Streaming

curl -N https://inference.dagon.so/v1/chat/completions \
  -H "Authorization: Bearer $DAGON_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "abliterated-model-large-flash", "stream": true, "max_tokens": 512,
       "messages": [{"role": "user", "content": "Write a haiku about ledgers."}]}'

import os
from openai import OpenAI

client = OpenAI(base_url="https://inference.dagon.so/v1", api_key=os.environ["DAGON_KEY"])

stream = client.chat.completions.create(
    model="abliterated-model-large-flash",
    messages=[{"role": "user", "content": "Write a haiku about ledgers."}],
    max_tokens=512,
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://inference.dagon.so/v1", apiKey: process.env.DAGON_KEY });

const stream = await client.chat.completions.create({
  model: "abliterated-model-large-flash",
  messages: [{ role: "user", content: "Write a haiku about ledgers." }],
  max_tokens: 512,
  stream: true,
});
for await (const chunk of stream) process.stdout.write(chunk.choices[0]?.delta?.content ?? "");