fix(deps): update dependency openai to v4.83.0 #242
Conversation
![renovate[bot]](https://avatars.githubusercontent.com/in/2740?s=60&v=4){kind=small}
|
openai debug - [puLL-Merge] - openai/[email protected] Diffdiff --git .release-please-manifest.json .release-please-manifest.json
index b1ab5c7b9..b2ee58e08 100644
--- .release-please-manifest.json
+++ .release-please-manifest.json
@@ -1,3 +1,3 @@
{
- ".": "4.79.4"
+ ".": "4.82.0"
}
diff --git .stats.yml .stats.yml
index 9600edae3..e49b5c56e 100644
--- .stats.yml
+++ .stats.yml
@@ -1,2 +1,2 @@
configured_endpoints: 69
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-b5b0e2c794b012919701c3fd43286af10fa25d33ceb8a881bec2636028f446e0.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-6204952a29973265b9c0d66fc67ffaf53c6a90ae4d75cdacf9d147676f5274c9.yml
diff --git CHANGELOG.md CHANGELOG.md
index 4254a9b8f..7565cb01a 100644
--- CHANGELOG.md
+++ CHANGELOG.md
@@ -1,5 +1,50 @@
# Changelog
+## 4.82.0 (2025-01-31)
+
+Full Changelog: [v4.81.0...v4.82.0](https://github.com/openai/openai-node/compare/v4.81.0...v4.82.0)
+
+### Features
+
+* **api:** add o3-mini ([#1295](https://github.com/openai/openai-node/issues/1295)) ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+
+### Bug Fixes
+
+* **examples/realtime:** remove duplicate `session.update` call ([#1293](https://github.com/openai/openai-node/issues/1293)) ([ad800b4](https://github.com/openai/openai-node/commit/ad800b4f9410c6838994c24a3386ea708717f72b))
+* **types:** correct metadata type + other fixes ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+## 4.81.0 (2025-01-29)
+
+Full Changelog: [v4.80.1...v4.81.0](https://github.com/openai/openai-node/compare/v4.80.1...v4.81.0)
+
+### Features
+
+* **azure:** Realtime API support ([#1287](https://github.com/openai/openai-node/issues/1287)) ([fe090c0](https://github.com/openai/openai-node/commit/fe090c0a57570217eb0b431e2cce40bf61de2b75))
+
+## 4.80.1 (2025-01-24)
+
+Full Changelog: [v4.80.0...v4.80.1](https://github.com/openai/openai-node/compare/v4.80.0...v4.80.1)
+
+### Bug Fixes
+
+* **azure:** include retry count header ([3e0ba40](https://github.com/openai/openai-node/commit/3e0ba409e57ce276fb1f95cd11c801e4ccaad572))
+
+
+### Documentation
+
+* fix typo, "zodFunctionTool" -> "zodFunction" ([#1128](https://github.com/openai/openai-node/issues/1128)) ([b7ab6bb](https://github.com/openai/openai-node/commit/b7ab6bb304973ade94830f37eb646e800226d5ef))
+* **helpers:** fix type annotation ([fc019df](https://github.com/openai/openai-node/commit/fc019df1d9cc276e8f8e689742853a09aa94991a))
+* **readme:** fix realtime errors docs link ([#1286](https://github.com/openai/openai-node/issues/1286)) ([d1d50c8](https://github.com/openai/openai-node/commit/d1d50c897c18cefea964e8057fe1acfd766ae2bf))
+
+## 4.80.0 (2025-01-22)
+
+Full Changelog: [v4.79.4...v4.80.0](https://github.com/openai/openai-node/compare/v4.79.4...v4.80.0)
+
+### Features
+
+* **api:** update enum values, comments, and examples ([#1280](https://github.com/openai/openai-node/issues/1280)) ([d38f2c2](https://github.com/openai/openai-node/commit/d38f2c2648b6990f217c3c7d83ca31f3739641d3))
+
## 4.79.4 (2025-01-21)
Full Changelog: [v4.79.3...v4.79.4](https://github.com/openai/openai-node/compare/v4.79.3...v4.79.4)
diff --git README.md README.md
index 3bd386e99..a1f4bf760 100644
--- README.md
+++ README.md
@@ -157,7 +157,7 @@ A full example can be found [here](https://github.com/openai/openai-node/blob/ma
### Realtime error handling
-When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime/realtime-api-beta#handling-errors), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
+When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime-model-capabilities#error-handling), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
It is **highly recommended** that you register an `error` event listener and handle errors approriately as typically the underlying connection is still usable.
@@ -499,7 +499,7 @@ const credential = new DefaultAzureCredential();
const scope = 'https://cognitiveservices.azure.com/.default';
const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: "<The API version, e.g. 2024-10-01-preview>" });
const result = await openai.chat.completions.create({
model: 'gpt-4o',
@@ -509,6 +509,26 @@ const result = await openai.chat.completions.create({
console.log(result.choices[0]!.message?.content);
\`\`\`
+### Realtime API
+This SDK provides real-time streaming capabilities for Azure OpenAI through the `OpenAIRealtimeWS` and `OpenAIRealtimeWebSocket` clients described previously.
+
+To utilize the real-time features, begin by creating a fully configured `AzureOpenAI` client and passing it into either `OpenAIRealtimeWS.azure` or `OpenAIRealtimeWebSocket.azure`. For example:
+
+```ts
+const cred = new DefaultAzureCredential();
+const scope = 'https://cognitiveservices.azure.com/.default';
+const deploymentName = 'gpt-4o-realtime-preview-1001';
+const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+});
+const rt = await OpenAIRealtimeWS.azure(client);
+```
+
+Once the instance has been created, you can then begin sending requests and receiving streaming responses in real time.
+
### Retries
Certain errors will be automatically retried 2 times by default, with a short exponential backoff.
diff --git api.md api.md
index 33ab95ef6..516188b20 100644
--- api.md
+++ api.md
@@ -5,6 +5,7 @@ Types:
- <code><a href="./src/resources/shared.ts">ErrorObject</a></code>
- <code><a href="./src/resources/shared.ts">FunctionDefinition</a></code>
- <code><a href="./src/resources/shared.ts">FunctionParameters</a></code>
+- <code><a href="./src/resources/shared.ts">Metadata</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONObject</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONSchema</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatText</a></code>
diff --git examples/azure.ts examples/azure/chat.ts
similarity index 91%
rename from examples/azure.ts
rename to examples/azure/chat.ts
index 5fe1718fa..46df820f8 100755
--- examples/azure.ts
+++ examples/azure/chat.ts
@@ -2,6 +2,7 @@
import { AzureOpenAI } from 'openai';
import { getBearerTokenProvider, DefaultAzureCredential } from '@azure/identity';
+import 'dotenv/config';
// Corresponds to your Model deployment within your OpenAI resource, e.g. gpt-4-1106-preview
// Navigate to the Azure OpenAI Studio to deploy a model.
@@ -13,7 +14,7 @@ const azureADTokenProvider = getBearerTokenProvider(credential, scope);
// Make sure to set AZURE_OPENAI_ENDPOINT with the endpoint of your Azure resource.
// You can find it in the Azure Portal.
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: '2024-10-01-preview' });
async function main() {
console.log('Non-streaming:');
diff --git a/examples/azure/realtime/websocket.ts b/examples/azure/realtime/websocket.ts
new file mode 100644
index 000000000..bec74e654
--- /dev/null
+++ examples/azure/realtime/websocket.ts
@@ -0,0 +1,60 @@
+import { OpenAIRealtimeWebSocket } from 'openai/beta/realtime/websocket';
+import { AzureOpenAI } from 'openai';
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWebSocket.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.addEventListener('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.addEventListener('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git a/examples/azure/realtime/ws.ts b/examples/azure/realtime/ws.ts
new file mode 100644
index 000000000..6ab7b742a
--- /dev/null
+++ examples/azure/realtime/ws.ts
@@ -0,0 +1,60 @@
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import { OpenAIRealtimeWS } from 'openai/beta/realtime/ws';
+import { AzureOpenAI } from 'openai';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWS.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.on('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.on('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git examples/package.json examples/package.json
index b8c34ac45..70ec2c523 100644
--- examples/package.json
+++ examples/package.json
@@ -7,6 +7,7 @@
"private": true,
"dependencies": {
"@azure/identity": "^4.2.0",
+ "dotenv": "^16.4.7",
"express": "^4.18.2",
"next": "^14.1.1",
"openai": "file:..",
diff --git examples/realtime/ws.ts examples/realtime/ws.ts
index 4bbe85e5d..08c6fbcb6 100644
--- examples/realtime/ws.ts
+++ examples/realtime/ws.ts
@@ -6,13 +6,6 @@ async function main() {
// access the underlying `ws.WebSocket` instance
rt.socket.on('open', () => {
console.log('Connection opened!');
- rt.send({
- type: 'session.update',
- session: {
- modalities: ['foo'] as any,
- model: 'gpt-4o-realtime-preview',
- },
- });
rt.send({
type: 'session.update',
session: {
diff --git helpers.md helpers.md
index abf980c82..16bc1f277 100644
--- helpers.md
+++ helpers.md
@@ -49,7 +49,7 @@ if (message?.parsed) {
The `.parse()` method will also automatically parse `function` tool calls if:
-- You use the `zodFunctionTool()` helper method
+- You use the `zodFunction()` helper method
- You mark your tool schema with `"strict": True`
For example:
@@ -226,7 +226,7 @@ on in the documentation page [Message](https://platform.openai.com/docs/api-refe
```ts
.on('textCreated', (content: Text) => ...)
-.on('textDelta', (delta: RunStepDelta, snapshot: Text) => ...)
+.on('textDelta', (delta: TextDelta, snapshot: Text) => ...)
