```
 
+### Preview operation groups and opt-in feature flags
+
+Some preview operations require an explicit `foundryFeatures` opt-in flag. For example:
+
+```ts snippet:previewflag
+await project.agents.createVersion(
+  "preview-agent",
+  {
+    kind: "workflow",
+  },
+  { foundryFeatures: "WorkflowAgents=V1Preview" },
+);
+for await (const rule of project.evaluationRules.list()) {
+  console.log(rule.id);
+}
+```
+
+Preview operation groups include `.beta.memoryStores`, `.beta.evaluationTaxonomies`, `.beta.evaluators`, `.beta.insights`, `.beta.schedules`, and `.beta.redTeams`.
+
 ## Examples
 
 ### Performing Responses operations using OpenAI client
@@ -121,7 +141,7 @@ See the "responses" folder in the [package samples][samples] for additional samp
 
 
 ```ts snippet:openAI
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 const response = await openAIClient.responses.create({
   model: deploymentName,
   input: "What is the size of France in square miles?",
@@ -141,7 +161,7 @@ The `.agents` property on the `AIProjectsClient` gives you access to all Agent o
 OpenAI Responses protocol, so you will likely need to get an `OpenAI` client to do Agent operations, as shown in the example below.
 
 ```ts snippet:agents
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 const agent = await project.agents.createVersion("my-agent-basic", {
   kind: "prompt",
   model: deploymentName,
@@ -203,7 +223,7 @@ These tools work immediately without requiring external connections.
 Write and run Javascript code in a sandboxed environment, process files and work with diverse data formats. [OpenAI Documentation](https://platform.openai.com/docs/guides/tools-code-interpreter)
 
 ```ts snippet:agent-code-interpreter
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 const response = await openAIClient.responses.create({
   model: deploymentName,
   input: "I need to solve the equation 3x + 11 = 14. Can you help me?",
@@ -219,7 +239,7 @@ See the full sample code in [agentCodeInterpreter.ts](https://github.com/Azure/a
 Built-in RAG (Retrieval-Augmented Generation) tool to process and search through documents using vector stores for knowledge retrieval. [OpenAI Documentation](https://platform.openai.com/docs/assistants/tools/file-search)
 
 ```ts snippet:agent-file-search
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 const assetFilePath = path.join(
   __dirname,
   "..",
@@ -282,7 +302,7 @@ After calling `responses.create()`, you can download file using the returned res
 ```ts snippet:agent-image-generation-download
 import { fileURLToPath } from "url";
 
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 const agent = await project.agents.createVersion("agent-image-generation", {
   kind: "prompt",
   model: deploymentName,
@@ -321,12 +341,12 @@ if (imageData && imageData.length > 0 && imageData[0].result) {
 }
 ```
 
-**Web Search**
+**Web Search (Preview)**
 
 Perform general web searches to retrieve current information from the internet. [OpenAI Documentation](https://platform.openai.com/docs/guides/tools-web-search)
 
 ```ts snippet:agent-web-search
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 // Create Agent with web search tool
 const agent = await project.agents.createVersion("agent-web-search", {
   kind: "prompt",
@@ -364,7 +384,7 @@ console.log(`Response: ${response.output_text}`);
 
 See the full sample code in [agentWebSearch.ts](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples-dev/agents/tools/agentWebSearch.ts).
 
-**Computer Use**
+**Computer Use (Preview)**
 
 Enable agents to interact directly with computer systems for task automation and system operations:
 
