telnyx-ai-assistants-javascript

Name: telnyx-ai-assistants-javascript
Author: team-telnyx

27installs18forks

How to install telnyx-ai-assistants-javascript?

team-telnyx/ai/telnyx-ai-assistants-javascript

$npx -y skills add team-telnyx/ai --skill telnyx-ai-assistants-javascript

Installs into the current project.

Summary

AI voice assistants with custom instructions, knowledge bases, and tool integrations.

Files · 1

View on GitHub

SKILL.md

1	<!-- Auto-generated from Telnyx OpenAPI specs. Do not edit. -->
2
3	# Telnyx AI Assistants - JavaScript
4
5	## Installation
6
7	```bash
8	npm install telnyx@6.74.2
9	```
10
11	## Setup
12
13	```javascript
14	import Telnyx from 'telnyx';
15
16	const client = new Telnyx({
17	apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted
18	});
19	```
20
21	All examples below assume `client` is already initialized as shown above.
22
23	## Error Handling
24
25	All API calls can fail with network errors, rate limits (429), validation errors (422),
26	or authentication errors (401). Always handle errors in production code:
27
28	```javascript
29	try {
30	const assistant = await client.ai.assistants.create({
31	instructions: 'You are a helpful assistant.',
32	name: 'my-resource',
33	model: 'openai/gpt-4o',
34	});
35	} catch (err) {
36	if (err instanceof Telnyx.APIConnectionError) {
37	console.error('Network error — check connectivity and retry');
38	} else if (err instanceof Telnyx.RateLimitError) {
39	const retryAfter = err.headers?.['retry-after'] \|\| 1;
40	await new Promise(r => setTimeout(r, retryAfter * 1000));
41	} else if (err instanceof Telnyx.APIError) {
42	console.error(`API error ${err.status}: ${err.message}`);
43	if (err.status === 422) {
44	console.error('Validation error — check required fields and formats');
45	}
46	}
47	}
48	```
49
50	Common error codes: `401` invalid API key, `403` insufficient permissions,
51	`404` resource not found, `422` validation error (check field formats),
52	`429` rate limited (retry with exponential backoff).
53
54	## Important Notes
55
56	- Phone numbers must be in E.164 format (e.g., `+13125550001`). Include the `+` prefix and country code. No spaces, dashes, or parentheses.
57	- Pagination: List methods return an auto-paginating iterator. Use `for await (const item of result) { ... }` to iterate through all pages automatically.
58
59	## Reference Use Rules
60
61	Do not invent Telnyx parameters, enums, response fields, or webhook fields.
62
63	- If the parameter, enum, or response field you need is not shown inline in this skill, read [references/api-details.md](references/api-details.md) before writing code.
64	- Before using any operation in `## Additional Operations`, read [the optional-parameters section](references/api-details.md#optional-parameters) and [the response-schemas section](references/api-details.md#response-schemas).
65
66	## Core Tasks
67
68	### Create an assistant
69
70	Assistant creation is the entrypoint for any AI assistant integration. Agents need the exact creation method and the top-level fields returned by the SDK.
71
72	`client.ai.assistants.create()` — `POST /ai/assistants`
73
74	\| Parameter \| Type \| Required \| Description \|
75	\|-----------\|------\|----------\|-------------\|
76	\| `name` \| string \| Yes \| \|
77	\| `instructions` \| string \| Yes \| System instructions for the assistant. \|
78	\| `tags` \| array[string] \| No \| Tags associated with the assistant. \|
79	\| `model` \| string \| No \| ID of the model to use when `external_llm` is not set. \|
80	\| `tools` \| array[object] \| No \| Deprecated for new integrations. \|
81	\| ... \| \| \| +23 optional params in [references/api-details.md](references/api-details.md) \|
82
83	```javascript
84	const assistant = await client.ai.assistants.create({
85	instructions: 'You are a helpful assistant.',
86	name: 'my-resource',
87	model: 'openai/gpt-4o',
88	});
89
90	console.log(assistant.id);
91	```
92
93	Primary response fields:
94	- `assistant.id`
95	- `assistant.name`
96	- `assistant.model`
97	- `assistant.instructions`
98	- `assistant.createdAt`
99	- `assistant.conversationFlow`
100
101	### Chat with an assistant
102
103	Chat is the primary runtime path. Agents need the exact assistant method and the response content field.
104
105	`client.ai.assistants.chat()` — `POST /ai/assistants/{assistant_id}/chat`
106
107	\| Parameter \| Type \| Required \| Description \|
108	\|-----------\|------\|----------\|-------------\|
109	\| `content` \| string \| Yes \| The message content sent by the client to the assistant \|
110	\| `conversation_id` \| string (UUID) \| Yes \| A unique identifier for the conversation thread, used to mai... \|
111	\| `assistant_id` \| string (UUID) \| Yes \| Unique identifier of the assistant. \|
112	\| `name` \| string \| No \| The optional display name of the user sending the message \|
113
114	```javascript
115	const response = await client.ai.assistants.chat('assistant_id', {
116	content: 'Tell me a joke about cats',
117	conversation_id: '42b20469-1215-4a9a-8964-c36f66b406f4',
118	});
119
120	console.log(response.content);
121	```
122
123	Primary response fields:
124	- `response.content`
125
126	### Create an assistant test
127
128	Test creation is the main validation path for production assistant behavior before deployment.
129
130	`client.ai.assistants.tests.create()` — `POST /ai/assistants/tests`
131
132	\| Parameter \| Type \| Required \| Description \|
133	\|-----------\|------\|----------\|-------------\|
134	\| `name` \| string \|

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

telnyx-ai-assistants-javascript

27installs18forks

View on GitHub

How to install telnyx-ai-assistants-javascript?

team-telnyx/ai/telnyx-ai-assistants-javascript

$npx -y skills add team-telnyx/ai --skill telnyx-ai-assistants-javascript

Installs into the current project.