.on('textDone', (content: Text, snapshot: Message) => ...)diff --git jsr.json jsr.json
export class OpenAIRealtimeError extends OpenAIError { -export function buildRealtimeURL(props: { baseURL: string; model: string }): URL {
interface MessageEvent {
@@ -77,6 +84,45 @@ export class OpenAIRealtimeWebSocket extends OpenAIRealtimeEmitter {
send(event: RealtimeClientEvent) { export class OpenAIRealtimeWS extends OpenAIRealtimeEmitter {
+async function getAzureHeaders(client: AzureOpenAI) {
diff --git src/resources/batches.ts src/resources/batches.ts export class Batches extends APIResource { /**
export interface BatchListParams extends CursorPageParams {} /**
import { APIResource } from '../../../resource'; /**
/**
/**
@@ -1723,8 +1764,11 @@ export namespace SessionUpdateEvent {
@@ -1756,8 +1800,19 @@ export namespace SessionUpdateEvent {
@@ -1797,15 +1852,33 @@ export namespace SessionUpdateEvent {
@@ -86,6 +88,7 @@ export interface Session { /**
@@ -200,7 +203,7 @@ export interface SessionCreateResponse {
/** export interface SessionCreateParams {
@@ -390,8 +385,11 @@ export interface SessionCreateParams {
@@ -423,8 +421,19 @@ export interface SessionCreateParams {
@@ -464,15 +473,33 @@ export namespace SessionCreateParams {
export interface Tool { @@ -407,11 +408,13 @@ export interface Message { /**
export namespace MessageCreateParams {
export interface MessageListParams extends CursorPageParams { /**
export namespace AdditionalMessage {
export interface RunListParams extends CursorPageParams { export class Steps extends APIResource { /**
export namespace Message {
@@ -658,7 +671,8 @@ export interface ThreadCreateAndRunParamsBase { export namespace ThreadCreateAndRunParams {
export type ChatModel =
@@ -300,8 +299,7 @@ export interface ChatCompletionChunk { /**
@@ -1014,10 +1012,14 @@ export interface ChatCompletionCreateParamsBase { /**
diff --git src/resources/embeddings.ts src/resources/embeddings.ts
diff --git src/resources/shared.ts src/resources/shared.ts +/**
export interface ResponseFormatJSONObject { /**
@@ -33,7 +33,9 @@ describe('resource assistants', () => {
diff --git tests/api-resources/beta/realtime/sessions.test.ts tests/api-resources/beta/realtime/sessions.test.ts describe('resource sessions', () => {
diff --git tests/api-resources/beta/threads/runs/runs.test.ts tests/api-resources/beta/threads/runs/runs.test.ts
diff --git tests/api-resources/beta/threads/threads.test.ts tests/api-resources/beta/threads/threads.test.ts
@@ -118,7 +120,7 @@ describe('resource threads', () => {
@@ -130,15 +132,17 @@ describe('resource threads', () => {
diff --git tests/api-resources/chat/completions.test.ts tests/api-resources/chat/completions.test.ts
diff --git tests/api-resources/completions.test.ts tests/api-resources/completions.test.ts
diff --git tests/lib/azure.test.ts tests/lib/azure.test.ts
describe('defaultQuery', () => { |
|
anthropic debug - [puLL-Merge] - openai/[email protected] Diffdiff --git .release-please-manifest.json .release-please-manifest.json
index b1ab5c7b9..b2ee58e08 100644
--- .release-please-manifest.json
+++ .release-please-manifest.json
@@ -1,3 +1,3 @@
{
- ".": "4.79.4"
+ ".": "4.82.0"
}
diff --git .stats.yml .stats.yml
index 9600edae3..e49b5c56e 100644
--- .stats.yml
+++ .stats.yml
@@ -1,2 +1,2 @@
configured_endpoints: 69
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-b5b0e2c794b012919701c3fd43286af10fa25d33ceb8a881bec2636028f446e0.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-6204952a29973265b9c0d66fc67ffaf53c6a90ae4d75cdacf9d147676f5274c9.yml
diff --git CHANGELOG.md CHANGELOG.md
index 4254a9b8f..7565cb01a 100644
--- CHANGELOG.md
+++ CHANGELOG.md
@@ -1,5 +1,50 @@
# Changelog
+## 4.82.0 (2025-01-31)
+
+Full Changelog: [v4.81.0...v4.82.0](https://github.com/openai/openai-node/compare/v4.81.0...v4.82.0)
+
+### Features
+
+* **api:** add o3-mini ([#1295](https://github.com/openai/openai-node/issues/1295)) ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+
+### Bug Fixes
+
+* **examples/realtime:** remove duplicate `session.update` call ([#1293](https://github.com/openai/openai-node/issues/1293)) ([ad800b4](https://github.com/openai/openai-node/commit/ad800b4f9410c6838994c24a3386ea708717f72b))
+* **types:** correct metadata type + other fixes ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+## 4.81.0 (2025-01-29)
+
+Full Changelog: [v4.80.1...v4.81.0](https://github.com/openai/openai-node/compare/v4.80.1...v4.81.0)
+
+### Features
+
+* **azure:** Realtime API support ([#1287](https://github.com/openai/openai-node/issues/1287)) ([fe090c0](https://github.com/openai/openai-node/commit/fe090c0a57570217eb0b431e2cce40bf61de2b75))
+
+## 4.80.1 (2025-01-24)
+
+Full Changelog: [v4.80.0...v4.80.1](https://github.com/openai/openai-node/compare/v4.80.0...v4.80.1)
+
+### Bug Fixes
+
+* **azure:** include retry count header ([3e0ba40](https://github.com/openai/openai-node/commit/3e0ba409e57ce276fb1f95cd11c801e4ccaad572))
+
+
+### Documentation
+
+* fix typo, "zodFunctionTool" -> "zodFunction" ([#1128](https://github.com/openai/openai-node/issues/1128)) ([b7ab6bb](https://github.com/openai/openai-node/commit/b7ab6bb304973ade94830f37eb646e800226d5ef))
+* **helpers:** fix type annotation ([fc019df](https://github.com/openai/openai-node/commit/fc019df1d9cc276e8f8e689742853a09aa94991a))
+* **readme:** fix realtime errors docs link ([#1286](https://github.com/openai/openai-node/issues/1286)) ([d1d50c8](https://github.com/openai/openai-node/commit/d1d50c897c18cefea964e8057fe1acfd766ae2bf))
+
+## 4.80.0 (2025-01-22)
+
+Full Changelog: [v4.79.4...v4.80.0](https://github.com/openai/openai-node/compare/v4.79.4...v4.80.0)
+
+### Features
+
+* **api:** update enum values, comments, and examples ([#1280](https://github.com/openai/openai-node/issues/1280)) ([d38f2c2](https://github.com/openai/openai-node/commit/d38f2c2648b6990f217c3c7d83ca31f3739641d3))
+
## 4.79.4 (2025-01-21)
Full Changelog: [v4.79.3...v4.79.4](https://github.com/openai/openai-node/compare/v4.79.3...v4.79.4)
diff --git README.md README.md
index 3bd386e99..a1f4bf760 100644
--- README.md
+++ README.md
@@ -157,7 +157,7 @@ A full example can be found [here](https://github.com/openai/openai-node/blob/ma
### Realtime error handling
-When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime/realtime-api-beta#handling-errors), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
+When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime-model-capabilities#error-handling), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
It is **highly recommended** that you register an `error` event listener and handle errors approriately as typically the underlying connection is still usable.
@@ -499,7 +499,7 @@ const credential = new DefaultAzureCredential();
const scope = 'https://cognitiveservices.azure.com/.default';
const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: "<The API version, e.g. 2024-10-01-preview>" });
const result = await openai.chat.completions.create({
model: 'gpt-4o',
@@ -509,6 +509,26 @@ const result = await openai.chat.completions.create({
console.log(result.choices[0]!.message?.content);
\`\`\`
+### Realtime API
+This SDK provides real-time streaming capabilities for Azure OpenAI through the `OpenAIRealtimeWS` and `OpenAIRealtimeWebSocket` clients described previously.
+
+To utilize the real-time features, begin by creating a fully configured `AzureOpenAI` client and passing it into either `OpenAIRealtimeWS.azure` or `OpenAIRealtimeWebSocket.azure`. For example:
+
+```ts
+const cred = new DefaultAzureCredential();
+const scope = 'https://cognitiveservices.azure.com/.default';
+const deploymentName = 'gpt-4o-realtime-preview-1001';
+const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+});
+const rt = await OpenAIRealtimeWS.azure(client);
+```
+
+Once the instance has been created, you can then begin sending requests and receiving streaming responses in real time.
+
### Retries
Certain errors will be automatically retried 2 times by default, with a short exponential backoff.
diff --git api.md api.md
index 33ab95ef6..516188b20 100644
--- api.md
+++ api.md
@@ -5,6 +5,7 @@ Types:
- <code><a href="./src/resources/shared.ts">ErrorObject</a></code>
- <code><a href="./src/resources/shared.ts">FunctionDefinition</a></code>
- <code><a href="./src/resources/shared.ts">FunctionParameters</a></code>
+- <code><a href="./src/resources/shared.ts">Metadata</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONObject</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONSchema</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatText</a></code>
diff --git examples/azure.ts examples/azure/chat.ts
similarity index 91%
rename from examples/azure.ts
rename to examples/azure/chat.ts
index 5fe1718fa..46df820f8 100755
--- examples/azure.ts
+++ examples/azure/chat.ts
@@ -2,6 +2,7 @@
import { AzureOpenAI } from 'openai';
import { getBearerTokenProvider, DefaultAzureCredential } from '@azure/identity';
+import 'dotenv/config';
// Corresponds to your Model deployment within your OpenAI resource, e.g. gpt-4-1106-preview
// Navigate to the Azure OpenAI Studio to deploy a model.
@@ -13,7 +14,7 @@ const azureADTokenProvider = getBearerTokenProvider(credential, scope);
// Make sure to set AZURE_OPENAI_ENDPOINT with the endpoint of your Azure resource.
// You can find it in the Azure Portal.
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: '2024-10-01-preview' });
async function main() {
console.log('Non-streaming:');
diff --git a/examples/azure/realtime/websocket.ts b/examples/azure/realtime/websocket.ts
new file mode 100644
index 000000000..bec74e654
--- /dev/null
+++ examples/azure/realtime/websocket.ts
@@ -0,0 +1,60 @@
+import { OpenAIRealtimeWebSocket } from 'openai/beta/realtime/websocket';
+import { AzureOpenAI } from 'openai';
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWebSocket.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.addEventListener('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.addEventListener('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git a/examples/azure/realtime/ws.ts b/examples/azure/realtime/ws.ts
new file mode 100644
index 000000000..6ab7b742a
--- /dev/null
+++ examples/azure/realtime/ws.ts
@@ -0,0 +1,60 @@
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import { OpenAIRealtimeWS } from 'openai/beta/realtime/ws';
+import { AzureOpenAI } from 'openai';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWS.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.on('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.on('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git examples/package.json examples/package.json
index b8c34ac45..70ec2c523 100644
--- examples/package.json
+++ examples/package.json
@@ -7,6 +7,7 @@
"private": true,
"dependencies": {
"@azure/identity": "^4.2.0",
+ "dotenv": "^16.4.7",
"express": "^4.18.2",
"next": "^14.1.1",
"openai": "file:..",
diff --git examples/realtime/ws.ts examples/realtime/ws.ts
index 4bbe85e5d..08c6fbcb6 100644
--- examples/realtime/ws.ts
+++ examples/realtime/ws.ts
@@ -6,13 +6,6 @@ async function main() {
// access the underlying `ws.WebSocket` instance
rt.socket.on('open', () => {
console.log('Connection opened!');
- rt.send({
- type: 'session.update',
- session: {
- modalities: ['foo'] as any,
- model: 'gpt-4o-realtime-preview',
- },
- });
rt.send({
type: 'session.update',
session: {
diff --git helpers.md helpers.md
index abf980c82..16bc1f277 100644
--- helpers.md
+++ helpers.md
@@ -49,7 +49,7 @@ if (message?.parsed) {
The `.parse()` method will also automatically parse `function` tool calls if:
-- You use the `zodFunctionTool()` helper method
+- You use the `zodFunction()` helper method
- You mark your tool schema with `"strict": True`
For example:
@@ -226,7 +226,7 @@ on in the documentation page [Message](https://platform.openai.com/docs/api-refe
```ts
.on('textCreated', (content: Text) => ...)
