telnyx-ai-inference-python

Name: telnyx-ai-inference-python
Author: team-telnyx

187stars18forks

How to install telnyx-ai-inference-python?

team-telnyx/ai/telnyx-ai-inference-python

$npx -y skills add team-telnyx/ai --skill telnyx-ai-inference-python

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	<!-- Auto-generated from Telnyx OpenAPI specs. Do not edit. -->
2
3	# Telnyx Ai Inference - Python
4
5	## Installation
6
7	```bash
8	pip install telnyx
9	```
10
11	## Setup
12
13	```python
14	import os
15	from telnyx import Telnyx
16
17	client = Telnyx(
18	api_key=os.environ.get("TELNYX_API_KEY"), # This is the default and can be omitted
19	)
20	```
21
22	All examples below assume `client` is already initialized as shown above.
23
24	## Error Handling
25
26	All API calls can fail with network errors, rate limits (429), validation errors (422),
27	or authentication errors (401). Always handle errors in production code:
28
29	```python
30	import telnyx
31
32	try:
33	result = client.messages.send(to="+13125550001", from_="+13125550002", text="Hello")
34	except telnyx.APIConnectionError:
35	print("Network error — check connectivity and retry")
36	except telnyx.RateLimitError:
37	# 429: rate limited — wait and retry with exponential backoff
38	import time
39	time.sleep(1) # Check Retry-After header for actual delay
40	except telnyx.APIStatusError as e:
41	print(f"API error {e.status_code}: {e.message}")
42	if e.status_code == 422:
43	print("Validation error — check required fields and formats")
44	```
45
46	Common error codes: `401` invalid API key, `403` insufficient permissions,
47	`404` resource not found, `422` validation error (check field formats),
48	`429` rate limited (retry with exponential backoff).
49
50	## Important Notes
51
52	- Pagination: List methods return an auto-paginating iterator. Use `for item in page_result:` to iterate through all pages automatically.
53
54	## Transcribe speech to text
55
56	Transcribe speech to text. This endpoint is consistent with the [OpenAI Transcription API](https://platform.openai.com/docs/api-reference/audio/createTranscription) and may be used with the OpenAI JS or Python SDK.
57
58	`POST /ai/audio/transcriptions`
59
60	```python
61	response = client.ai.audio.transcribe(
62	model="distil-whisper/distil-large-v2",
63	)
64	print(response.text)
65	```
66
67	Returns: `duration` (number), `segments` (array[object]), `text` (string)
68
69	## Create a chat completion
70
71	Chat with a language model. This endpoint is consistent with the [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat) and may be used with the OpenAI JS or Python SDK.
72
73	`POST /ai/chat/completions` — Required: `messages`
74
75	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), `stream` (boolean), `temperature` (number), `tool_choice` (enum: none, auto, required), `tools` (array[object]), `top_logprobs` (integer), `top_p` (number), `use_beam_search` (boolean)
76
77	```python
78	response = client.ai.chat.create_completion(
79	messages=[{
80	"role": "system",
81	"content": "You are a friendly chatbot.",
82	}, {
83	"role": "user",
84	"content": "Hello, world!",
85	}],
86	)
87	print(response)
88	```
89
90	## List conversations
91
92	Retrieve a list of all AI conversations configured by the user. Supports [PostgREST-style query parameters](https://postgrest.org/en/stable/api.html#horizontal-filtering-rows) for filtering. Examples are included for the standard metadata fields, but you can filter on any field in the metadata JSON object.
93
94	`GET /ai/conversations`
95
96	```python
97	conversations = client.ai.conversations.list()
98	print(conversations.data)
99	```
100
101	Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)
102
103	## Create a conversation
104
105	Create a new AI Conversation.
106
107	`POST /ai/conversations`
108
109	Optional: `metadata` (object), `name` (string)
110
111	```python
112	conversation = client.ai.conversations.create()
113	print(conversation.id)
114	```
115
116	Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)
117
118	## Get Insight Template Groups
119
120	Get all insight groups
121
122	`GET /ai/conversations/insight-groups`
123
124	```python
125	page = client.ai.conversations.insight_groups.retrieve_insight_groups()
126	page = page.data[0]
127	print(page.id)
128	```
129
130	Returns: `created_at` (date-time), `description` (string), `id` (uuid), `insights` (array[object]), `name` (string), `webhook` (string)
131
132	## Create Insight Template Group
133
134	Create a new insight group
135
136	`POST /ai/conversations/insight-groups` — Required: `name`
137
138	Optional: `description` (string), `webhook` (string)
139
140	```python
141	insight_template_group_detail = client.ai.conversations.insight_groups.insight_groups(
142	name="my-resource",
143	)
144	print(insight_template_group_det

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-inference-python

187stars18forks

View on GitHub

How to install telnyx-ai-inference-python?

