diff --git a/packages/langchain/README.md b/packages/langchain/README.md
index 0eb2f2a4..cc787984 100644
--- a/packages/langchain/README.md
+++ b/packages/langchain/README.md
@@ -13,11 +13,7 @@ $ npm install @langchain/openai // if you want to use OpenAI models
 ## Pre-requisites
 
 - [Enable the AI Core service in BTP](https://help.sap.com/docs/sap-ai-core/sap-ai-core-service-guide/initial-setup).
-- Project configured with Node.js v20 or higher and native ESM support enabled.
-- For testing your application locally:
-  - Download a service key for your AI Core service instance.
-  - Create a `.env` file in the sample-code directory.
-  - Add an entry `AICORE_SERVICE_KEY='<content-of-service-key>'`.
+- Ensure the project is configured with Node.js v20 or higher, along with native ESM support.
 
 ## Usage
 
diff --git a/packages/langchain/src/index.ts b/packages/langchain/src/index.ts
index f279b95a..75d19020 100644
--- a/packages/langchain/src/index.ts
+++ b/packages/langchain/src/index.ts
@@ -1,4 +1,4 @@
-export { OpenAiChatClient, OpenAiEmbeddingClient } from './openai/index.js';
+export { AzureOpenAiChatClient, AzureOpenAiEmbeddingClient } from './openai/index.js';
 export type {
   OpenAiChatModelInput,
   OpenAiEmbeddingInput,
diff --git a/packages/langchain/src/openai/chat.ts b/packages/langchain/src/openai/chat.ts
index cee8f8b6..4546f337 100644
--- a/packages/langchain/src/openai/chat.ts
+++ b/packages/langchain/src/openai/chat.ts
@@ -3,31 +3,26 @@ import { BaseMessage } from '@langchain/core/messages';
 import type { ChatResult } from '@langchain/core/outputs';
 import { AzureChatOpenAI, AzureOpenAI } from '@langchain/openai';
 import { OpenAiChatClient as OpenAiChatClientBase } from '@sap-ai-sdk/foundation-models';
-import { mapLangchainToAiClient, mapResponseToChatResult } from './util.js';
+import { mapLangchainToAiClient, mapResponseToChatResult, toArrayOrUndefined } from './util.js';
 import type { OpenAiChatModelInput, OpenAiChatCallOptions } from './types.js';
 
 /**
  * OpenAI Language Model Wrapper to generate texts.
  */
-export class OpenAiChatClient extends AzureChatOpenAI {
+export class AzureOpenAiChatClient extends AzureChatOpenAI {
   declare CallOptions: OpenAiChatCallOptions;
   private openAiChatClient: OpenAiChatClientBase;
 
   constructor(fields: OpenAiChatModelInput) {
     const defaultValues = new AzureOpenAI({ apiKey: 'dummy' });
-    const stop = fields.stop
-      ? Array.isArray(fields.stop)
-        ? fields.stop
-        : [fields.stop]
-      : defaultValues.stop;
+    const stop = toArrayOrUndefined<string>(fields.stop);
     super({
       ...defaultValues,
       ...fields,
       stop,
       // overrides the apikey values as they are not applicable for BTP
       azureOpenAIApiKey: undefined,
-      openAIApiKey: undefined,
-      apiKey: 'dummy'
+      openAIApiKey: undefined
     });
 
     this.openAiChatClient = new OpenAiChatClientBase({ ...fields });
diff --git a/packages/langchain/src/openai/embedding.ts b/packages/langchain/src/openai/embedding.ts
index 82e9c159..ffc5610f 100644
--- a/packages/langchain/src/openai/embedding.ts
+++ b/packages/langchain/src/openai/embedding.ts
@@ -10,7 +10,7 @@ import { OpenAiEmbeddingInput } from './types.js';
 /**
  * OpenAI GPT Language Model Wrapper to embed texts.
  */
-export class OpenAiEmbeddingClient extends AzureOpenAIEmbeddings {
+export class AzureOpenAiEmbeddingClient extends AzureOpenAIEmbeddings {
   private btpOpenAIClient: OpenAiEmbeddingClientBase;
 
