telnyx-ai-inference-javascript

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Telnyx Ai Inference - JavaScript

Telnyx AI推理 - JavaScript

Installation

安装

bash

npm install telnyx

bash

npm install telnyx

Setup

设置

javascript

import Telnyx from 'telnyx';

const client = new Telnyx({
  apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted
});

All examples below assume

client

is already initialized as shown above.

javascript

import Telnyx from 'telnyx';

const client = new Telnyx({
  apiKey: process.env['TELNYX_API_KEY'], // 这是默认配置，可省略
});

以下所有示例均假设

client

已按照上述方式完成初始化。

List conversations

列出对话

Retrieve a list of all AI conversations configured by the user.

GET /ai/conversations

javascript

const conversations = await client.ai.conversations.list();

console.log(conversations.data);

检索用户配置的所有AI对话列表。

GET /ai/conversations

javascript

const conversations = await client.ai.conversations.list();

console.log(conversations.data);

Create a conversation

创建对话

Create a new AI Conversation.

POST /ai/conversations

javascript

const conversation = await client.ai.conversations.create();

console.log(conversation.id);

创建新的AI对话。

POST /ai/conversations

javascript

const conversation = await client.ai.conversations.create();

console.log(conversation.id);

Get Insight Template Groups

获取洞察模板组

Get all insight groups

GET /ai/conversations/insight-groups

javascript

// Automatically fetches more pages as needed.
for await (const insightTemplateGroup of client.ai.conversations.insightGroups.retrieveInsightGroups()) {
  console.log(insightTemplateGroup.id);
}

获取所有洞察组

GET /ai/conversations/insight-groups

javascript

// 根据需要自动获取更多页面数据
for await (const insightTemplateGroup of client.ai.conversations.insightGroups.retrieveInsightGroups()) {
  console.log(insightTemplateGroup.id);
}

Create Insight Template Group

创建洞察模板组

Create a new insight group

POST /ai/conversations/insight-groups

— Required:

name

javascript

const insightTemplateGroupDetail = await client.ai.conversations.insightGroups.insightGroups({
  name: 'name',
});

console.log(insightTemplateGroupDetail.data);

创建新的洞察组

POST /ai/conversations/insight-groups

— 必填参数：

name

javascript

const insightTemplateGroupDetail = await client.ai.conversations.insightGroups.insightGroups({
  name: 'name',
});

console.log(insightTemplateGroupDetail.data);

Get Insight Template Group

获取单个洞察模板组

Get insight group by ID

GET /ai/conversations/insight-groups/{group_id}

javascript

const insightTemplateGroupDetail = await client.ai.conversations.insightGroups.retrieve(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);

console.log(insightTemplateGroupDetail.data);

通过ID获取洞察组

GET /ai/conversations/insight-groups/{group_id}

javascript

const insightTemplateGroupDetail = await client.ai.conversations.insightGroups.retrieve(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);

console.log(insightTemplateGroupDetail.data);

Update Insight Template Group

更新洞察模板组

Update an insight template group

PUT /ai/conversations/insight-groups/{group_id}

javascript

const insightTemplateGroupDetail = await client.ai.conversations.insightGroups.update(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);

console.log(insightTemplateGroupDetail.data);

更新洞察模板组信息

PUT /ai/conversations/insight-groups/{group_id}

javascript

const insightTemplateGroupDetail = await client.ai.conversations.insightGroups.update(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);

console.log(insightTemplateGroupDetail.data);

Delete Insight Template Group

删除洞察模板组

Delete insight group by ID

DELETE /ai/conversations/insight-groups/{group_id}

javascript

await client.ai.conversations.insightGroups.delete('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');

通过ID删除洞察组

DELETE /ai/conversations/insight-groups/{group_id}

javascript

await client.ai.conversations.insightGroups.delete('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');

Assign Insight Template To Group

为组分配洞察模板

Assign an insight to a group

POST /ai/conversations/insight-groups/{group_id}/insights/{insight_id}/assign

javascript

await client.ai.conversations.insightGroups.insights.assign(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  { group_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' },
);

