OmniMind Protocol Python SDK for AIoT Devices
Project description
OmniMind Python SDK
OmniMind SDK is a high-performance communication library for AIoT devices using the OmniMind Protocol. It supports real-time voice streaming, text messaging, and hardware tool registration (MCP).
Installation
pip install omnimind-sdk
If you need audio support (optional):
pip install omnimind-sdk[audio]
Quick Start
from omnimind import OmniMindClient
def on_text(content, role):
print(f"[{role}] {content}")
client = OmniMindClient(
server_url="ws://127.0.0.1:8082/v1/ws",
sn="YOUR_DEVICE_SN",
token="YOUR_TOKEN"
)
client.set_text_callback(on_text)
client.connect()
client.send_text("Hello, who are you?")
Features
- Real-time Voice: Stream audio chunks using Opus/PCM.
- Tool Registration: Register hardware capabilities as tools for AI to call.
- Heartbeat: Automatic PING/PONG mechanism to keep connection alive.
- Protobuf: Efficient binary serialization.
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
omnimind_sdk-1.0.0.tar.gz
(9.2 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file omnimind_sdk-1.0.0.tar.gz.
File metadata
- Download URL: omnimind_sdk-1.0.0.tar.gz
- Upload date:
- Size: 9.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0e15db369ea6c086a5584c0c03b2680dd30375beee7e258e34610014479180de
|
|
| MD5 |
b963c9fe6b5c83e4777d69c238f54844
|
|
| BLAKE2b-256 |
2a372a8c75b0e25d23cf04ecdb2046e4e0e787e0f010f5b3cb94636bd44a50f6
|
File details
Details for the file omnimind_sdk-1.0.0-py3-none-any.whl.
File metadata
- Download URL: omnimind_sdk-1.0.0-py3-none-any.whl
- Upload date:
- Size: 9.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9606bb9b71c535c7c5a42a3484d0b9d110b53b00ecd34dd2986ce8e169de166c
|
|
| MD5 |
10ff35cdf27401963a7d746a2bcf7bbd
|
|
| BLAKE2b-256 |
b05f33ecbdd4de48394178e9ac822be2b1f4d7b5f69bf71c7d09ca49768a00ff
|