-.on('textDelta', (delta: RunStepDelta, snapshot: Text) => ...)
+.on('textDelta', (delta: TextDelta, snapshot: Text) => ...)
.on('textDone', (content: Text, snapshot: Message) => ...)diff --git jsr.json jsr.json
export class OpenAIRealtimeError extends OpenAIError { -export function buildRealtimeURL(props: { baseURL: string; model: string }): URL {
interface MessageEvent {
@@ -77,6 +84,45 @@ export class OpenAIRealtimeWebSocket extends OpenAIRealtimeEmitter {
send(event: RealtimeClientEvent) { export class OpenAIRealtimeWS extends OpenAIRealtimeEmitter {
+async function getAzureHeaders(client: AzureOpenAI) {
diff --git src/resources/batches.ts src/resources/batches.ts export class Batches extends APIResource { /**
export interface BatchListParams extends CursorPageParams {} /**
import { APIResource } from '../../../resource'; /**
/**
/**
@@ -1723,8 +1764,11 @@ export namespace SessionUpdateEvent {
@@ -1756,8 +1800,19 @@ export namespace SessionUpdateEvent {
@@ -1797,15 +1852,33 @@ export namespace SessionUpdateEvent {
@@ -86,6 +88,7 @@ export interface Session { /**
@@ -200,7 +203,7 @@ export interface SessionCreateResponse {
/** export interface SessionCreateParams {
@@ -390,8 +385,11 @@ export interface SessionCreateParams {
@@ -423,8 +421,19 @@ export interface SessionCreateParams {
@@ -464,15 +473,33 @@ export namespace SessionCreateParams {
export interface Tool { @@ -407,11 +408,13 @@ export interface Message { /**
export namespace MessageCreateParams {
export interface MessageListParams extends CursorPageParams { /**
export namespace AdditionalMessage {
export interface RunListParams extends CursorPageParams { export class Steps extends APIResource { /**
export namespace Message {
@@ -658,7 +671,8 @@ export interface ThreadCreateAndRunParamsBase { export namespace ThreadCreateAndRunParams {
export type ChatModel =
@@ -300,8 +299,7 @@ export interface ChatCompletionChunk { /**
@@ -1014,10 +1012,14 @@ export interface ChatCompletionCreateParamsBase { /**
diff --git src/resources/embeddings.ts src/resources/embeddings.ts
diff --git src/resources/shared.ts src/resources/shared.ts +/**
export interface ResponseFormatJSONObject { /**
@@ -33,7 +33,9 @@ describe('resource assistants', () => {
diff --git tests/api-resources/beta/realtime/sessions.test.ts tests/api-resources/beta/realtime/sessions.test.ts describe('resource sessions', () => {
diff --git tests/api-resources/beta/threads/runs/runs.test.ts tests/api-resources/beta/threads/runs/runs.test.ts
diff --git tests/api-resources/beta/threads/threads.test.ts tests/api-resources/beta/threads/threads.test.ts
@@ -118,7 +120,7 @@ describe('resource threads', () => {
@@ -130,15 +132,17 @@ describe('resource threads', () => {
diff --git tests/api-resources/chat/completions.test.ts tests/api-resources/chat/completions.test.ts
diff --git tests/api-resources/completions.test.ts tests/api-resources/completions.test.ts
diff --git tests/lib/azure.test.ts tests/lib/azure.test.ts
describe('defaultQuery', () => { Possible Issues
Security Hotspots
|
|
bedrock debug - [puLL-Merge] - openai/[email protected] Diffdiff --git .release-please-manifest.json .release-please-manifest.json
index b1ab5c7b9..b2ee58e08 100644
--- .release-please-manifest.json
+++ .release-please-manifest.json
@@ -1,3 +1,3 @@
{
- ".": "4.79.4"
+ ".": "4.82.0"
}
diff --git .stats.yml .stats.yml
index 9600edae3..e49b5c56e 100644
--- .stats.yml
+++ .stats.yml
@@ -1,2 +1,2 @@
configured_endpoints: 69
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-b5b0e2c794b012919701c3fd43286af10fa25d33ceb8a881bec2636028f446e0.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-6204952a29973265b9c0d66fc67ffaf53c6a90ae4d75cdacf9d147676f5274c9.yml
diff --git CHANGELOG.md CHANGELOG.md
index 4254a9b8f..7565cb01a 100644
--- CHANGELOG.md
+++ CHANGELOG.md
@@ -1,5 +1,50 @@
# Changelog
+## 4.82.0 (2025-01-31)
+
+Full Changelog: [v4.81.0...v4.82.0](https://github.com/openai/openai-node/compare/v4.81.0...v4.82.0)
+
+### Features
+
+* **api:** add o3-mini ([#1295](https://github.com/openai/openai-node/issues/1295)) ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+
+### Bug Fixes
+
+* **examples/realtime:** remove duplicate `session.update` call ([#1293](https://github.com/openai/openai-node/issues/1293)) ([ad800b4](https://github.com/openai/openai-node/commit/ad800b4f9410c6838994c24a3386ea708717f72b))
+* **types:** correct metadata type + other fixes ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+## 4.81.0 (2025-01-29)
+
+Full Changelog: [v4.80.1...v4.81.0](https://github.com/openai/openai-node/compare/v4.80.1...v4.81.0)
+
+### Features
+
+* **azure:** Realtime API support ([#1287](https://github.com/openai/openai-node/issues/1287)) ([fe090c0](https://github.com/openai/openai-node/commit/fe090c0a57570217eb0b431e2cce40bf61de2b75))
+
+## 4.80.1 (2025-01-24)
+
+Full Changelog: [v4.80.0...v4.80.1](https://github.com/openai/openai-node/compare/v4.80.0...v4.80.1)
+
+### Bug Fixes
+
+* **azure:** include retry count header ([3e0ba40](https://github.com/openai/openai-node/commit/3e0ba409e57ce276fb1f95cd11c801e4ccaad572))
+
+
+### Documentation
+
+* fix typo, "zodFunctionTool" -> "zodFunction" ([#1128](https://github.com/openai/openai-node/issues/1128)) ([b7ab6bb](https://github.com/openai/openai-node/commit/b7ab6bb304973ade94830f37eb646e800226d5ef))
+* **helpers:** fix type annotation ([fc019df](https://github.com/openai/openai-node/commit/fc019df1d9cc276e8f8e689742853a09aa94991a))
+* **readme:** fix realtime errors docs link ([#1286](https://github.com/openai/openai-node/issues/1286)) ([d1d50c8](https://github.com/openai/openai-node/commit/d1d50c897c18cefea964e8057fe1acfd766ae2bf))
+
+## 4.80.0 (2025-01-22)
+
+Full Changelog: [v4.79.4...v4.80.0](https://github.com/openai/openai-node/compare/v4.79.4...v4.80.0)
+
+### Features
+
+* **api:** update enum values, comments, and examples ([#1280](https://github.com/openai/openai-node/issues/1280)) ([d38f2c2](https://github.com/openai/openai-node/commit/d38f2c2648b6990f217c3c7d83ca31f3739641d3))
+
## 4.79.4 (2025-01-21)
Full Changelog: [v4.79.3...v4.79.4](https://github.com/openai/openai-node/compare/v4.79.3...v4.79.4)
diff --git README.md README.md
index 3bd386e99..a1f4bf760 100644
--- README.md
+++ README.md
@@ -157,7 +157,7 @@ A full example can be found [here](https://github.com/openai/openai-node/blob/ma
### Realtime error handling
-When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime/realtime-api-beta#handling-errors), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
+When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime-model-capabilities#error-handling), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
It is **highly recommended** that you register an `error` event listener and handle errors approriately as typically the underlying connection is still usable.
@@ -499,7 +499,7 @@ const credential = new DefaultAzureCredential();
const scope = 'https://cognitiveservices.azure.com/.default';
const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: "<The API version, e.g. 2024-10-01-preview>" });
const result = await openai.chat.completions.create({
model: 'gpt-4o',
@@ -509,6 +509,26 @@ const result = await openai.chat.completions.create({
console.log(result.choices[0]!.message?.content);
\`\`\`
+### Realtime API
+This SDK provides real-time streaming capabilities for Azure OpenAI through the `OpenAIRealtimeWS` and `OpenAIRealtimeWebSocket` clients described previously.
+
+To utilize the real-time features, begin by creating a fully configured `AzureOpenAI` client and passing it into either `OpenAIRealtimeWS.azure` or `OpenAIRealtimeWebSocket.azure`. For example:
+
+```ts
+const cred = new DefaultAzureCredential();
+const scope = 'https://cognitiveservices.azure.com/.default';
+const deploymentName = 'gpt-4o-realtime-preview-1001';
+const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+});
+const rt = await OpenAIRealtimeWS.azure(client);
+```
+
+Once the instance has been created, you can then begin sending requests and receiving streaming responses in real time.
+
### Retries
Certain errors will be automatically retried 2 times by default, with a short exponential backoff.
diff --git api.md api.md
index 33ab95ef6..516188b20 100644
--- api.md
+++ api.md
@@ -5,6 +5,7 @@ Types:
- <code><a href="./src/resources/shared.ts">ErrorObject</a></code>
- <code><a href="./src/resources/shared.ts">FunctionDefinition</a></code>
- <code><a href="./src/resources/shared.ts">FunctionParameters</a></code>
+- <code><a href="./src/resources/shared.ts">Metadata</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONObject</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONSchema</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatText</a></code>
diff --git examples/azure.ts examples/azure/chat.ts
similarity index 91%
rename from examples/azure.ts
rename to examples/azure/chat.ts
index 5fe1718fa..46df820f8 100755
--- examples/azure.ts
+++ examples/azure/chat.ts
@@ -2,6 +2,7 @@
import { AzureOpenAI } from 'openai';
import { getBearerTokenProvider, DefaultAzureCredential } from '@azure/identity';
+import 'dotenv/config';
// Corresponds to your Model deployment within your OpenAI resource, e.g. gpt-4-1106-preview
// Navigate to the Azure OpenAI Studio to deploy a model.