将洞察分配给指定组

POST /ai/conversations/insight-groups/{group_id}/insights/{insight_id}/assign

javascript

await client.ai.conversations.insightGroups.insights.assign(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  { group_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' },
);

Unassign Insight Template From Group

从组中移除洞察模板

Remove an insight from a group

DELETE /ai/conversations/insight-groups/{group_id}/insights/{insight_id}/unassign

javascript

await client.ai.conversations.insightGroups.insights.deleteUnassign(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  { group_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' },
);

将洞察从组中移除

DELETE /ai/conversations/insight-groups/{group_id}/insights/{insight_id}/unassign

javascript

await client.ai.conversations.insightGroups.insights.deleteUnassign(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
  { group_id: '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e' },
);

Get Insight Templates

获取洞察模板

Get all insights

GET /ai/conversations/insights

javascript

// Automatically fetches more pages as needed.
for await (const insightTemplate of client.ai.conversations.insights.list()) {
  console.log(insightTemplate.id);
}

获取所有洞察模板

GET /ai/conversations/insights

javascript

// 根据需要自动获取更多页面数据
for await (const insightTemplate of client.ai.conversations.insights.list()) {
  console.log(insightTemplate.id);
}

Create Insight Template

创建洞察模板

Create a new insight

POST /ai/conversations/insights

— Required:

instructions

name

javascript

const insightTemplateDetail = await client.ai.conversations.insights.create({
  instructions: 'instructions',
  name: 'name',
});

console.log(insightTemplateDetail.data);

创建新的洞察模板

POST /ai/conversations/insights

— 必填参数：

instructions

name

javascript

const insightTemplateDetail = await client.ai.conversations.insights.create({
  instructions: 'instructions',
  name: 'name',
});

console.log(insightTemplateDetail.data);

Get Insight Template

获取单个洞察模板

Get insight by ID

GET /ai/conversations/insights/{insight_id}

javascript

const insightTemplateDetail = await client.ai.conversations.insights.retrieve(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);

console.log(insightTemplateDetail.data);

通过ID获取洞察模板

GET /ai/conversations/insights/{insight_id}

javascript

const insightTemplateDetail = await client.ai.conversations.insights.retrieve(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);

console.log(insightTemplateDetail.data);

Update Insight Template

更新洞察模板

Update an insight template

PUT /ai/conversations/insights/{insight_id}

javascript

const insightTemplateDetail = await client.ai.conversations.insights.update(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);

console.log(insightTemplateDetail.data);

更新洞察模板信息

PUT /ai/conversations/insights/{insight_id}

javascript

const insightTemplateDetail = await client.ai.conversations.insights.update(
  '182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e',
);

console.log(insightTemplateDetail.data);

Delete Insight Template

删除洞察模板

Delete insight by ID

DELETE /ai/conversations/insights/{insight_id}

javascript

await client.ai.conversations.insights.delete('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');

通过ID删除洞察模板

DELETE /ai/conversations/insights/{insight_id}

javascript

await client.ai.conversations.insights.delete('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e');

Get a conversation

获取单个对话

Retrieve a specific AI conversation by its ID.

GET /ai/conversations/{conversation_id}

javascript

const conversation = await client.ai.conversations.retrieve('conversation_id');

console.log(conversation.data);

通过ID检索特定的AI对话。

GET /ai/conversations/{conversation_id}

javascript

const conversation = await client.ai.conversations.retrieve('conversation_id');

console.log(conversation.data);

Update conversation metadata

更新对话元数据

Update metadata for a specific conversation.

PUT /ai/conversations/{conversation_id}

javascript

const conversation = await client.ai.conversations.update('conversation_id');

console.log(conversation.data);

更新特定对话的元数据。

PUT /ai/conversations/{conversation_id}

javascript

const conversation = await client.ai.conversations.update('conversation_id');

console.log(conversation.data);

Delete a conversation

删除对话

Delete a specific conversation by its ID.