@@ -398,7 +418,7 @@ See the full sample code in [agentComputerUse.ts](https://github.com/Azure/azure
 Integrate MCP servers to extend agent capabilities with standardized tools and resources. [OpenAI Documentation](https://platform.openai.com/docs/guides/tools-connectors-mcp)
 
 ```ts snippet:agent-mcp
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 const agent = await project.agents.createVersion("agent-mcp", {
   kind: "prompt",
   model: deploymentName,
@@ -446,7 +466,7 @@ const agent = await project.agents.createVersion("MyOpenApiAgent", {
   kind: "prompt",
   model: deploymentName,
   instructions:
-    "You are a helpful assistant that can call external APIs defined by OpenAPI specs to answer user questions.",
+    "You are a helpful assistant that can call external APIs defined by OpenAPI specs to answer user questions. When calling the weather tool, always include the query parameter format=j1.",
   tools: [
     {
       type: "openapi",
@@ -504,7 +524,7 @@ console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${age
 
 See the full sample code in [agentFunctionTool.ts](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples-dev/agents/agentFunctionTool.ts).
 
-* **Memory Search Tool**
+* **Memory Search Tool (Preview)**
 
 The Memory Store Tool adds Memory to an Agent, allowing the Agent's AI model to search for past information related to the current user prompt.
 
@@ -515,7 +535,7 @@ const memoryStoreName = "AgentMemoryStore";
 const embeddingModelDeployment =
   process.env["AZURE_AI_EMBEDDING_MODEL_DEPLOYMENT_NAME"] || "<embedding model>";
 const scope = "user_123";
-const memoryStore = await project.memoryStores.create(
+const memoryStore = await project.beta.memoryStores.create(
   memoryStoreName,
   {
     kind: "default",
@@ -541,7 +561,7 @@ const agent = await project.agents.createVersion("MemorySearchAgent", {
     "You are a helpful assistant that remembers user preferences using the memory search tool.",
   tools: [
     {
-      type: "memory_search",
+      type: "memory_search_preview",
       memory_store_name: memoryStore.name,
       scope,
       update_delay: 1, // wait briefly after conversation inactivity before updating memories
@@ -616,7 +636,7 @@ console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${age
 
 See the full sample code in [agentBingGrounding.ts](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingGrounding.ts).
 
-**Bing Custom Search**
+**Bing Custom Search (Preview)**
 
 Use custom-configured Bing search instances for domain-specific or filtered web search results:
 ```ts snippet:agent-bing-custom-search
@@ -646,7 +666,7 @@ console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${age
 
 See the full sample code in [agentBingCustomSearch.ts](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples-dev/agents/tools/agentBingCustomSearch.ts).
 
-**Microsoft Fabric**
+**Microsoft Fabric (Preview)**
 
 Connect to and query Microsoft Fabric:
 
@@ -674,7 +694,7 @@ console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${age
 
 See the full sample code in [agentFabric.ts](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples-dev/agents/tools/agentFabric.ts).
 
-**SharePoint**
+**Microsoft SharePoint (Preview)**
 
 Access and search SharePoint documents, lists, and sites for enterprise knowledge integration:
 
@@ -704,7 +724,7 @@ console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${age
 
 See the full sample code in [agentSharepoint.ts](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples-dev/agents/tools/agentSharepoint.ts).
 
-**Browser Automation**
+**Browser Automation (Preview)**
 
 Automate browser interactions for web scraping, testing, and interaction with web applications:
 
@@ -758,7 +778,7 @@ console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${age
 
 See the full sample code in [agentMcpConnectionAuth.ts](https://github.com/Azure/azure-sdk-for-js/blob/main/sdk/ai/ai-projects/samples-dev/agents/tools/agentMcpConnectionAuth.ts).
 
-**Agent-to-Agent (A2A)**
+**Agent-to-Agent (A2A) (Preview)**
 
 Enable multi-agent collaboration where agents can communicate and delegate tasks to other specialized agents:
 
@@ -838,7 +858,7 @@ The code below shows some evaluation operations. Full list of sample can be foun
 
 
 ```ts snippet:evaluations
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 const dataSourceConfig = {
   type: "custom" as const,
   item_schema: {
@@ -961,7 +981,9 @@ for await (const azureOpenAIConnection of project.connections.list({
 console.log(`Retrieved ${azureAIConnections.length} Azure OpenAI connections`);
 
 // Get the details of a default connection
-const defaultConnection = await project.connections.getDefault("AzureOpenAI", true);
+const defaultConnection = await project.connections.getDefault("AzureOpenAI", {
+  includeCredentials: true,
+});
 console.log(`Retrieved default connection ${JSON.stringify(defaultConnection, null, 2)}`);
 ```
 
