Async Python client for the Nexus AI infrastructure API
Project description
nexus-client
Async Python client for the Nexus AI infrastructure API.
Install
pip install nexus-client
Quick start
import asyncio
from nexus_client import AILayerClient
async def main():
client = AILayerClient(
base_url="https://your-nexus-host/api",
api_key="your-api-key",
)
agent = await client.create_agent(
name="assistant",
model="openai/gpt-4o-mini",
system_prompt="You are a helpful assistant.",
)
thread = await client.create_thread(agent_id=agent["id"])
async for event in client.stream_chat(
agent_id=agent["id"],
thread_id=thread["id"],
message={"role": "user", "content": [{"type": "text", "text": "Hello!"}]},
):
if event.type == "delta" and event.text:
print(event.text, end="", flush=True)
asyncio.run(main())
See the full docs for all methods and stream event types.
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
ai_layer_client-0.1.0.tar.gz
(3.9 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 ai_layer_client-0.1.0.tar.gz.
File metadata
- Download URL: ai_layer_client-0.1.0.tar.gz
- Upload date:
- Size: 3.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
69ddc56d131d8d5b10cad3e4cde06552725e1cb799265d0b924708ca5d1646f8
|
|
| MD5 |
90b0eea130a2aaa51323e837b15ad807
|
|
| BLAKE2b-256 |
6faeb4bb1c053692a7ffcfba77c205523f8965ec4887fd2f3bd1084b8ec50348
|
File details
Details for the file ai_layer_client-0.1.0-py3-none-any.whl.
File metadata
- Download URL: ai_layer_client-0.1.0-py3-none-any.whl
- Upload date:
- Size: 4.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a567335c108c0dbab974cd8a0dd69f0312135b551f0eeeb7328102e53a48048a
|
|
| MD5 |
14eeb564a65721a549dd081490570774
|
|
| BLAKE2b-256 |
cfc114d8209fe337239eef49a234b9d0f24f0a9668c397034f48e1f28c378d93
|