team-telnyx/ai/telnyx-ai-inference-python

$npx -y skills add team-telnyx/ai --skill telnyx-ai-inference-python

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	<!-- Auto-generated from Telnyx OpenAPI specs. Do not edit. -->
2
3	# Telnyx Ai Inference - Python
4
5	## Installation
6
7	```bash
8	pip install telnyx
9	```
10
11	## Setup
12
13	```python
14	import os
15	from telnyx import Telnyx
16
17	client = Telnyx(
18	api_key=os.environ.get("TELNYX_API_KEY"), # This is the default and can be omitted
19	)
20	```
21
22	All examples below assume `client` is already initialized as shown above.
23
24	## Error Handling
25
26	All API calls can fail with network errors, rate limits (429), validation errors (422),
27	or authentication errors (401). Always handle errors in production code:
28
29	```python
30	import telnyx
31
32	try:
33	result = client.messages.send(to="+13125550001", from_="+13125550002", text="Hello")
34	except telnyx.APIConnectionError:
35	print("Network error — check connectivity and retry")
36	except telnyx.RateLimitError:
37	# 429: rate limited — wait and retry with exponential backoff
38	import time
39	time.sleep(1) # Check Retry-After header for actual delay
40	except telnyx.APIStatusError as e:
41	print(f"API error {e.status_code}: {e.message}")
42	if e.status_code == 422:
43	print("Validation error — check required fields and formats")
44	```
45
46	Common error codes: `401` invalid API key, `403` insufficient permissions,
47	`404` resource not found, `422` validation error (check field formats),
48	`429` rate limited (retry with exponential backoff).
49
50	## Important Notes
51
52	- Pagination: List methods return an auto-paginating iterator. Use `for item in page_result:` to iterate through all pages automatically.
53
54	## Transcribe speech to text
55
56	Transcribe speech to text. This endpoint is consistent with the [OpenAI Transcription API](https://platform.openai.com/docs/api-reference/audio/createTranscription) and may be used with the OpenAI JS or Python SDK.
57
58	`POST /ai/audio/transcriptions`
59
60	```python
61	response = client.ai.audio.transcribe(
62	model="distil-whisper/distil-large-v2",
63	)
64	print(response.text)
65	```
66
67	Returns: `duration` (number), `segments` (array[object]), `text` (string)
68
69	## Create a chat completion
70
71	Chat with a language model. This endpoint is consistent with the [OpenAI Chat Completions API](https://platform.openai.com/docs/api-reference/chat) and may be used with the OpenAI JS or Python SDK.
72
73	`POST /ai/chat/completions` — Required: `messages`
74
75	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), `stream` (boolean), `temperature` (number), `tool_choice` (enum: none, auto, required), `tools` (array[object]), `top_logprobs` (integer), `top_p` (number), `use_beam_search` (boolean)
76
77	```python
78	response = client.ai.chat.create_completion(
79	messages=[{
80	"role": "system",
81	"content": "You are a friendly chatbot.",
82	}, {
83	"role": "user",
84	"content": "Hello, world!",
85	}],
86	)
87	print(response)
88	```
89
90	## List conversations
91
92	Retrieve a list of all AI conversations configured by the user. Supports [PostgREST-style query parameters](https://postgrest.org/en/stable/api.html#horizontal-filtering-rows) for filtering. Examples are included for the standard metadata fields, but you can filter on any field in the metadata JSON object.
93
94	`GET /ai/conversations`
95
96	```python
97	conversations = client.ai.conversations.list()
98	print(conversations.data)
99	```
100
101	Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)
102
103	## Create a conversation
104
105	Create a new AI Conversation.
106
107	`POST /ai/conversations`
108
109	Optional: `metadata` (object), `name` (string)
110
111	```python
112	conversation = client.ai.conversations.create()
113	print(conversation.id)
114	```
115
116	Returns: `created_at` (date-time), `id` (uuid), `last_message_at` (date-time), `metadata` (object), `name` (string)
117
118	## Get Insight Template Groups
119
120	Get all insight groups
121
122	`GET /ai/conversations/insight-groups`
123
124	```python
125	page = client.ai.conversations.insight_groups.retrieve_insight_groups()
126	page = page.data[0]
127	print(page.id)
128	```
129
130	Returns: `created_at` (date-time), `description` (string), `id` (uuid), `insights` (array[object]), `name` (string), `webhook` (string)
131
132	## Create Insight Template Group
133
134	Create a new insight group
135
136	`POST /ai/conversations/insight-groups` — Required: `name`
137
138	Optional: `description` (string), `webhook` (string)
139
140	```python
141	insight_template_group_detail = client.ai.conversations.insight_groups.insight_groups(
142	name="my-resource",
143	)
144	print(insight_template_group_det

People who liked this also viewed

6 picks

Type