@@ -1045,7 +1067,7 @@ console.log("All specified Datasets have been deleted.");
 The code below shows some Files operations using the OpenAI client, which allow you to upload, retrieve, list, and delete files. These operations are useful for working with files that can be used for fine-tuning and other AI model operations. Full samples can be found under the "files" folder in the [package samples][samples].
 
 ```ts snippet:files
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 console.log("Uploading file");
 const created = await openAIClient.files.create({
   file: fs.createReadStream(filePath),
@@ -1119,7 +1141,7 @@ import { JobCreateParams } from "openai/resources/fine-tuning/jobs";
 
 const trainingFilePath = "training_data_path.jsonl";
 const validationFilePath = "validation_data_path.jsonl";
-const openAIClient = await project.getOpenAIClient();
+const openAIClient = project.getOpenAIClient();
 // 1) Create the training and validation files
 const trainingFile = await openAIClient.files.create({
   file: fs.createReadStream(trainingFilePath),
@@ -1243,7 +1265,6 @@ additional questions or comments.
 <!-- LINKS -->
 
 [code_of_conduct]: https://opensource.microsoft.com/codeofconduct/
-[entra_id]: https://learn.microsoft.com/azure/ai-foundry/foundry-models/how-to/configure-entra-id?tabs=javascript&pivots=ai-foundry-portal
 [default_azure_credential]: https://github.com/Azure/azure-sdk-for-js/tree/main/sdk/identity/identity#defaultazurecredential
 [azure_sub]: https://azure.microsoft.com/free/
 [evaluators]: https://learn.microsoft.com/azure/ai-studio/how-to/develop/evaluate-sdk

package/dist/browser/aiProjectClient.d.ts

@@ -1,20 +1,16 @@
 import OpenAI from "openai";
-import { AIProjectClientOptionalParams } from "./api/index.js";
-import { AgentsOperations } from "./classic/agents/index.js";
-import { ConnectionsOperations } from "./classic/connections/index.js";
-import { DatasetsOperations } from "./classic/datasets/index.js";
-import { DeploymentsOperations } from "./classic/deployments/index.js";
-import { EvaluationRulesOperations } from "./classic/evaluationRules/index.js";
-import { EvaluationTaxonomiesOperations } from "./classic/evaluationTaxonomies/index.js";
-import { EvaluatorsOperations } from "./classic/evaluators/index.js";
-import { IndexesOperations } from "./classic/indexes/index.js";
-import { InsightsOperations } from "./classic/insights/index.js";
-import { MemoryStoresOperations } from "./classic/memoryStores/index.js";
-import { TelemetryOperations } from "./classic/telemetry/index.js";
-import { RedTeamsOperations } from "./classic/redTeams/index.js";
-import { SchedulesOperations } from "./classic/schedules/index.js";
-import { TokenCredential } from "@azure/core-auth";
-export { AIProjectClientOptionalParams } from "./api/aiProjectContext.js";
+import type { ClientOptions as OpenAIClientOptions } from "openai";
+import type { AIProjectClientOptionalParams } from "./api/index.js";
+import type { AgentsOperations } from "./classic/agents/index.js";
+import type { BetaOperations } from "./classic/beta/index.js";
+import type { ConnectionsOperations } from "./classic/connections/index.js";