DELETE /ai/conversations/{conversation_id}

javascript

await client.ai.conversations.delete('conversation_id');

通过ID删除特定对话。

DELETE /ai/conversations/{conversation_id}

javascript

await client.ai.conversations.delete('conversation_id');

Get insights for a conversation

获取对话的洞察信息

Retrieve insights for a specific conversation

GET /ai/conversations/{conversation_id}/conversations-insights

javascript

const response = await client.ai.conversations.retrieveConversationsInsights('conversation_id');

console.log(response.data);

检索特定对话的洞察信息

GET /ai/conversations/{conversation_id}/conversations-insights

javascript

const response = await client.ai.conversations.retrieveConversationsInsights('conversation_id');

console.log(response.data);

Create Message

创建消息

Add a new message to the conversation.

POST /ai/conversations/{conversation_id}/message

— Required:

role

javascript

await client.ai.conversations.addMessage('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', { role: 'role' });

向对话中添加新消息。

POST /ai/conversations/{conversation_id}/message

— 必填参数：

role

javascript

await client.ai.conversations.addMessage('182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e', { role: 'role' });

Get conversation messages

获取对话消息

Retrieve messages for a specific conversation, including tool calls made by the assistant.

GET /ai/conversations/{conversation_id}/messages

javascript

const messages = await client.ai.conversations.messages.list('conversation_id');

console.log(messages.data);

检索特定对话的消息，包括助手发起的工具调用。

GET /ai/conversations/{conversation_id}/messages

javascript

const messages = await client.ai.conversations.messages.list('conversation_id');

console.log(messages.data);

Get Tasks by Status

按状态获取任务

Retrieve tasks for the user that are either

queued

processing

failed

success

partial_success

based on the query string.

GET /ai/embeddings

javascript

const embeddings = await client.ai.embeddings.list();

console.log(embeddings.data);

根据查询字符串检索用户的任务，状态包括

queued

（排队中）、

processing

（处理中）、

failed

（失败）、

success

（成功）或

partial_success

（部分成功）。

GET /ai/embeddings

javascript

const embeddings = await client.ai.embeddings.list();

console.log(embeddings.data);

Embed documents

嵌入文档

Perform embedding on a Telnyx Storage Bucket using an embedding model.

POST /ai/embeddings

— Required:

bucket_name

javascript

const embeddingResponse = await client.ai.embeddings.create({ bucket_name: 'bucket_name' });

console.log(embeddingResponse.data);

使用嵌入模型对Telnyx存储桶中的文档执行嵌入操作。

POST /ai/embeddings

— 必填参数：

bucket_name

javascript

const embeddingResponse = await client.ai.embeddings.create({ bucket_name: 'bucket_name' });

console.log(embeddingResponse.data);

List embedded buckets

列出已嵌入的存储桶

Get all embedding buckets for a user.

GET /ai/embeddings/buckets

javascript

const buckets = await client.ai.embeddings.buckets.list();

console.log(buckets.data);

获取用户的所有嵌入存储桶。

GET /ai/embeddings/buckets

javascript

const buckets = await client.ai.embeddings.buckets.list();

console.log(buckets.data);

Get file-level embedding statuses for a bucket

获取存储桶的文件级嵌入状态

Get all embedded files for a given user bucket, including their processing status.

GET /ai/embeddings/buckets/{bucket_name}

javascript

const bucket = await client.ai.embeddings.buckets.retrieve('bucket_name');

console.log(bucket.data);

获取指定用户存储桶的所有已嵌入文件，包括它们的处理状态。

GET /ai/embeddings/buckets/{bucket_name}

javascript

const bucket = await client.ai.embeddings.buckets.retrieve('bucket_name');

console.log(bucket.data);

Disable AI for an Embedded Bucket

禁用嵌入存储桶的AI功能

Deletes an entire bucket's embeddings and disables the bucket for AI-use, returning it to normal storage pricing.