@@ -13,7 +14,7 @@ const azureADTokenProvider = getBearerTokenProvider(credential, scope);
// Make sure to set AZURE_OPENAI_ENDPOINT with the endpoint of your Azure resource.
// You can find it in the Azure Portal.
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: '2024-10-01-preview' });
async function main() {
console.log('Non-streaming:');
diff --git a/examples/azure/realtime/websocket.ts b/examples/azure/realtime/websocket.ts
new file mode 100644
index 000000000..bec74e654
--- /dev/null
+++ examples/azure/realtime/websocket.ts
@@ -0,0 +1,60 @@
+import { OpenAIRealtimeWebSocket } from 'openai/beta/realtime/websocket';
+import { AzureOpenAI } from 'openai';
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWebSocket.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.addEventListener('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.addEventListener('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git a/examples/azure/realtime/ws.ts b/examples/azure/realtime/ws.ts
new file mode 100644
index 000000000..6ab7b742a
--- /dev/null
+++ examples/azure/realtime/ws.ts
@@ -0,0 +1,60 @@
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import { OpenAIRealtimeWS } from 'openai/beta/realtime/ws';
+import { AzureOpenAI } from 'openai';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWS.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.on('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.on('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git examples/package.json examples/package.json
index b8c34ac45..70ec2c523 100644
--- examples/package.json
+++ examples/package.json
@@ -7,6 +7,7 @@
"private": true,
"dependencies": {
"@azure/identity": "^4.2.0",
+ "dotenv": "^16.4.7",
"express": "^4.18.2",
"next": "^14.1.1",
"openai": "file:..",
diff --git examples/realtime/ws.ts examples/realtime/ws.ts
index 4bbe85e5d..08c6fbcb6 100644
--- examples/realtime/ws.ts
+++ examples/realtime/ws.ts
@@ -6,13 +6,6 @@ async function main() {
// access the underlying `ws.WebSocket` instance
rt.socket.on('open', () => {
console.log('Connection opened!');
- rt.send({
- type: 'session.update',
- session: {
- modalities: ['foo'] as any,
- model: 'gpt-4o-realtime-preview',
- },
- });
rt.send({
type: 'session.update',
session: {
diff --git helpers.md helpers.md
index abf980c82..16bc1f277 100644
--- helpers.md
+++ helpers.md
@@ -49,7 +49,7 @@ if (message?.parsed) {
The `.parse()` method will also automatically parse `function` tool calls if:
-- You use the `zodFunctionTool()` helper method
+- You use the `zodFunction()` helper method
- You mark your tool schema with `"strict": True`
For example:
@@ -226,7 +226,7 @@ on in the documentation page [Message](https://platform.openai.com/docs/api-refe
```ts
.on('textCreated', (content: Text) => ...)
-.on('textDelta', (delta: RunStepDelta, snapshot: Text) => ...)
+.on('textDelta', (delta: TextDelta, snapshot: Text) => ...)
.on('textDone', (content: Text, snapshot: Message) => ...)diff --git jsr.json jsr.json
export class OpenAIRealtimeError extends OpenAIError { -export function buildRealtimeURL(props: { baseURL: string; model: string }): URL {
interface MessageEvent {
@@ -77,6 +84,45 @@ export class OpenAIRealtimeWebSocket extends OpenAIRealtimeEmitter {
send(event: RealtimeClientEvent) { export class OpenAIRealtimeWS extends OpenAIRealtimeEmitter {
+async function getAzureHeaders(client: AzureOpenAI) {
diff --git src/resources/batches.ts src/resources/batches.ts export class Batches extends APIResource { /**
export interface BatchListParams extends CursorPageParams {} /**
import { APIResource } from '../../../resource'; /**
/**
/**
@@ -1723,8 +1764,11 @@ export namespace SessionUpdateEvent {
@@ -1756,8 +1800,19 @@ export namespace SessionUpdateEvent {
@@ -1797,15 +1852,33 @@ export namespace SessionUpdateEvent {
@@ -86,6 +88,7 @@ export interface Session { /**
@@ -200,7 +203,7 @@ export interface SessionCreateResponse {
/** export interface SessionCreateParams {
@@ -390,8 +385,11 @@ export interface SessionCreateParams {
@@ -423,8 +421,19 @@ export interface SessionCreateParams {
@@ -464,15 +473,33 @@ export namespace SessionCreateParams {
export interface Tool { @@ -407,11 +408,13 @@ export interface Message { /**
export namespace MessageCreateParams {
export interface MessageListParams extends CursorPageParams { /**
export namespace AdditionalMessage {
export interface RunListParams extends CursorPageParams { export class Steps extends APIResource { /**
export namespace Message {
@@ -658,7 +671,8 @@ export interface ThreadCreateAndRunParamsBase { export namespace ThreadCreateAndRunParams {
export type ChatModel =
@@ -300,8 +299,7 @@ export interface ChatCompletionChunk { /**
@@ -1014,10 +1012,14 @@ export interface ChatCompletionCreateParamsBase { /**
diff --git src/resources/embeddings.ts src/resources/embeddings.ts
diff --git src/resources/shared.ts src/resources/shared.ts +/**
export interface ResponseFormatJSONObject { /**
@@ -33,7 +33,9 @@ describe('resource assistants', () => {
diff --git tests/api-resources/beta/realtime/sessions.test.ts tests/api-resources/beta/realtime/sessions.test.ts describe('resource sessions', () => {
diff --git tests/api-resources/beta/threads/runs/runs.test.ts tests/api-resources/beta/threads/runs/runs.test.ts
diff --git tests/api-resources/beta/threads/threads.test.ts tests/api-resources/beta/threads/threads.test.ts
@@ -118,7 +120,7 @@ describe('resource threads', () => {
@@ -130,15 +132,17 @@ describe('resource threads', () => {
diff --git tests/api-resources/chat/completions.test.ts tests/api-resources/chat/completions.test.ts
diff --git tests/api-resources/completions.test.ts tests/api-resources/completions.test.ts
diff --git tests/lib/azure.test.ts tests/lib/azure.test.ts
describe('defaultQuery', () => { Security Hotspots
|
renovate
bot
changed the title
renovate
bot
force-pushed
the
renovate/openai-4.x-lockfile
branch
from
9ef032a to
2a0f0f5
Compare
|
anthropic debug - [puLL-Merge] - openai/[email protected] Diffdiff --git .release-please-manifest.json .release-please-manifest.json
index b1ab5c7b9..6eb0f130e 100644
--- .release-please-manifest.json
+++ .release-please-manifest.json
@@ -1,3 +1,3 @@
{
- ".": "4.79.4"
+ ".": "4.83.0"
}
diff --git .stats.yml .stats.yml
index 9600edae3..df7877dfd 100644
--- .stats.yml
+++ .stats.yml
@@ -1,2 +1,2 @@
configured_endpoints: 69
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-b5b0e2c794b012919701c3fd43286af10fa25d33ceb8a881bec2636028f446e0.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-fc5dbc19505b0035f9e7f88868619f4fb519b048bde011f6154f3132d4be71fb.yml
diff --git CHANGELOG.md CHANGELOG.md
index 4254a9b8f..f61def5e4 100644
--- CHANGELOG.md
+++ CHANGELOG.md
@@ -1,5 +1,64 @@
# Changelog
+## 4.83.0 (2025-02-05)
+
+Full Changelog: [v4.82.0...v4.83.0](https://github.com/openai/openai-node/compare/v4.82.0...v4.83.0)
+
+### Features
+
+* **client:** send `X-Stainless-Timeout` header ([#1299](https://github.com/openai/openai-node/issues/1299)) ([ddfc686](https://github.com/openai/openai-node/commit/ddfc686f43a3420c3adf8dec2e82b4d10a121eb8))
+
+
+### Bug Fixes
+
+* **api/types:** correct audio duration & role types ([#1300](https://github.com/openai/openai-node/issues/1300)) ([a955ac2](https://github.com/openai/openai-node/commit/a955ac2bf5bee663d530d0c82b0005bf3ce6fc47))
+* **azure/audio:** use model param for deployments ([#1297](https://github.com/openai/openai-node/issues/1297)) ([85de382](https://github.com/openai/openai-node/commit/85de382db17cbe5f112650e79d0fc1cc841efbb2))
+
+## 4.82.0 (2025-01-31)
+
+Full Changelog: [v4.81.0...v4.82.0](https://github.com/openai/openai-node/compare/v4.81.0...v4.82.0)
+
+### Features
+
+* **api:** add o3-mini ([#1295](https://github.com/openai/openai-node/issues/1295)) ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+
+### Bug Fixes
+
+* **examples/realtime:** remove duplicate `session.update` call ([#1293](https://github.com/openai/openai-node/issues/1293)) ([ad800b4](https://github.com/openai/openai-node/commit/ad800b4f9410c6838994c24a3386ea708717f72b))
+* **types:** correct metadata type + other fixes ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+## 4.81.0 (2025-01-29)
+
+Full Changelog: [v4.80.1...v4.81.0](https://github.com/openai/openai-node/compare/v4.80.1...v4.81.0)
+
+### Features
+
+* **azure:** Realtime API support ([#1287](https://github.com/openai/openai-node/issues/1287)) ([fe090c0](https://github.com/openai/openai-node/commit/fe090c0a57570217eb0b431e2cce40bf61de2b75))
+
+## 4.80.1 (2025-01-24)
+
+Full Changelog: [v4.80.0...v4.80.1](https://github.com/openai/openai-node/compare/v4.80.0...v4.80.1)
+
+### Bug Fixes
+
+* **azure:** include retry count header ([3e0ba40](https://github.com/openai/openai-node/commit/3e0ba409e57ce276fb1f95cd11c801e4ccaad572))
+
+
+### Documentation
+
+* fix typo, "zodFunctionTool" -> "zodFunction" ([#1128](https://github.com/openai/openai-node/issues/1128)) ([b7ab6bb](https://github.com/openai/openai-node/commit/b7ab6bb304973ade94830f37eb646e800226d5ef))
+* **helpers:** fix type annotation ([fc019df](https://github.com/openai/openai-node/commit/fc019df1d9cc276e8f8e689742853a09aa94991a))
+* **readme:** fix realtime errors docs link ([#1286](https://github.com/openai/openai-node/issues/1286)) ([d1d50c8](https://github.com/openai/openai-node/commit/d1d50c897c18cefea964e8057fe1acfd766ae2bf))
+
+## 4.80.0 (2025-01-22)
+
+Full Changelog: [v4.79.4...v4.80.0](https://github.com/openai/openai-node/compare/v4.79.4...v4.80.0)
+
+### Features
+
+* **api:** update enum values, comments, and examples ([#1280](https://github.com/openai/openai-node/issues/1280)) ([d38f2c2](https://github.com/openai/openai-node/commit/d38f2c2648b6990f217c3c7d83ca31f3739641d3))
+
## 4.79.4 (2025-01-21)
Full Changelog: [v4.79.3...v4.79.4](https://github.com/openai/openai-node/compare/v4.79.3...v4.79.4)
diff --git README.md README.md
index 3bd386e99..a1f4bf760 100644
--- README.md
+++ README.md
@@ -157,7 +157,7 @@ A full example can be found [here](https://github.com/openai/openai-node/blob/ma
### Realtime error handling
-When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime/realtime-api-beta#handling-errors), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
+When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime-model-capabilities#error-handling), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
It is **highly recommended** that you register an `error` event listener and handle errors approriately as typically the underlying connection is still usable.