+import type { DatasetsOperations } from "./classic/datasets/index.js";
+import type { DeploymentsOperations } from "./classic/deployments/index.js";
+import type { EvaluationRulesOperations } from "./classic/evaluationRules/index.js";
+import type { IndexesOperations } from "./classic/indexes/index.js";
+import type { TelemetryOperations } from "./classic/telemetry/index.js";
+import type { TokenCredential } from "@azure/core-auth";
+export type { AIProjectClientOptionalParams } from "./api/aiProjectContext.js";
 /**
  * The main client for the AIProjectClient service. It provides access to the various operations available in the service.
  * @class AIProjectClient
@@ -24,16 +20,22 @@ export { AIProjectClientOptionalParams } from "./api/aiProjectContext.js";
  * @param {string} endpoint - The endpoint to use
  * @param {TokenCredential} credential - The credential to use
  * @param {AIProjectClientOptionalParams} [options] - Optional parameters for the client.
- * @property {RedTeamsOperations} redTeams - The operation groups for redTeams
  * @property {DeploymentsOperations} deployments - The operation groups for deployments
  * @property {IndexesOperations} indexes - The operation groups for indexes
  * @property {DatasetsOperations} datasets - The operation groups for datasets
  * @property {ConnectionsOperations} connections - The operation groups for connections
- * @property {MemoryStoresOperations} memoryStores - The operation groups for memoryStores
  * @property {AgentsOperations} agents - The operation groups for agents
+ * @property {BetaOperations} beta - The operation groups for beta include beta features:
+ * - Memory Stores
+ * - Evaluators
+ * - Evaluation Rules
+ * - Evaluation Taxonomies
+ * - Insights
+ * - Schedules
+ * - Red Teams
  * @property {TelemetryOperations} telemetry - The operation groups for telemetry
  * @property {getEndpointUrl} getEndpointUrl - gets the endpoint of the client
- * @property {getOpenAIClient} getOpenAIClient - gets the OpenAI client
+ * @property {getOpenAIClient} getOpenAIClient - gets the OpenAI client with optional OpenAI client options
  */
 export declare class AIProjectClient {
     private _cognitiveScopeClient;
@@ -42,37 +44,35 @@ export declare class AIProjectClient {
     private _credential;
     private _options;
     constructor(endpoint: string, credential: TokenCredential, options?: AIProjectClientOptionalParams);
-    /** The operation groups for schedules */
-    readonly schedules: SchedulesOperations;
-    /** The operation groups for insights */
-    readonly insights: InsightsOperations;
-    /** The operation groups for evaluators */
-    readonly evaluators: EvaluatorsOperations;
-    /** The operation groups for evaluationTaxonomies */
-    readonly evaluationTaxonomies: EvaluationTaxonomiesOperations;
-    /** The operation groups for evaluationRules */
-    readonly evaluationRules: EvaluationRulesOperations;
-    /** The operation groups for redTeams */
-    readonly redTeams: RedTeamsOperations;
-    /** The operation groups for deployments */
-    readonly deployments: DeploymentsOperations;