Summary

AI voice assistants with custom instructions, knowledge bases, and tool integrations.

Files · 1

View on GitHub

SKILL.md

1	<!-- Auto-generated from Telnyx OpenAPI specs. Do not edit. -->
2
3	# Telnyx AI Assistants - JavaScript
4
5	## Installation
6
7	```bash
8	npm install telnyx@6.74.2
9	```
10
11	## Setup
12
13	```javascript
14	import Telnyx from 'telnyx';
15
16	const client = new Telnyx({
17	apiKey: process.env['TELNYX_API_KEY'], // This is the default and can be omitted
18	});
19	```
20
21	All examples below assume `client` is already initialized as shown above.
22
23	## Error Handling
24
25	All API calls can fail with network errors, rate limits (429), validation errors (422),
26	or authentication errors (401). Always handle errors in production code:
27
28	```javascript
29	try {
30	const assistant = await client.ai.assistants.create({
31	instructions: 'You are a helpful assistant.',
32	name: 'my-resource',
33	model: 'openai/gpt-4o',
34	});
35	} catch (err) {
36	if (err instanceof Telnyx.APIConnectionError) {
37	console.error('Network error — check connectivity and retry');
38	} else if (err instanceof Telnyx.RateLimitError) {
39	const retryAfter = err.headers?.['retry-after'] \|\| 1;
40	await new Promise(r => setTimeout(r, retryAfter * 1000));
41	} else if (err instanceof Telnyx.APIError) {
42	console.error(`API error ${err.status}: ${err.message}`);
43	if (err.status === 422) {
44	console.error('Validation error — check required fields and formats');
45	}
46	}
47	}
48	```
49
50	Common error codes: `401` invalid API key, `403` insufficient permissions,
51	`404` resource not found, `422` validation error (check field formats),
52	`429` rate limited (retry with exponential backoff).
53
54	## Important Notes
55
56	- Phone numbers must be in E.164 format (e.g., `+13125550001`). Include the `+` prefix and country code. No spaces, dashes, or parentheses.
57	- Pagination: List methods return an auto-paginating iterator. Use `for await (const item of result) { ... }` to iterate through all pages automatically.
58
59	## Reference Use Rules
60
61	Do not invent Telnyx parameters, enums, response fields, or webhook fields.
62
63	- If the parameter, enum, or response field you need is not shown inline in this skill, read [references/api-details.md](references/api-details.md) before writing code.
64	- Before using any operation in `## Additional Operations`, read [the optional-parameters section](references/api-details.md#optional-parameters) and [the response-schemas section](references/api-details.md#response-schemas).
65
66	## Core Tasks
67
68	### Create an assistant
69
70	Assistant creation is the entrypoint for any AI assistant integration. Agents need the exact creation method and the top-level fields returned by the SDK.
71
72	`client.ai.assistants.create()` — `POST /ai/assistants`
73
74	\| Parameter \| Type \| Required \| Description \|
75	\|-----------\|------\|----------\|-------------\|
76	\| `name` \| string \| Yes \| \|
77	\| `instructions` \| string \| Yes \| System instructions for the assistant. \|
78	\| `tags` \| array[string] \| No \| Tags associated with the assistant. \|
79	\| `model` \| string \| No \| ID of the model to use when `external_llm` is not set. \|
80	\| `tools` \| array[object] \| No \| Deprecated for new integrations. \|
81	\| ... \| \| \| +23 optional params in [references/api-details.md](references/api-details.md) \|
82
83	```javascript
84	const assistant = await client.ai.assistants.create({
85	instructions: 'You are a helpful assistant.',
86	name: 'my-resource',
87	model: 'openai/gpt-4o',
88	});
89
90	console.log(assistant.id);
91	```
92
93	Primary response fields:
94	- `assistant.id`
95	- `assistant.name`
96	- `assistant.model`
97	- `assistant.instructions`
98	- `assistant.createdAt`
99	- `assistant.conversationFlow`
100
101	### Chat with an assistant
102
103	Chat is the primary runtime path. Agents need the exact assistant method and the response content field.
104
105	`client.ai.assistants.chat()` — `POST /ai/assistants/{assistant_id}/chat`
106
107	\| Parameter \| Type \| Required \| Description \|
108	\|-----------\|------\|----------\|-------------\|
109	\| `content` \| string \| Yes \| The message content sent by the client to the assistant \|
110	\| `conversation_id` \| string (UUID) \| Yes \| A unique identifier for the conversation thread, used to mai... \|
111	\| `assistant_id` \| string (UUID) \| Yes \| Unique identifier of the assistant. \|
112	\| `name` \| string \| No \| The optional display name of the user sending the message \|
113
114	```javascript
115	const response = await client.ai.assistants.chat('assistant_id', {
116	content: 'Tell me a joke about cats',
117	conversation_id: '42b20469-1215-4a9a-8964-c36f66b406f4',
118	});
119
120	console.log(response.content);
121	```
122
123	Primary response fields:
124	- `response.content`
125
126	### Create an assistant test
127
128	Test creation is the main validation path for production assistant behavior before deployment.
129
130	`client.ai.assistants.tests.create()` — `POST /ai/assistants/tests`
131
132	\| Parameter \| Type \| Required \| Description \|
133	\|-----------\|------\|----------\|-------------\|
134	\| `name` \| string \|

People who liked this also viewed

6 picks

Type