   constructor(fields: OpenAiEmbeddingInput) {
@@ -45,9 +45,8 @@ export class OpenAiEmbeddingClient extends AzureOpenAIEmbeddings {
   private async createEmbedding(
     query: OpenAiEmbeddingParameters
   ): Promise<OpenAiEmbeddingOutput> {
-    const res = await this.caller.callWithOptions({}, () =>
+    return this.caller.callWithOptions({}, () =>
       this.btpOpenAIClient.run(query)
     );
-    return res;
   }
 }
diff --git a/packages/langchain/src/openai/util.test.ts b/packages/langchain/src/openai/util.test.ts
index 8ce5cc62..e00d191c 100644
--- a/packages/langchain/src/openai/util.test.ts
+++ b/packages/langchain/src/openai/util.test.ts
@@ -14,7 +14,7 @@ import {
   parseMockResponse
 } from '../../../../test-util/mock-http.js';
 import { mapResponseToChatResult } from './util.js';
-import { OpenAiChatClient } from './chat.js';
+import { AzureOpenAiChatClient } from './chat.js';
 
 const openAiMockResponse = parseMockResponse<OpenAiChatCompletionOutput>(
   'foundation-models',
@@ -98,7 +98,7 @@ describe('Mapping Functions', () => {
       chatCompletionEndpoint
     );
 
-    const client = new OpenAiChatClient({ deploymentId: '1234' });
+    const client = new AzureOpenAiChatClient({ deploymentId: '1234' });
     const runSpy = jest.spyOn(OpenAiChatClientBase.prototype, 'run');
     await client.generate([[langchainPrompt]]);
     expect(runSpy).toHaveBeenCalledWith(request);
diff --git a/packages/langchain/src/openai/util.ts b/packages/langchain/src/openai/util.ts
index 2d1b989a..2a30ec57 100644
--- a/packages/langchain/src/openai/util.ts
+++ b/packages/langchain/src/openai/util.ts
@@ -15,7 +15,7 @@ import type {
   OpenAiChatCompletionParameters
 } from '@sap-ai-sdk/foundation-models';
 import { zodToJsonSchema } from 'zod-to-json-schema';
-import { OpenAiChatClient } from './chat.js';
+import { AzureOpenAiChatClient } from './chat.js';
 import { OpenAiChatCallOptions } from './types.js';
 
 /**
@@ -143,6 +143,18 @@ export function mapBaseMessageToOpenAiChatMessage(
   } as OpenAiChatMessage;
 }
 
+/**
+ * Converts a value to an array or returns undefined.
+ * @param value - The value to convert.
+ * @returns The value as an array, undefined if the input is falsy, or the original array if input is already an array.
+ */
+export function toArrayOrUndefined<T>(value?: T | T[]): T[] | undefined {
+  if(value === undefined) {
+    return undefined;
+  }
+  return Array.isArray(value) ? value : [value];
+}
+
 /**
  * Checks if a given array is a structured tool array.
  * @param tools - The array to check.
@@ -159,15 +171,15 @@ export function isStructuredToolArray(
 }
 
 /**
- * Maps the langchain's input interface to our own client's input interface
+ * Maps Langchain's input interface to our own client's input interface
  * @param client The Langchain OpenAI client
  * @param options The Langchain call options
  * @param messages The messages to be send
- * @returns A AI SDK compatibile request
+ * @returns An AI SDK compatibile request
  * @internal
  */
 export function mapLangchainToAiClient(
-  client: OpenAiChatClient,
+  client: AzureOpenAiChatClient,
   options: OpenAiChatCallOptions,
   messages: BaseMessage[]
 ): OpenAiChatCompletionParameters {