DELETE /ai/embeddings/buckets/{bucket_name}

javascript

await client.ai.embeddings.buckets.delete('bucket_name');

删除整个存储桶的嵌入数据，禁用该存储桶的AI使用权限，使其恢复为普通存储定价。

DELETE /ai/embeddings/buckets/{bucket_name}

javascript

await client.ai.embeddings.buckets.delete('bucket_name');

Search for documents

搜索文档

Perform a similarity search on a Telnyx Storage Bucket, returning the most similar

num_docs

document chunks to the query.

POST /ai/embeddings/similarity-search

— Required:

bucket_name

query

javascript

const response = await client.ai.embeddings.similaritySearch({
  bucket_name: 'bucket_name',
  query: 'query',
});

console.log(response.data);

在Telnyx存储桶中执行相似度搜索，返回与查询最相似的

num_docs

个文档片段。

POST /ai/embeddings/similarity-search

— 必填参数：

bucket_name

query

javascript

const response = await client.ai.embeddings.similaritySearch({
  bucket_name: 'bucket_name',
  query: 'query',
});

console.log(response.data);

Embed URL content

嵌入URL内容

Embed website content from a specified URL, including child pages up to 5 levels deep within the same domain.

POST /ai/embeddings/url

— Required:

url

bucket_name

javascript

const embeddingResponse = await client.ai.embeddings.url({
  bucket_name: 'bucket_name',
  url: 'url',
});

console.log(embeddingResponse.data);

嵌入指定URL的网站内容，包括同一域名下深度最多5层的子页面。

POST /ai/embeddings/url

— 必填参数：

url

bucket_name

javascript

const embeddingResponse = await client.ai.embeddings.url({
  bucket_name: 'bucket_name',
  url: 'url',
});

console.log(embeddingResponse.data);

Get an embedding task's status

获取嵌入任务的状态

Check the status of a current embedding task.

GET /ai/embeddings/{task_id}

javascript

const embedding = await client.ai.embeddings.retrieve('task_id');

console.log(embedding.data);

检查当前嵌入任务的状态。

GET /ai/embeddings/{task_id}

javascript

const embedding = await client.ai.embeddings.retrieve('task_id');

console.log(embedding.data);

List all clusters

列出所有聚类

GET /ai/clusters

javascript

// Automatically fetches more pages as needed.
for await (const clusterListResponse of client.ai.clusters.list()) {
  console.log(clusterListResponse.task_id);
}

GET /ai/clusters

javascript

// 根据需要自动获取更多页面数据
for await (const clusterListResponse of client.ai.clusters.list()) {
  console.log(clusterListResponse.task_id);
}

Compute new clusters

计算新聚类

Starts a background task to compute how the data in an embedded storage bucket is clustered.

POST /ai/clusters

— Required:

bucket

javascript

const response = await client.ai.clusters.compute({ bucket: 'bucket' });

console.log(response.data);

启动后台任务，计算嵌入存储桶中数据的聚类情况。

POST /ai/clusters

— 必填参数：

bucket

javascript

const response = await client.ai.clusters.compute({ bucket: 'bucket' });

console.log(response.data);

Fetch a cluster

获取单个聚类

GET /ai/clusters/{task_id}

javascript

const cluster = await client.ai.clusters.retrieve('task_id');

console.log(cluster.data);

GET /ai/clusters/{task_id}

javascript

const cluster = await client.ai.clusters.retrieve('task_id');

console.log(cluster.data);

Delete a cluster

删除聚类

DELETE /ai/clusters/{task_id}

javascript

await client.ai.clusters.delete('task_id');

DELETE /ai/clusters/{task_id}

javascript

await client.ai.clusters.delete('task_id');

Fetch a cluster visualization

获取聚类可视化图

GET /ai/clusters/{task_id}/graph

javascript

const response = await client.ai.clusters.fetchGraph('task_id');

console.log(response);

const content = await response.blob();
console.log(content);

GET /ai/clusters/{task_id}/graph

javascript

const response = await client.ai.clusters.fetchGraph('task_id');

console.log(response);

const content = await response.blob();
console.log(content);

Transcribe speech to text

语音转文字

Transcribe speech to text.