     /** The operation groups for indexes */
     readonly indexes: IndexesOperations;
+    /** The operation groups for deployments */
+    readonly deployments: DeploymentsOperations;
     /** The operation groups for datasets */
     readonly datasets: DatasetsOperations;
     /** The operation groups for connections */
     readonly connections: ConnectionsOperations;
-    /** The operation groups for memoryStores */
-    readonly memoryStores: MemoryStoresOperations;
+    /** The operation groups for evaluationRules */
+    readonly evaluationRules: EvaluationRulesOperations;
     /** The operation groups for agents */
     readonly agents: AgentsOperations;
+    /** The operation groups for beta include beta features:
+     * - Memory Stores
+     * - Evaluators
+     * - Evaluation Rules
+     * - Evaluation Taxonomies
+     * - Insights
+     * - Schedules
+     * - Red Teams
+     */
+    readonly beta: BetaOperations;
     /** The operation groups for telemetry */
     readonly telemetry: TelemetryOperations;
     /**
      * gets the OpenAI client
      * @returns the OpenAI client
      */
-    getOpenAIClient(): Promise<OpenAI>;
+    getOpenAIClient(opts?: OpenAIClientOptions): OpenAI;
     /**
      * gets the endpoint of the client
      * @returns the endpoint of the client

package/dist/browser/aiProjectClient.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"aiProjectClient.d.ts","sourceRoot":"","sources":["../../src/aiProjectClient.ts"],"names":[],"mappings":"AAIA,OAAO,MAAM,MAAM,QAAQ,CAAC;AAE5B,OAAO,EAAqC,6BAA6B,EAAE,MAAM,gBAAgB,CAAC;AAClG,OAAO,EAAE,gBAAgB,EAAwB,MAAM,2BAA2B,CAAC;AACnF,OAAO,EAAE,qBAAqB,EAA6B,MAAM,gCAAgC,CAAC;AAClG,OAAO,EAAE,kBAAkB,EAA0B,MAAM,6BAA6B,CAAC;AACzF,OAAO,EAAE,qBAAqB,EAA6B,MAAM,gCAAgC,CAAC;AAClG,OAAO,EACL,yBAAyB,EAE1B,MAAM,oCAAoC,CAAC;AAC5C,OAAO,EACL,8BAA8B,EAE/B,MAAM,yCAAyC,CAAC;AACjD,OAAO,EAAE,oBAAoB,EAA4B,MAAM,+BAA+B,CAAC;AAC/F,OAAO,EAAE,iBAAiB,EAAyB,MAAM,4BAA4B,CAAC;AACtF,OAAO,EAAE,kBAAkB,EAA0B,MAAM,6BAA6B,CAAC;AACzF,OAAO,EACL,sBAAsB,EAEvB,MAAM,iCAAiC,CAAC;AACzC,OAAO,EAAE,mBAAmB,EAA2B,MAAM,8BAA8B,CAAC;AAC5F,OAAO,EAAE,kBAAkB,EAA0B,MAAM,6BAA6B,CAAC;AACzF,OAAO,EAAE,mBAAmB,EAA2B,MAAM,8BAA8B,CAAC;AAC5F,OAAO,EAAE,eAAe,EAAE,MAAM,kBAAkB,CAAC;AAInD,OAAO,EAAE,6BAA6B,EAAE,MAAM,2BAA2B,CAAC;AAE1E;;;;;;;;;;;;;;;;;;;GAmBG;AACH,qBAAa,eAAe;IAC1B,OAAO,CAAC,qBAAqB,CAAmB;IAChD,OAAO,CAAC,iBAAiB,CAAmB;IAC5C,OAAO,CAAC,SAAS,CAAS;IAC1B,OAAO,CAAC,WAAW,CAAkB;IACrC,OAAO,CAAC,QAAQ,CAAgC;gBAG9C,QAAQ,EAAE,MAAM,EAChB,UAAU,EAAE,eAAe,EAC3B,OAAO,GAAE,6BAAkC;IAqC7C,yCAAyC;IACzC,SAAgB,SAAS,EAAE,mBAAmB,CAAC;IAC/C,wCAAwC;IACxC,SAAgB,QAAQ,EAAE,kBAAkB,CAAC;IAC7C,0CAA0C;IAC1C,SAAgB,UAAU,EAAE,oBAAoB,CAAC;IACjD,oDAAoD;IACpD,SAAgB,oBAAoB,EAAE,8BAA8B,CAAC;IACrE,+CAA+C;IAC/C,SAAgB,eAAe,EAAE,yBAAyB,CAAC;IAC3D,wCAAwC;IACxC,SAAgB,QAAQ,EAAE,kBAAkB,CAAC;IAC7C,2CAA2C;IAC3C,SAAgB,WAAW,EAAE,qBAAqB,CAAC;IACnD,uCAAuC;IACvC,SAAgB,OAAO,EAAE,iBAAiB,CAAC;IAC3C,wCAAwC;IACxC,SAAgB,QAAQ,EAAE,kBAAkB,CAAC;IAC7C,2CAA2C;IAC3C,SAAgB,WAAW,EAAE,qBAAqB,CAAC;IACnD,4CAA4C;IAC5C,SAAgB,YAAY,EAAE,sBAAsB,CAAC;IACrD,sCAAsC;IACtC,SAAgB,MAAM,EAAE,gBAAgB,CAAC;IACzC,yCAAyC;IACzC,SAAgB,SAAS,EAAE,mBAAmB,CAAC;IAC/C;;;OAGG;IACU,eAAe,IAAI,OAAO,CAAC,MAAM,CAAC;IAsB/C;;;OAGG;IACH,IAAW,QAAQ,IAAI,MAAM,CAE5B;CACF"}