@@ -499,7 +499,7 @@ const credential = new DefaultAzureCredential();
const scope = 'https://cognitiveservices.azure.com/.default';
const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: "<The API version, e.g. 2024-10-01-preview>" });
const result = await openai.chat.completions.create({
model: 'gpt-4o',
@@ -509,6 +509,26 @@ const result = await openai.chat.completions.create({
console.log(result.choices[0]!.message?.content);
\`\`\`
+### Realtime API
+This SDK provides real-time streaming capabilities for Azure OpenAI through the `OpenAIRealtimeWS` and `OpenAIRealtimeWebSocket` clients described previously.
+
+To utilize the real-time features, begin by creating a fully configured `AzureOpenAI` client and passing it into either `OpenAIRealtimeWS.azure` or `OpenAIRealtimeWebSocket.azure`. For example:
+
+```ts
+const cred = new DefaultAzureCredential();
+const scope = 'https://cognitiveservices.azure.com/.default';
+const deploymentName = 'gpt-4o-realtime-preview-1001';
+const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+});
+const rt = await OpenAIRealtimeWS.azure(client);
+```
+
+Once the instance has been created, you can then begin sending requests and receiving streaming responses in real time.
+
### Retries
Certain errors will be automatically retried 2 times by default, with a short exponential backoff.
diff --git api.md api.md
index 33ab95ef6..01854a8e0 100644
--- api.md
+++ api.md
@@ -5,6 +5,7 @@ Types:
- <code><a href="./src/resources/shared.ts">ErrorObject</a></code>
- <code><a href="./src/resources/shared.ts">FunctionDefinition</a></code>
- <code><a href="./src/resources/shared.ts">FunctionParameters</a></code>
+- <code><a href="./src/resources/shared.ts">Metadata</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONObject</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONSchema</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatText</a></code>
@@ -228,6 +229,7 @@ Types:
- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemInputAudioTranscriptionFailedEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemTruncateEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemTruncatedEvent</a></code>
+- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemWithReference</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">ErrorEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">InputAudioBufferAppendEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">InputAudioBufferClearEvent</a></code>
diff --git examples/azure.ts examples/azure/chat.ts
similarity index 91%
rename from examples/azure.ts
rename to examples/azure/chat.ts
index 5fe1718fa..46df820f8 100755
--- examples/azure.ts
+++ examples/azure/chat.ts
@@ -2,6 +2,7 @@
import { AzureOpenAI } from 'openai';
import { getBearerTokenProvider, DefaultAzureCredential } from '@azure/identity';
+import 'dotenv/config';
// Corresponds to your Model deployment within your OpenAI resource, e.g. gpt-4-1106-preview
// Navigate to the Azure OpenAI Studio to deploy a model.
@@ -13,7 +14,7 @@ const azureADTokenProvider = getBearerTokenProvider(credential, scope);
// Make sure to set AZURE_OPENAI_ENDPOINT with the endpoint of your Azure resource.
// You can find it in the Azure Portal.
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: '2024-10-01-preview' });
async function main() {
console.log('Non-streaming:');
diff --git a/examples/azure/realtime/websocket.ts b/examples/azure/realtime/websocket.ts
new file mode 100644
index 000000000..bec74e654
--- /dev/null
+++ examples/azure/realtime/websocket.ts
@@ -0,0 +1,60 @@
+import { OpenAIRealtimeWebSocket } from 'openai/beta/realtime/websocket';
+import { AzureOpenAI } from 'openai';
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWebSocket.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.addEventListener('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.addEventListener('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git a/examples/azure/realtime/ws.ts b/examples/azure/realtime/ws.ts
new file mode 100644
index 000000000..6ab7b742a
--- /dev/null
+++ examples/azure/realtime/ws.ts
@@ -0,0 +1,60 @@
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import { OpenAIRealtimeWS } from 'openai/beta/realtime/ws';
+import { AzureOpenAI } from 'openai';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWS.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.on('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.on('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git examples/package.json examples/package.json
index b8c34ac45..70ec2c523 100644
--- examples/package.json
+++ examples/package.json
@@ -7,6 +7,7 @@
"private": true,
"dependencies": {
"@azure/identity": "^4.2.0",
+ "dotenv": "^16.4.7",
"express": "^4.18.2",
"next": "^14.1.1",
"openai": "file:..",
diff --git examples/realtime/ws.ts examples/realtime/ws.ts
index 4bbe85e5d..08c6fbcb6 100644
--- examples/realtime/ws.ts
+++ examples/realtime/ws.ts
@@ -6,13 +6,6 @@ async function main() {
// access the underlying `ws.WebSocket` instance
rt.socket.on('open', () => {
console.log('Connection opened!');
- rt.send({
- type: 'session.update',
- session: {
- modalities: ['foo'] as any,
- model: 'gpt-4o-realtime-preview',
- },
- });
rt.send({
type: 'session.update',
session: {
diff --git helpers.md helpers.md
index abf980c82..16bc1f277 100644
--- helpers.md
+++ helpers.md
@@ -49,7 +49,7 @@ if (message?.parsed) {
The `.parse()` method will also automatically parse `function` tool calls if:
-- You use the `zodFunctionTool()` helper method
+- You use the `zodFunction()` helper method
- You mark your tool schema with `"strict": True`
For example:
@@ -226,7 +226,7 @@ on in the documentation page [Message](https://platform.openai.com/docs/api-refe
```ts
.on('textCreated', (content: Text) => ...)
-.on('textDelta', (delta: RunStepDelta, snapshot: Text) => ...)
+.on('textDelta', (delta: TextDelta, snapshot: Text) => ...)
.on('textDone', (content: Text, snapshot: Message) => ...)diff --git jsr.json jsr.json
export class OpenAIRealtimeError extends OpenAIError { -export function buildRealtimeURL(props: { baseURL: string; model: string }): URL {
interface MessageEvent {
@@ -77,6 +84,45 @@ export class OpenAIRealtimeWebSocket extends OpenAIRealtimeEmitter {
send(event: RealtimeClientEvent) { export class OpenAIRealtimeWS extends OpenAIRealtimeEmitter {
+async function getAzureHeaders(client: AzureOpenAI) {
private buildHeaders({
@@ -814,6 +822,7 @@ export type RequestOptions<
@@ -103,7 +106,7 @@ export interface TranscriptionVerbose {
diff --git src/resources/audio/translations.ts src/resources/audio/translations.ts
@@ -38,7 +41,7 @@ export interface TranslationVerbose {
export class Batches extends APIResource { /**
export interface BatchListParams extends CursorPageParams {} /**
import { APIResource } from '../../../resource'; /**
+/**
/**
/**
/**
@@ -1723,8 +1835,11 @@ export namespace SessionUpdateEvent {
@@ -1756,8 +1871,19 @@ export namespace SessionUpdateEvent {
@@ -1797,15 +1923,33 @@ export namespace SessionUpdateEvent {
@@ -86,6 +88,7 @@ export interface Session { /**
@@ -200,7 +203,7 @@ export interface SessionCreateResponse {
/** export interface SessionCreateParams {
@@ -390,8 +385,11 @@ export interface SessionCreateParams {
@@ -423,8 +421,19 @@ export interface SessionCreateParams {
@@ -464,15 +473,33 @@ export namespace SessionCreateParams {
export interface Tool { @@ -407,11 +408,13 @@ export interface Message { /**
export namespace MessageCreateParams {
export interface MessageListParams extends CursorPageParams { /**
export namespace AdditionalMessage {
export interface RunListParams extends CursorPageParams { export class Steps extends APIResource { /**
export namespace Message {
@@ -658,7 +671,8 @@ export interface ThreadCreateAndRunParamsBase { export namespace ThreadCreateAndRunParams {
export type ChatModel =
@@ -300,8 +299,7 @@ export interface ChatCompletionChunk { /**
@@ -373,7 +371,7 @@ export namespace ChatCompletionChunk {
/**
/**
diff --git src/resources/embeddings.ts src/resources/embeddings.ts
diff --git src/resources/shared.ts src/resources/shared.ts +/**
export interface ResponseFormatJSONObject { /**
@@ -33,7 +33,9 @@ describe('resource assistants', () => {
diff --git tests/api-resources/beta/realtime/sessions.test.ts tests/api-resources/beta/realtime/sessions.test.ts describe('resource sessions', () => {
diff --git tests/api-resources/beta/threads/runs/runs.test.ts tests/api-resources/beta/threads/runs/runs.test.ts
diff --git tests/api-resources/beta/threads/threads.test.ts tests/api-resources/beta/threads/threads.test.ts
@@ -118,7 +120,7 @@ describe('resource threads', () => {
@@ -130,15 +132,17 @@ describe('resource threads', () => {
diff --git tests/api-resources/chat/completions.test.ts tests/api-resources/chat/completions.test.ts
diff --git tests/api-resources/completions.test.ts tests/api-resources/completions.test.ts
diff --git tests/lib/azure.test.ts tests/lib/azure.test.ts
describe('defaultQuery', () => {
Security Hotspots
Possible Issues
|
|
openai debug - [puLL-Merge] - openai/[email protected] Diffdiff --git .release-please-manifest.json .release-please-manifest.json
index b1ab5c7b9..6eb0f130e 100644
--- .release-please-manifest.json
+++ .release-please-manifest.json
@@ -1,3 +1,3 @@
{
- ".": "4.79.4"
+ ".": "4.83.0"
}
diff --git .stats.yml .stats.yml
index 9600edae3..df7877dfd 100644
--- .stats.yml
+++ .stats.yml
@@ -1,2 +1,2 @@
configured_endpoints: 69
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-b5b0e2c794b012919701c3fd43286af10fa25d33ceb8a881bec2636028f446e0.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-fc5dbc19505b0035f9e7f88868619f4fb519b048bde011f6154f3132d4be71fb.yml
diff --git CHANGELOG.md CHANGELOG.md
index 4254a9b8f..f61def5e4 100644