POST /ai/audio/transcriptions

javascript

const response = await client.ai.audio.transcribe({ model: 'distil-whisper/distil-large-v2' });

console.log(response.text);

将语音转录为文字。

POST /ai/audio/transcriptions

javascript

const response = await client.ai.audio.transcribe({ model: 'distil-whisper/distil-large-v2' });

console.log(response.text);

Create a chat completion

创建聊天补全

Chat with a language model.

POST /ai/chat/completions

— Required:

messages

javascript

const response = await client.ai.chat.createCompletion({
  messages: [
    { role: 'system', content: 'You are a friendly chatbot.' },
    { role: 'user', content: 'Hello, world!' },
  ],
});

console.log(response);

与语言模型进行对话。

POST /ai/chat/completions

— 必填参数：

messages

javascript

const response = await client.ai.chat.createCompletion({
  messages: [
    { role: 'system', content: '你是一个友好的聊天机器人。' },
    { role: 'user', content: '你好，世界！' },
  ],
});

console.log(response);

List fine tuning jobs

列出微调任务

Retrieve a list of all fine tuning jobs created by the user.

GET /ai/fine_tuning/jobs

javascript

const jobs = await client.ai.fineTuning.jobs.list();

console.log(jobs.data);

检索用户创建的所有微调任务列表。

GET /ai/fine_tuning/jobs

javascript

const jobs = await client.ai.fineTuning.jobs.list();

console.log(jobs.data);

Create a fine tuning job

创建微调任务

Create a new fine tuning job.

POST /ai/fine_tuning/jobs

— Required:

model

training_file

javascript

const fineTuningJob = await client.ai.fineTuning.jobs.create({
  model: 'model',
  training_file: 'training_file',
});

console.log(fineTuningJob.id);

创建新的微调任务。

POST /ai/fine_tuning/jobs

— 必填参数：

model

training_file

javascript

const fineTuningJob = await client.ai.fineTuning.jobs.create({
  model: 'model',
  training_file: 'training_file',
});

console.log(fineTuningJob.id);

Get a fine tuning job

获取单个微调任务

Retrieve a fine tuning job by

job_id

GET /ai/fine_tuning/jobs/{job_id}

javascript

const fineTuningJob = await client.ai.fineTuning.jobs.retrieve('job_id');

console.log(fineTuningJob.id);

通过

job_id

检索微调任务。

GET /ai/fine_tuning/jobs/{job_id}

javascript

const fineTuningJob = await client.ai.fineTuning.jobs.retrieve('job_id');

console.log(fineTuningJob.id);

Cancel a fine tuning job

取消微调任务

Cancel a fine tuning job.

POST /ai/fine_tuning/jobs/{job_id}/cancel

javascript

const fineTuningJob = await client.ai.fineTuning.jobs.cancel('job_id');

console.log(fineTuningJob.id);

取消微调任务。

POST /ai/fine_tuning/jobs/{job_id}/cancel

javascript

const fineTuningJob = await client.ai.fineTuning.jobs.cancel('job_id');

console.log(fineTuningJob.id);

Get available models

获取可用模型

This endpoint returns a list of Open Source and OpenAI models that are available for use.

GET /ai/models

javascript

const response = await client.ai.retrieveModels();

console.log(response.data);

该接口返回可使用的开源模型和OpenAI模型列表。

GET /ai/models

javascript

const response = await client.ai.retrieveModels();

console.log(response.data);

Summarize file content

总结文件内容

Generate a summary of a file's contents.

POST /ai/summarize

— Required:

bucket

filename

javascript

const response = await client.ai.summarize({ bucket: 'bucket', filename: 'filename' });

console.log(response.data);

生成文件内容的总结。

POST /ai/summarize

— 必填参数：

bucket

filename

javascript

const response = await client.ai.summarize({ bucket: 'bucket', filename: 'filename' });

console.log(response.data);