+{"version":3,"file":"aiProjectClient.d.ts","sourceRoot":"","sources":["../../src/aiProjectClient.ts"],"names":[],"mappings":"AAIA,OAAO,MAAM,MAAM,QAAQ,CAAC;AAC5B,OAAO,KAAK,EAAE,aAAa,IAAI,mBAAmB,EAAE,MAAM,QAAQ,CAAC;AAEnE,OAAO,KAAK,EAAoB,6BAA6B,EAAE,MAAM,gBAAgB,CAAC;AAEtF,OAAO,KAAK,EAAE,gBAAgB,EAAE,MAAM,2BAA2B,CAAC;AAElE,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,yBAAyB,CAAC;AAE9D,OAAO,KAAK,EAAE,qBAAqB,EAAE,MAAM,gCAAgC,CAAC;AAE5E,OAAO,KAAK,EAAE,kBAAkB,EAAE,MAAM,6BAA6B,CAAC;AAEtE,OAAO,KAAK,EAAE,qBAAqB,EAAE,MAAM,gCAAgC,CAAC;AAE5E,OAAO,KAAK,EAAE,yBAAyB,EAAE,MAAM,oCAAoC,CAAC;AAEpF,OAAO,KAAK,EAAE,iBAAiB,EAAE,MAAM,4BAA4B,CAAC;AAEpE,OAAO,KAAK,EAAE,mBAAmB,EAAE,MAAM,8BAA8B,CAAC;AAExE,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,kBAAkB,CAAC;AAKxD,YAAY,EAAE,6BAA6B,EAAE,MAAM,2BAA2B,CAAC;AAE/E;;;;;;;;;;;;;;;;;;;;;;;;;GAyBG;AACH,qBAAa,eAAe;IAC1B,OAAO,CAAC,qBAAqB,CAAmB;IAChD,OAAO,CAAC,iBAAiB,CAAmB;IAC5C,OAAO,CAAC,SAAS,CAAS;IAC1B,OAAO,CAAC,WAAW,CAAkB;IACrC,OAAO,CAAC,QAAQ,CAAgC;gBAG9C,QAAQ,EAAE,MAAM,EAChB,UAAU,EAAE,eAAe,EAC3B,OAAO,GAAE,6BAAkC;IA8B7C,uCAAuC;IACvC,SAAgB,OAAO,EAAE,iBAAiB,CAAC;IAC3C,2CAA2C;IAC3C,SAAgB,WAAW,EAAE,qBAAqB,CAAC;IACnD,wCAAwC;IACxC,SAAgB,QAAQ,EAAE,kBAAkB,CAAC;IAC7C,2CAA2C;IAC3C,SAAgB,WAAW,EAAE,qBAAqB,CAAC;IACnD,+CAA+C;IAC/C,SAAgB,eAAe,EAAE,yBAAyB,CAAC;IAC3D,sCAAsC;IACtC,SAAgB,MAAM,EAAE,gBAAgB,CAAC;IACzC;;;;;;;;OAQG;IACH,SAAgB,IAAI,EAAE,cAAc,CAAC;IACrC,yCAAyC;IACzC,SAAgB,SAAS,EAAE,mBAAmB,CAAC;IAC/C;;;OAGG;IAEI,eAAe,CAAC,IAAI,CAAC,EAAE,mBAAmB,GAAG,MAAM;IA8B1D;;;OAGG;IACH,IAAW,QAAQ,IAAI,MAAM,CAE5B;CACF"}

package/dist/browser/aiProjectClient.js

@@ -5,20 +5,16 @@ import OpenAI from "openai";
 import { getBearerTokenProvider } from "@azure/identity";
 import { createAIProject } from "./api/index.js";
 import { _getAgentsOperations } from "./classic/agents/index.js";
+import { _getBetaOperations } from "./classic/beta/index.js";
 import { _getConnectionsOperations } from "./classic/connections/index.js";
 import { _getDatasetsOperations } from "./classic/datasets/index.js";
 import { _getDeploymentsOperations } from "./classic/deployments/index.js";
-import { _getEvaluationRulesOperations, } from "./classic/evaluationRules/index.js";
-import { _getEvaluationTaxonomiesOperations, } from "./classic/evaluationTaxonomies/index.js";
-import { _getEvaluatorsOperations } from "./classic/evaluators/index.js";
+import { _getEvaluationRulesOperations } from "./classic/evaluationRules/index.js";
 import { _getIndexesOperations } from "./classic/indexes/index.js";
-import { _getInsightsOperations } from "./classic/insights/index.js";
-import { _getMemoryStoresOperations, } from "./classic/memoryStores/index.js";
 import { _getTelemetryOperations } from "./classic/telemetry/index.js";
-import { _getRedTeamsOperations } from "./classic/redTeams/index.js";
-import { _getSchedulesOperations } from "./classic/schedules/index.js";
 import { overwriteOpenAIClient } from "./overwriteOpenAIClient.js";
 import { getCustomFetch } from "./getCustomFetch.js";
+import { getOpenAIDefaultHeaders } from "./util.js";
 /**