--- CHANGELOG.md
+++ CHANGELOG.md
@@ -1,5 +1,64 @@
# Changelog
+## 4.83.0 (2025-02-05)
+
+Full Changelog: [v4.82.0...v4.83.0](https://github.com/openai/openai-node/compare/v4.82.0...v4.83.0)
+
+### Features
+
+* **client:** send `X-Stainless-Timeout` header ([#1299](https://github.com/openai/openai-node/issues/1299)) ([ddfc686](https://github.com/openai/openai-node/commit/ddfc686f43a3420c3adf8dec2e82b4d10a121eb8))
+
+
+### Bug Fixes
+
+* **api/types:** correct audio duration & role types ([#1300](https://github.com/openai/openai-node/issues/1300)) ([a955ac2](https://github.com/openai/openai-node/commit/a955ac2bf5bee663d530d0c82b0005bf3ce6fc47))
+* **azure/audio:** use model param for deployments ([#1297](https://github.com/openai/openai-node/issues/1297)) ([85de382](https://github.com/openai/openai-node/commit/85de382db17cbe5f112650e79d0fc1cc841efbb2))
+
+## 4.82.0 (2025-01-31)
+
+Full Changelog: [v4.81.0...v4.82.0](https://github.com/openai/openai-node/compare/v4.81.0...v4.82.0)
+
+### Features
+
+* **api:** add o3-mini ([#1295](https://github.com/openai/openai-node/issues/1295)) ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+
+### Bug Fixes
+
+* **examples/realtime:** remove duplicate `session.update` call ([#1293](https://github.com/openai/openai-node/issues/1293)) ([ad800b4](https://github.com/openai/openai-node/commit/ad800b4f9410c6838994c24a3386ea708717f72b))
+* **types:** correct metadata type + other fixes ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+## 4.81.0 (2025-01-29)
+
+Full Changelog: [v4.80.1...v4.81.0](https://github.com/openai/openai-node/compare/v4.80.1...v4.81.0)
+
+### Features
+
+* **azure:** Realtime API support ([#1287](https://github.com/openai/openai-node/issues/1287)) ([fe090c0](https://github.com/openai/openai-node/commit/fe090c0a57570217eb0b431e2cce40bf61de2b75))
+
+## 4.80.1 (2025-01-24)
+
+Full Changelog: [v4.80.0...v4.80.1](https://github.com/openai/openai-node/compare/v4.80.0...v4.80.1)
+
+### Bug Fixes
+
+* **azure:** include retry count header ([3e0ba40](https://github.com/openai/openai-node/commit/3e0ba409e57ce276fb1f95cd11c801e4ccaad572))
+
+
+### Documentation
+
+* fix typo, "zodFunctionTool" -> "zodFunction" ([#1128](https://github.com/openai/openai-node/issues/1128)) ([b7ab6bb](https://github.com/openai/openai-node/commit/b7ab6bb304973ade94830f37eb646e800226d5ef))
+* **helpers:** fix type annotation ([fc019df](https://github.com/openai/openai-node/commit/fc019df1d9cc276e8f8e689742853a09aa94991a))
+* **readme:** fix realtime errors docs link ([#1286](https://github.com/openai/openai-node/issues/1286)) ([d1d50c8](https://github.com/openai/openai-node/commit/d1d50c897c18cefea964e8057fe1acfd766ae2bf))
+
+## 4.80.0 (2025-01-22)
+
+Full Changelog: [v4.79.4...v4.80.0](https://github.com/openai/openai-node/compare/v4.79.4...v4.80.0)
+
+### Features
+
+* **api:** update enum values, comments, and examples ([#1280](https://github.com/openai/openai-node/issues/1280)) ([d38f2c2](https://github.com/openai/openai-node/commit/d38f2c2648b6990f217c3c7d83ca31f3739641d3))
+
## 4.79.4 (2025-01-21)
Full Changelog: [v4.79.3...v4.79.4](https://github.com/openai/openai-node/compare/v4.79.3...v4.79.4)
diff --git README.md README.md
index 3bd386e99..a1f4bf760 100644
--- README.md
+++ README.md
@@ -157,7 +157,7 @@ A full example can be found [here](https://github.com/openai/openai-node/blob/ma
### Realtime error handling
-When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime/realtime-api-beta#handling-errors), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
+When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime-model-capabilities#error-handling), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
It is **highly recommended** that you register an `error` event listener and handle errors approriately as typically the underlying connection is still usable.
@@ -499,7 +499,7 @@ const credential = new DefaultAzureCredential();
const scope = 'https://cognitiveservices.azure.com/.default';
const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: "<The API version, e.g. 2024-10-01-preview>" });
const result = await openai.chat.completions.create({
model: 'gpt-4o',
@@ -509,6 +509,26 @@ const result = await openai.chat.completions.create({
console.log(result.choices[0]!.message?.content);
\`\`\`
+### Realtime API
+This SDK provides real-time streaming capabilities for Azure OpenAI through the `OpenAIRealtimeWS` and `OpenAIRealtimeWebSocket` clients described previously.
+
+To utilize the real-time features, begin by creating a fully configured `AzureOpenAI` client and passing it into either `OpenAIRealtimeWS.azure` or `OpenAIRealtimeWebSocket.azure`. For example:
+
+```ts
+const cred = new DefaultAzureCredential();
+const scope = 'https://cognitiveservices.azure.com/.default';
+const deploymentName = 'gpt-4o-realtime-preview-1001';
+const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+});
+const rt = await OpenAIRealtimeWS.azure(client);
+```
+
+Once the instance has been created, you can then begin sending requests and receiving streaming responses in real time.
+
### Retries
Certain errors will be automatically retried 2 times by default, with a short exponential backoff.
diff --git api.md api.md
index 33ab95ef6..01854a8e0 100644
--- api.md
+++ api.md
@@ -5,6 +5,7 @@ Types:
- <code><a href="./src/resources/shared.ts">ErrorObject</a></code>
- <code><a href="./src/resources/shared.ts">FunctionDefinition</a></code>
- <code><a href="./src/resources/shared.ts">FunctionParameters</a></code>
+- <code><a href="./src/resources/shared.ts">Metadata</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONObject</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONSchema</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatText</a></code>
@@ -228,6 +229,7 @@ Types:
- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemInputAudioTranscriptionFailedEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemTruncateEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemTruncatedEvent</a></code>
+- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemWithReference</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">ErrorEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">InputAudioBufferAppendEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">InputAudioBufferClearEvent</a></code>
diff --git examples/azure.ts examples/azure/chat.ts
similarity index 91%
rename from examples/azure.ts
rename to examples/azure/chat.ts
index 5fe1718fa..46df820f8 100755
--- examples/azure.ts
+++ examples/azure/chat.ts
@@ -2,6 +2,7 @@
import { AzureOpenAI } from 'openai';
import { getBearerTokenProvider, DefaultAzureCredential } from '@azure/identity';
+import 'dotenv/config';
// Corresponds to your Model deployment within your OpenAI resource, e.g. gpt-4-1106-preview
// Navigate to the Azure OpenAI Studio to deploy a model.
@@ -13,7 +14,7 @@ const azureADTokenProvider = getBearerTokenProvider(credential, scope);
// Make sure to set AZURE_OPENAI_ENDPOINT with the endpoint of your Azure resource.
// You can find it in the Azure Portal.
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: '2024-10-01-preview' });
async function main() {
console.log('Non-streaming:');
diff --git a/examples/azure/realtime/websocket.ts b/examples/azure/realtime/websocket.ts
new file mode 100644
index 000000000..bec74e654
--- /dev/null
+++ examples/azure/realtime/websocket.ts
@@ -0,0 +1,60 @@
+import { OpenAIRealtimeWebSocket } from 'openai/beta/realtime/websocket';
+import { AzureOpenAI } from 'openai';
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWebSocket.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.addEventListener('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.addEventListener('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git a/examples/azure/realtime/ws.ts b/examples/azure/realtime/ws.ts
new file mode 100644
index 000000000..6ab7b742a
--- /dev/null
+++ examples/azure/realtime/ws.ts
@@ -0,0 +1,60 @@
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import { OpenAIRealtimeWS } from 'openai/beta/realtime/ws';
+import { AzureOpenAI } from 'openai';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWS.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.on('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.on('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git examples/package.json examples/package.json
index b8c34ac45..70ec2c523 100644
--- examples/package.json
+++ examples/package.json
@@ -7,6 +7,7 @@
"private": true,
"dependencies": {
"@azure/identity": "^4.2.0",
+ "dotenv": "^16.4.7",
"express": "^4.18.2",
"next": "^14.1.1",
"openai": "file:..",
diff --git examples/realtime/ws.ts examples/realtime/ws.ts
index 4bbe85e5d..08c6fbcb6 100644
--- examples/realtime/ws.ts
+++ examples/realtime/ws.ts
@@ -6,13 +6,6 @@ async function main() {
// access the underlying `ws.WebSocket` instance
rt.socket.on('open', () => {
console.log('Connection opened!');
- rt.send({
- type: 'session.update',
- session: {
- modalities: ['foo'] as any,
- model: 'gpt-4o-realtime-preview',
- },
- });
rt.send({
type: 'session.update',
session: {
diff --git helpers.md helpers.md
index abf980c82..16bc1f277 100644
--- helpers.md
+++ helpers.md
@@ -49,7 +49,7 @@ if (message?.parsed) {
The `.parse()` method will also automatically parse `function` tool calls if:
-- You use the `zodFunctionTool()` helper method
+- You use the `zodFunction()` helper method
- You mark your tool schema with `"strict": True`
For example:
@@ -226,7 +226,7 @@ on in the documentation page [Message](https://platform.openai.com/docs/api-refe
```ts
.on('textCreated', (content: Text) => ...)
-.on('textDelta', (delta: RunStepDelta, snapshot: Text) => ...)
+.on('textDelta', (delta: TextDelta, snapshot: Text) => ...)
