retoor b9d20b4a3d feat: add console entry point and async chat streaming in client module
- Register yura CLI entry point in setup.cfg pointing to yura.cli:run
- Add new src/yura/cli.py module for command-line interface
- Implement streaming chat method in AsyncClient with websocket connection handling
- Fix ensure_connection method signature to include self parameter
- Remove redundant done check from cli_client loop to avoid premature exit
2024-11-27 22:46:21 +00:00

Yura LLM Client for Katya server

Part of project with as target replacing the native ollama protocol. This protocol supports streaming and is usable trough https and it is possible to directly attach a web client to the backend.

Install

pip install -e .

Build

make build

Command line usage

yura ws://[host]:[port]/[path]/

Python

import asyncio
from yura.client import AsyncClient

async def communicate():
    client = AsyncClient("ws://[host]:[port]/[path]/")
    async for response in client.chat("Your prompt"):
         print(response)

asyncio.run(communicate())
S
Description
Async client for the katya AI server
Readme
334 KiB
Languages
Python 96.9%
Makefile 3.1%