  * The main client for the AIProjectClient service. It provides access to the various operations available in the service.
  * @class AIProjectClient
@@ -28,16 +24,22 @@ import { getCustomFetch } from "./getCustomFetch.js";
  * @param {string} endpoint - The endpoint to use
  * @param {TokenCredential} credential - The credential to use
  * @param {AIProjectClientOptionalParams} [options] - Optional parameters for the client.
- * @property {RedTeamsOperations} redTeams - The operation groups for redTeams
  * @property {DeploymentsOperations} deployments - The operation groups for deployments
  * @property {IndexesOperations} indexes - The operation groups for indexes
  * @property {DatasetsOperations} datasets - The operation groups for datasets
  * @property {ConnectionsOperations} connections - The operation groups for connections
- * @property {MemoryStoresOperations} memoryStores - The operation groups for memoryStores
  * @property {AgentsOperations} agents - The operation groups for agents
+ * @property {BetaOperations} beta - The operation groups for beta include beta features:
+ * - Memory Stores
+ * - Evaluators
+ * - Evaluation Rules
+ * - Evaluation Taxonomies
+ * - Insights
+ * - Schedules
+ * - Red Teams
  * @property {TelemetryOperations} telemetry - The operation groups for telemetry
  * @property {getEndpointUrl} getEndpointUrl - gets the endpoint of the client
- * @property {getOpenAIClient} getOpenAIClient - gets the OpenAI client
+ * @property {getOpenAIClient} getOpenAIClient - gets the OpenAI client with optional OpenAI client options
  */
 export class AIProjectClient {
     _cognitiveScopeClient;
@@ -50,9 +52,7 @@ export class AIProjectClient {
         this._credential = credential;
         this._options = options;
         const prefixFromOptions = options?.userAgentOptions?.userAgentPrefix;
-        const userAgentPrefix = prefixFromOptions
-            ? `${prefixFromOptions} azsdk-js-client`
-            : `azsdk-js-client`;
+        const userAgentPrefix = prefixFromOptions ? `${prefixFromOptions}` : "";
         this._cognitiveScopeClient = createAIProject(endpoint, this._credential, {
             ...options,
             userAgentOptions: { userAgentPrefix },
@@ -65,62 +65,60 @@ export class AIProjectClient {
             ...options,
             userAgentOptions: { userAgentPrefix },
         });
-        this.schedules = _getSchedulesOperations(this._cognitiveScopeClient);
-        this.insights = _getInsightsOperations(this._cognitiveScopeClient);
-        this.evaluators = _getEvaluatorsOperations(this._cognitiveScopeClient);
-        this.evaluationTaxonomies = _getEvaluationTaxonomiesOperations(this._cognitiveScopeClient);
-        this.evaluationRules = _getEvaluationRulesOperations(this._cognitiveScopeClient);
-        this.redTeams = _getRedTeamsOperations(this._cognitiveScopeClient);
-        this.deployments = _getDeploymentsOperations(this._azureScopeClient);
         this.indexes = _getIndexesOperations(this._azureScopeClient);
+        this.deployments = _getDeploymentsOperations(this._azureScopeClient);
         this.datasets = _getDatasetsOperations(this._azureScopeClient, this._options);