.on('textDone', (content: Text, snapshot: Message) => ...)diff --git jsr.json jsr.json
export class OpenAIRealtimeError extends OpenAIError { -export function buildRealtimeURL(props: { baseURL: string; model: string }): URL {
interface MessageEvent {
@@ -77,6 +84,45 @@ export class OpenAIRealtimeWebSocket extends OpenAIRealtimeEmitter {
send(event: RealtimeClientEvent) { export class OpenAIRealtimeWS extends OpenAIRealtimeEmitter {
+async function getAzureHeaders(client: AzureOpenAI) {
private buildHeaders({
@@ -814,6 +822,7 @@ export type RequestOptions<
@@ -103,7 +106,7 @@ export interface TranscriptionVerbose {
diff --git src/resources/audio/translations.ts src/resources/audio/translations.ts
@@ -38,7 +41,7 @@ export interface TranslationVerbose {
export class Batches extends APIResource { /**
export interface BatchListParams extends CursorPageParams {} /**
import { APIResource } from '../../../resource'; /**
+/**
/**
/**
/**
@@ -1723,8 +1835,11 @@ export namespace SessionUpdateEvent {
@@ -1756,8 +1871,19 @@ export namespace SessionUpdateEvent {
@@ -1797,15 +1923,33 @@ export namespace SessionUpdateEvent {
@@ -86,6 +88,7 @@ export interface Session { /**
@@ -200,7 +203,7 @@ export interface SessionCreateResponse {
/** export interface SessionCreateParams {
@@ -390,8 +385,11 @@ export interface SessionCreateParams {
@@ -423,8 +421,19 @@ export interface SessionCreateParams {
@@ -464,15 +473,33 @@ export namespace SessionCreateParams {
export interface Tool { @@ -407,11 +408,13 @@ export interface Message { /**
export namespace MessageCreateParams {
export interface MessageListParams extends CursorPageParams { /**
export namespace AdditionalMessage {
export interface RunListParams extends CursorPageParams { export class Steps extends APIResource { /**
export namespace Message {
@@ -658,7 +671,8 @@ export interface ThreadCreateAndRunParamsBase { export namespace ThreadCreateAndRunParams {
export type ChatModel =
@@ -300,8 +299,7 @@ export interface ChatCompletionChunk { /**
@@ -373,7 +371,7 @@ export namespace ChatCompletionChunk {
/**
/**
diff --git src/resources/embeddings.ts src/resources/embeddings.ts
diff --git src/resources/shared.ts src/resources/shared.ts +/**
export interface ResponseFormatJSONObject { /**
@@ -33,7 +33,9 @@ describe('resource assistants', () => {
diff --git tests/api-resources/beta/realtime/sessions.test.ts tests/api-resources/beta/realtime/sessions.test.ts describe('resource sessions', () => {
diff --git tests/api-resources/beta/threads/runs/runs.test.ts tests/api-resources/beta/threads/runs/runs.test.ts
diff --git tests/api-resources/beta/threads/threads.test.ts tests/api-resources/beta/threads/threads.test.ts
@@ -118,7 +120,7 @@ describe('resource threads', () => {
@@ -130,15 +132,17 @@ describe('resource threads', () => {
diff --git tests/api-resources/chat/completions.test.ts tests/api-resources/chat/completions.test.ts
diff --git tests/api-resources/completions.test.ts tests/api-resources/completions.test.ts
diff --git tests/lib/azure.test.ts tests/lib/azure.test.ts
describe('defaultQuery', () => {
|
|
bedrock debug - [puLL-Merge] - openai/[email protected] Diffdiff --git .release-please-manifest.json .release-please-manifest.json
index b1ab5c7b9..6eb0f130e 100644
--- .release-please-manifest.json
+++ .release-please-manifest.json
@@ -1,3 +1,3 @@
{
- ".": "4.79.4"
+ ".": "4.83.0"
}
diff --git .stats.yml .stats.yml
index 9600edae3..df7877dfd 100644
--- .stats.yml
+++ .stats.yml
@@ -1,2 +1,2 @@
configured_endpoints: 69
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-b5b0e2c794b012919701c3fd43286af10fa25d33ceb8a881bec2636028f446e0.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-fc5dbc19505b0035f9e7f88868619f4fb519b048bde011f6154f3132d4be71fb.yml
diff --git CHANGELOG.md CHANGELOG.md
index 4254a9b8f..f61def5e4 100644
--- CHANGELOG.md
+++ CHANGELOG.md
@@ -1,5 +1,64 @@
# Changelog
+## 4.83.0 (2025-02-05)
+
+Full Changelog: [v4.82.0...v4.83.0](https://github.com/openai/openai-node/compare/v4.82.0...v4.83.0)
+
+### Features
+
+* **client:** send `X-Stainless-Timeout` header ([#1299](https://github.com/openai/openai-node/issues/1299)) ([ddfc686](https://github.com/openai/openai-node/commit/ddfc686f43a3420c3adf8dec2e82b4d10a121eb8))
+
+
+### Bug Fixes
+
+* **api/types:** correct audio duration & role types ([#1300](https://github.com/openai/openai-node/issues/1300)) ([a955ac2](https://github.com/openai/openai-node/commit/a955ac2bf5bee663d530d0c82b0005bf3ce6fc47))
+* **azure/audio:** use model param for deployments ([#1297](https://github.com/openai/openai-node/issues/1297)) ([85de382](https://github.com/openai/openai-node/commit/85de382db17cbe5f112650e79d0fc1cc841efbb2))
+
+## 4.82.0 (2025-01-31)
+
+Full Changelog: [v4.81.0...v4.82.0](https://github.com/openai/openai-node/compare/v4.81.0...v4.82.0)
+
+### Features
+
+* **api:** add o3-mini ([#1295](https://github.com/openai/openai-node/issues/1295)) ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+
+### Bug Fixes
+
+* **examples/realtime:** remove duplicate `session.update` call ([#1293](https://github.com/openai/openai-node/issues/1293)) ([ad800b4](https://github.com/openai/openai-node/commit/ad800b4f9410c6838994c24a3386ea708717f72b))
+* **types:** correct metadata type + other fixes ([378e2f7](https://github.com/openai/openai-node/commit/378e2f7af62c570adb4c7644a4d49576b698de41))
+
+## 4.81.0 (2025-01-29)
+
+Full Changelog: [v4.80.1...v4.81.0](https://github.com/openai/openai-node/compare/v4.80.1...v4.81.0)
+
+### Features
+
+* **azure:** Realtime API support ([#1287](https://github.com/openai/openai-node/issues/1287)) ([fe090c0](https://github.com/openai/openai-node/commit/fe090c0a57570217eb0b431e2cce40bf61de2b75))
+
+## 4.80.1 (2025-01-24)
+
+Full Changelog: [v4.80.0...v4.80.1](https://github.com/openai/openai-node/compare/v4.80.0...v4.80.1)
+
+### Bug Fixes
+
+* **azure:** include retry count header ([3e0ba40](https://github.com/openai/openai-node/commit/3e0ba409e57ce276fb1f95cd11c801e4ccaad572))
+
+
+### Documentation
+
+* fix typo, "zodFunctionTool" -> "zodFunction" ([#1128](https://github.com/openai/openai-node/issues/1128)) ([b7ab6bb](https://github.com/openai/openai-node/commit/b7ab6bb304973ade94830f37eb646e800226d5ef))
+* **helpers:** fix type annotation ([fc019df](https://github.com/openai/openai-node/commit/fc019df1d9cc276e8f8e689742853a09aa94991a))
+* **readme:** fix realtime errors docs link ([#1286](https://github.com/openai/openai-node/issues/1286)) ([d1d50c8](https://github.com/openai/openai-node/commit/d1d50c897c18cefea964e8057fe1acfd766ae2bf))
+
+## 4.80.0 (2025-01-22)
+
+Full Changelog: [v4.79.4...v4.80.0](https://github.com/openai/openai-node/compare/v4.79.4...v4.80.0)
+
+### Features
+
+* **api:** update enum values, comments, and examples ([#1280](https://github.com/openai/openai-node/issues/1280)) ([d38f2c2](https://github.com/openai/openai-node/commit/d38f2c2648b6990f217c3c7d83ca31f3739641d3))
+
## 4.79.4 (2025-01-21)
Full Changelog: [v4.79.3...v4.79.4](https://github.com/openai/openai-node/compare/v4.79.3...v4.79.4)
diff --git README.md README.md
index 3bd386e99..a1f4bf760 100644
--- README.md
+++ README.md
@@ -157,7 +157,7 @@ A full example can be found [here](https://github.com/openai/openai-node/blob/ma
### Realtime error handling
-When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime/realtime-api-beta#handling-errors), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
+When an error is encountered, either on the client side or returned from the server through the [`error` event](https://platform.openai.com/docs/guides/realtime-model-capabilities#error-handling), the `error` event listener will be fired. However, if you haven't registered an `error` event listener then an `unhandled Promise rejection` error will be thrown.
It is **highly recommended** that you register an `error` event listener and handle errors approriately as typically the underlying connection is still usable.
@@ -499,7 +499,7 @@ const credential = new DefaultAzureCredential();
const scope = 'https://cognitiveservices.azure.com/.default';
const azureADTokenProvider = getBearerTokenProvider(credential, scope);
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: "<The API version, e.g. 2024-10-01-preview>" });
const result = await openai.chat.completions.create({
model: 'gpt-4o',
@@ -509,6 +509,26 @@ const result = await openai.chat.completions.create({
console.log(result.choices[0]!.message?.content);
\`\`\`
+### Realtime API
+This SDK provides real-time streaming capabilities for Azure OpenAI through the `OpenAIRealtimeWS` and `OpenAIRealtimeWebSocket` clients described previously.
+
+To utilize the real-time features, begin by creating a fully configured `AzureOpenAI` client and passing it into either `OpenAIRealtimeWS.azure` or `OpenAIRealtimeWebSocket.azure`. For example:
+
+```ts
+const cred = new DefaultAzureCredential();
+const scope = 'https://cognitiveservices.azure.com/.default';
+const deploymentName = 'gpt-4o-realtime-preview-1001';
+const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+});
+const rt = await OpenAIRealtimeWS.azure(client);
+```
+
+Once the instance has been created, you can then begin sending requests and receiving streaming responses in real time.
