跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
AI 与知识库

telnyx-ai-inference-java

Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides Java SDK examples.

team-telnyx · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add team-telnyx/ai --skill telnyx-ai-inference-java

技能说明


name: telnyx-ai-inference-java description: >- Access Telnyx LLM inference APIs, embeddings, and AI analytics for call insights and summaries. This skill provides Java SDK examples. metadata: author: telnyx product: ai-inference language: java generated_by: telnyx-openapi-pipeline

Telnyx Ai Inference - Java

Installation

<!-- Maven -->
<dependency>
    <groupId>com.telnyx.sdk</groupId>
    <artifactId>telnyx</artifactId>
    <version>6.89.0</version>
</dependency>

// Gradle
implementation("com.telnyx.sdk:telnyx:6.89.0")

Setup

import com.telnyx.sdk.client.TelnyxClient;
import com.telnyx.sdk.client.okhttp.TelnyxOkHttpClient;

TelnyxClient client = TelnyxOkHttpClient.fromEnv();

All examples below assume client is already initialized as shown above.

Error Handling

All API calls can fail with network errors, rate limits (429), validation errors (422), or authentication errors (401). Always handle errors in production code:

import com.telnyx.sdk.errors.TelnyxServiceException;

try {
    var result = client.messages().send(params);
} catch (TelnyxServiceException e) {
    System.err.println("API error " + e.statusCode() + ": " + e.getMessage());
    if (e.statusCode() == 422) {
        System.err.println("Validation error — check required fields and formats");
    } else if (e.statusCode() == 429) {
        // Rate limited — wait and retry with exponential backoff
        Thread.sleep(1000);
    }
}

Common error codes: 401 invalid API key, 403 insufficient permissions, 404 resource not found, 422 validation error (check field formats), 429 rate limited (retry with exponential backoff).

Important Notes

  • Pagination: List methods return a page. Use .autoPager() for automatic iteration: for (var item : page.autoPager()) { ... }. For manual control, use .hasNextPage() and .nextPage().

Transcribe speech to text

Transcribe speech to text. This endpoint is consistent with the OpenAI Transcription API and may be used with the OpenAI JS or Python SDK.

POST /ai/audio/transcriptions

import com.telnyx.sdk.models.ai.audio.AudioTranscribeParams;
import com.telnyx.sdk.models.ai.audio.AudioTranscribeResponse;

AudioTranscribeParams params = AudioTranscribeParams.builder()
    .model(AudioTranscribeParams.Model.DISTIL_WHISPER_DISTIL_LARGE_V2)
    .build();
AudioTranscribeResponse response = client.ai().audio().transcribe(params);

Returns: duration (number), segments (array[object]), text (string), words (array[object])

Create a chat completion

Deprecated: Use POST /v2/ai/openai/chat/completions instead. Chat with a language model. This endpoint is consistent with the OpenAI Chat Completions API and may be used with the OpenAI JS or Python SDK.

POST /ai/chat/completions — Required: messages

Optional: api_key_ref (string), best_of (integer), early_stopping (boolean), enable_thinking (boolean), frequency_penalty (number), guided_choice (array[string]), guided_json (object), guided_regex (string), length_penalty (number), logprobs (boolean), max_tokens (integer), min_p (number), model (string), n (number), presence_penalty (number), response_format (object), seed (integer), stop (object), stream (boolean), temperature (number), tool_choice (enum: none, auto, required), tools (array[object]), top_logprobs (integer), top_p (number), use_beam_search (boolean)

import com.telnyx.sdk.models.ai.chat.ChatCreateCompletionParams;
import com.telnyx.sdk.models.ai.chat.ChatCreateCompletionResponse;

ChatCreateCompletionParams params = ChatCreateCompletionParams.builder()
    .addMessage(ChatCreateCompletionParams.Message.builder()
        .content("You are a friendly chatbot.")
        .role(ChatCreateCompletionParams.Message.Role.SYSTEM)
        .build())
    .addMessage(ChatCreateCompletionParams.Message.builder()
        .content("Hello, world!")
        .role(ChatCreateCompletionParams.Message.Role.USER)
        .build())
    .build();
ChatCreateCompletionResponse response = client.ai().chat().createCompletion(params);

List conversations

Retrieve a list of all AI conversations configured by the user. Supports PostgREST-style query parameters for filtering. Examples are included for the standard metadata fields, but you can filter on any field in the metadata JSON object.

GET /ai/conversations

import com.telnyx.sdk.models.ai.conversations.ConversationListParams;
import com.telnyx.sdk.models.ai.conversations.ConversationListResponse;

ConversationListResponse conversations = client.ai().conversations().list();

Returns: created_at (date-time), id (uuid), last_message_at (date-time), metadata (object), name (string)

Create a conversation

Create a new AI Conversation.

POST /ai/conversations

Optional: metadata (object), name (string)

import com.telnyx.sdk.models.ai.conversations.Conversation;
import com.telnyx.sdk.models.ai.conversations.ConversationCreateParams;

Conversation conversation = client.ai().conversations().create();

Returns: created_at (date-time), id (uuid), last_message_at (date-time), metadata (object), name (string)

Aggregate Conversation Insights

Aggregate conversation insights by specified fields

GET /ai/conversations/conversation-insights/aggregates

import com.telnyx.sdk.models.ai.conversations.conversationinsights.ConversationInsightAggregateParams;
import com.telnyx.sdk.models.ai.conversations.conversationinsights.ConversationInsightAggregateResponse;

ConversationInsightAggregateResponse response = client.ai().conversations().conversationInsights().a
阅读完整来源 ↗