         this.connections = _getConnectionsOperations(this._azureScopeClient);
-        this.memoryStores = _getMemoryStoresOperations(this._cognitiveScopeClient);
+        this.evaluationRules = _getEvaluationRulesOperations(this._azureScopeClient);
         this.agents = _getAgentsOperations(this._azureScopeClient);
+        this.beta = _getBetaOperations(this._cognitiveScopeClient);
         this.telemetry = _getTelemetryOperations(this.connections);
     }
-    /** The operation groups for schedules */
-    schedules;
-    /** The operation groups for insights */
-    insights;
-    /** The operation groups for evaluators */
-    evaluators;
-    /** The operation groups for evaluationTaxonomies */
-    evaluationTaxonomies;
-    /** The operation groups for evaluationRules */
-    evaluationRules;
-    /** The operation groups for redTeams */
-    redTeams;
-    /** The operation groups for deployments */
-    deployments;
     /** The operation groups for indexes */
     indexes;
+    /** The operation groups for deployments */
+    deployments;
     /** The operation groups for datasets */
     datasets;
     /** The operation groups for connections */
     connections;
-    /** The operation groups for memoryStores */
-    memoryStores;
+    /** The operation groups for evaluationRules */
+    evaluationRules;
     /** The operation groups for agents */
     agents;
+    /** The operation groups for beta include beta features:
+     * - Memory Stores
+     * - Evaluators
+     * - Evaluation Rules
+     * - Evaluation Taxonomies
+     * - Insights
+     * - Schedules
+     * - Red Teams
+     */
+    beta;
     /** The operation groups for telemetry */
     telemetry;
     /**
      * gets the OpenAI client
      * @returns the OpenAI client
      */
-    async getOpenAIClient() {
+    // eslint-disable-next-line @azure/azure-sdk/ts-naming-options
+    getOpenAIClient(opts) {
         const scope = "https://ai.azure.com/.default";
-        const azureADTokenProvider = await getBearerTokenProvider(this._credential, scope);
         let customFetch;
         if (this._options.additionalPolicies?.find((policy) => policy.policy.name === "recording policy")) {
             customFetch = getCustomFetch(this._azureScopeClient.pipeline, this._options.httpClient);
         }
+        const defaultHeaders = getOpenAIDefaultHeaders(opts?.defaultHeaders, this._options?.userAgentOptions?.userAgentPrefix);
+        // Destructure opts to exclude defaultHeaders, then override specific properties
+        const { defaultHeaders: _ignoredHeaders, ...restOpts } = opts || {};
         const openAIOptions = {
-            apiKey: azureADTokenProvider,
+            ...restOpts,
+            apiKey: getBearerTokenProvider(this._credential, scope),
             baseURL: `${this._endpoint}/openai`,
             defaultQuery: { "api-version": this._options?.apiVersion || "2025-11-15-preview" },
             dangerouslyAllowBrowser: true,
+            defaultHeaders: defaultHeaders.toJSON({ preserveCase: true }),
             fetch: customFetch,
         };
         const openaiClient = new OpenAI(openAIOptions);