+
### Retries
Certain errors will be automatically retried 2 times by default, with a short exponential backoff.
diff --git api.md api.md
index 33ab95ef6..01854a8e0 100644
--- api.md
+++ api.md
@@ -5,6 +5,7 @@ Types:
- <code><a href="./src/resources/shared.ts">ErrorObject</a></code>
- <code><a href="./src/resources/shared.ts">FunctionDefinition</a></code>
- <code><a href="./src/resources/shared.ts">FunctionParameters</a></code>
+- <code><a href="./src/resources/shared.ts">Metadata</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONObject</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatJSONSchema</a></code>
- <code><a href="./src/resources/shared.ts">ResponseFormatText</a></code>
@@ -228,6 +229,7 @@ Types:
- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemInputAudioTranscriptionFailedEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemTruncateEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemTruncatedEvent</a></code>
+- <code><a href="./src/resources/beta/realtime/realtime.ts">ConversationItemWithReference</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">ErrorEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">InputAudioBufferAppendEvent</a></code>
- <code><a href="./src/resources/beta/realtime/realtime.ts">InputAudioBufferClearEvent</a></code>
diff --git examples/azure.ts examples/azure/chat.ts
similarity index 91%
rename from examples/azure.ts
rename to examples/azure/chat.ts
index 5fe1718fa..46df820f8 100755
--- examples/azure.ts
+++ examples/azure/chat.ts
@@ -2,6 +2,7 @@
import { AzureOpenAI } from 'openai';
import { getBearerTokenProvider, DefaultAzureCredential } from '@azure/identity';
+import 'dotenv/config';
// Corresponds to your Model deployment within your OpenAI resource, e.g. gpt-4-1106-preview
// Navigate to the Azure OpenAI Studio to deploy a model.
@@ -13,7 +14,7 @@ const azureADTokenProvider = getBearerTokenProvider(credential, scope);
// Make sure to set AZURE_OPENAI_ENDPOINT with the endpoint of your Azure resource.
// You can find it in the Azure Portal.
-const openai = new AzureOpenAI({ azureADTokenProvider });
+const openai = new AzureOpenAI({ azureADTokenProvider, apiVersion: '2024-10-01-preview' });
async function main() {
console.log('Non-streaming:');
diff --git a/examples/azure/realtime/websocket.ts b/examples/azure/realtime/websocket.ts
new file mode 100644
index 000000000..bec74e654
--- /dev/null
+++ examples/azure/realtime/websocket.ts
@@ -0,0 +1,60 @@
+import { OpenAIRealtimeWebSocket } from 'openai/beta/realtime/websocket';
+import { AzureOpenAI } from 'openai';
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWebSocket.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.addEventListener('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.addEventListener('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git a/examples/azure/realtime/ws.ts b/examples/azure/realtime/ws.ts
new file mode 100644
index 000000000..6ab7b742a
--- /dev/null
+++ examples/azure/realtime/ws.ts
@@ -0,0 +1,60 @@
+import { DefaultAzureCredential, getBearerTokenProvider } from '@azure/identity';
+import { OpenAIRealtimeWS } from 'openai/beta/realtime/ws';
+import { AzureOpenAI } from 'openai';
+import 'dotenv/config';
+
+async function main() {
+ const cred = new DefaultAzureCredential();
+ const scope = 'https://cognitiveservices.azure.com/.default';
+ const deploymentName = 'gpt-4o-realtime-preview-1001';
+ const azureADTokenProvider = getBearerTokenProvider(cred, scope);
+ const client = new AzureOpenAI({
+ azureADTokenProvider,
+ apiVersion: '2024-10-01-preview',
+ deployment: deploymentName,
+ });
+ const rt = await OpenAIRealtimeWS.azure(client);
+
+ // access the underlying `ws.WebSocket` instance
+ rt.socket.on('open', () => {
+ console.log('Connection opened!');
+ rt.send({
+ type: 'session.update',
+ session: {
+ modalities: ['text'],
+ model: 'gpt-4o-realtime-preview',
+ },
+ });
+
+ rt.send({
+ type: 'conversation.item.create',
+ item: {
+ type: 'message',
+ role: 'user',
+ content: [{ type: 'input_text', text: 'Say a couple paragraphs!' }],
+ },
+ });
+
+ rt.send({ type: 'response.create' });
+ });
+
+ rt.on('error', (err) => {
+ // in a real world scenario this should be logged somewhere as you
+ // likely want to continue procesing events regardless of any errors
+ throw err;
+ });
+
+ rt.on('session.created', (event) => {
+ console.log('session created!', event.session);
+ console.log();
+ });
+
+ rt.on('response.text.delta', (event) => process.stdout.write(event.delta));
+ rt.on('response.text.done', () => console.log());
+
+ rt.on('response.done', () => rt.close());
+
+ rt.socket.on('close', () => console.log('\nConnection closed!'));
+}
+
+main();
diff --git examples/package.json examples/package.json
index b8c34ac45..70ec2c523 100644
--- examples/package.json
+++ examples/package.json
@@ -7,6 +7,7 @@
"private": true,
"dependencies": {
"@azure/identity": "^4.2.0",
+ "dotenv": "^16.4.7",
"express": "^4.18.2",
"next": "^14.1.1",
"openai": "file:..",
diff --git examples/realtime/ws.ts examples/realtime/ws.ts
index 4bbe85e5d..08c6fbcb6 100644
--- examples/realtime/ws.ts
+++ examples/realtime/ws.ts
@@ -6,13 +6,6 @@ async function main() {
// access the underlying `ws.WebSocket` instance
rt.socket.on('open', () => {
console.log('Connection opened!');
- rt.send({
- type: 'session.update',
- session: {
- modalities: ['foo'] as any,
- model: 'gpt-4o-realtime-preview',
- },
- });
rt.send({
type: 'session.update',
session: {
diff --git helpers.md helpers.md
index abf980c82..16bc1f277 100644
--- helpers.md
+++ helpers.md
@@ -49,7 +49,7 @@ if (message?.parsed) {
The `.parse()` method will also automatically parse `function` tool calls if:
-- You use the `zodFunctionTool()` helper method
+- You use the `zodFunction()` helper method
- You mark your tool schema with `"strict": True`
For example:
@@ -226,7 +226,7 @@ on in the documentation page [Message](https://platform.openai.com/docs/api-refe
```ts
.on('textCreated', (content: Text) => ...)
-.on('textDelta', (delta: RunStepDelta, snapshot: Text) => ...)
+.on('textDelta', (delta: TextDelta, snapshot: Text) => ...)
.on('textDone', (content: Text, snapshot: Message) => ...)diff --git jsr.json jsr.json
export class OpenAIRealtimeError extends OpenAIError { -export function buildRealtimeURL(props: { baseURL: string; model: string }): URL {
interface MessageEvent {
@@ -77,6 +84,45 @@ export class OpenAIRealtimeWebSocket extends OpenAIRealtimeEmitter {
send(event: RealtimeClientEvent) { export class OpenAIRealtimeWS extends OpenAIRealtimeEmitter {
+async function getAzureHeaders(client: AzureOpenAI) {
private buildHeaders({
@@ -814,6 +822,7 @@ export type RequestOptions<
@@ -103,7 +106,7 @@ export interface TranscriptionVerbose {
diff --git src/resources/audio/translations.ts src/resources/audio/translations.ts
@@ -38,7 +41,7 @@ export interface TranslationVerbose {
export class Batches extends APIResource { /**
export interface BatchListParams extends CursorPageParams {} /**
import { APIResource } from '../../../resource'; /**
+/**
/**
/**
/**
@@ -1723,8 +1835,11 @@ export namespace SessionUpdateEvent {
@@ -1756,8 +1871,19 @@ export namespace SessionUpdateEvent {
@@ -1797,15 +1923,33 @@ export namespace SessionUpdateEvent {
@@ -86,6 +88,7 @@ export interface Session { /**
@@ -200,7 +203,7 @@ export interface SessionCreateResponse {
/** export interface SessionCreateParams {
@@ -390,8 +385,11 @@ export interface SessionCreateParams {
@@ -423,8 +421,19 @@ export interface SessionCreateParams {
@@ -464,15 +473,33 @@ export namespace SessionCreateParams {
export interface Tool { @@ -407,11 +408,13 @@ export interface Message { /**
export namespace MessageCreateParams {
export interface MessageListParams extends CursorPageParams { /**
export namespace AdditionalMessage {
export interface RunListParams extends CursorPageParams { export class Steps extends APIResource { /**
export namespace Message {
@@ -658,7 +671,8 @@ export interface ThreadCreateAndRunParamsBase { export namespace ThreadCreateAndRunParams {
export type ChatModel =
@@ -300,8 +299,7 @@ export interface ChatCompletionChunk { /**
@@ -373,7 +371,7 @@ export namespace ChatCompletionChunk {
/**
/**
diff --git src/resources/embeddings.ts src/resources/embeddings.ts
diff --git src/resources/shared.ts src/resources/shared.ts +/**
export interface ResponseFormatJSONObject { /**
@@ -33,7 +33,9 @@ describe('resource assistants', () => {
diff --git tests/api-resources/beta/realtime/sessions.test.ts tests/api-resources/beta/realtime/sessions.test.ts describe('resource sessions', () => {
diff --git tests/api-resources/beta/threads/runs/runs.test.ts tests/api-resources/beta/threads/runs/runs.test.ts
diff --git tests/api-resources/beta/threads/threads.test.ts tests/api-resources/beta/threads/threads.test.ts
@@ -118,7 +120,7 @@ describe('resource threads', () => {
@@ -130,15 +132,17 @@ describe('resource threads', () => {
diff --git tests/api-resources/chat/completions.test.ts tests/api-resources/chat/completions.test.ts
diff --git tests/api-resources/completions.test.ts tests/api-resources/completions.test.ts
diff --git tests/lib/azure.test.ts tests/lib/azure.test.ts
describe('defaultQuery', () => {
|
This PR contains the following updates:
4.79.4->4.83.0Release Notes
openai/openai-node (openai)
v4.83.0Compare Source
Full Changelog: v4.82.0...v4.83.0
Features
X-Stainless-Timeoutheader (#1299) (ddfc686)Bug Fixes
v4.82.0Compare Source
Full Changelog: v4.81.0...v4.82.0
Features
Bug Fixes
session.updatecall (#1293) (ad800b4)v4.81.0Compare Source
Full Changelog: v4.80.1...v4.81.0
Features
v4.80.1Compare Source
Full Changelog: v4.80.0...v4.80.1
Bug Fixes
Documentation
v4.80.0Compare Source
Full Changelog: v4.79.4...v4.80.0
Features
Configuration
📅 Schedule: Branch creation - "* 0-12 * * 3" (UTC), Automerge - At any time (no schedule defined).
🚦 Automerge: Disabled by config. Please merge this manually once you are satisfied.
♻ Rebasing: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox.
🔕 Ignore: Close this PR and you won't be reminded about this update again.
This PR was generated by Mend Renovate. View the repository job log.