Стриминг

from openai import OpenAI, APIError

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1",
)

stream = client.chat.completions.create(
    model="shannon-3",
    messages=[{"role": "user", "content": "Explain server-sent events in three sentences."}],
    stream=True,
)

answer, reasoning, tool_calls = [], [], []
finish_reason = usage = None

try:
    for chunk in stream:
        if chunk.usage:
            usage = chunk.usage
        if not chunk.choices:
            continue
        choice = chunk.choices[0]
        delta = choice.delta

        thought = getattr(delta, "reasoning_content", None)
        if thought:
            reasoning.append(thought)
        if delta.content:
            answer.append(delta.content)
            print(delta.content, end="", flush=True)
        for call in delta.tool_calls or []:
            tool_calls.append((call.id, call.function.name, call.function.arguments))
        if choice.finish_reason:
            finish_reason = choice.finish_reason
except APIError as error:
    # A failure after the stream started arrives as an error chunk.
    print(f"\nstream failed: {error}")

print(f"\n{finish_reason} {usage}")

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.shannon-ai.com/v1",
});

const stream = await client.chat.completions.create({
  model: "shannon-3",
  messages: [{ role: "user", content: "Explain server-sent events in three sentences." }],
  stream: true,
});

let answer = "";
let reasoning = "";
const toolCalls = [];
let finishReason = null;
let usage = null;

try {
  for await (const chunk of stream) {
    if (chunk.usage) usage = chunk.usage;
    const choice = chunk.choices?.[0];
    if (!choice) continue;
    const delta = choice.delta;

    if (delta.reasoning_content) reasoning += delta.reasoning_content;
    if (delta.content) {
      answer += delta.content;
      process.stdout.write(delta.content);
    }
    for (const call of delta.tool_calls ?? []) {
      toolCalls.push({ id: call.id, name: call.function.name, arguments: call.function.arguments });
    }
    if (choice.finish_reason) finishReason = choice.finish_reason;
  }
} catch (error) {
  // A failure after the stream started arrives as an error chunk.
  console.error("\nstream failed:", error.message);
}

console.log("\n", finishReason, usage);

curl -N https://api.shannon-ai.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "shannon-3",
    "messages": [{"role": "user", "content": "Explain server-sent events in three sentences."}],
    "stream": true
  }'

import json
import requests

response = requests.post(
    "https://api.shannon-ai.com/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "shannon-3",
        "messages": [{"role": "user", "content": "Explain server-sent events in three sentences."}],
        "stream": True,
    },
    stream=True,
)

# 1. Errors before the stream are plain JSON with their own status.
if response.status_code != 200:
    raise RuntimeError(f"{response.status_code}: {response.text}")

answer, done = [], False
for raw in response.iter_lines():          # 2. one line at a time
    line = raw.decode("utf-8")
    if not line.startswith("data: "):      # 3. empty lines and ": ping" comments
        continue
    data = line[len("data: "):]
    if data == "[DONE]":                   # 4. the end of the stream
        done = True
        break
    chunk = json.loads(data)
    if "error" in chunk:                   # 5. a failure inside the stream
        raise RuntimeError(chunk["error"]["message"])
    delta = chunk["choices"][0]["delta"]
    if delta.get("content"):
        answer.append(delta["content"])
    if chunk.get("usage"):
        print(chunk["choices"][0]["finish_reason"], chunk["usage"])

if not done:
    raise RuntimeError("the stream ended before [DONE]")
print("".join(answer))

const response = await fetch("https://api.shannon-ai.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "shannon-3",
    messages: [{ role: "user", content: "Explain server-sent events in three sentences." }],
    stream: true,
  }),
});

// 1. Errors before the stream are plain JSON with their own status.
if (!response.ok) throw new Error(`${response.status}: ${await response.text()}`);

const decoder = new TextDecoder();
let buffer = "";
let answer = "";
let done = false;

read: for await (const bytes of response.body) {
  buffer += decoder.decode(bytes, { stream: true });
  const lines = buffer.split("\n");       // 2. one line at a time
  buffer = lines.pop();                    //    keep the unfinished line
  for (const line of lines) {
    if (!line.startsWith("data: ")) continue;   // 3. empty lines and ": ping" comments
    const data = line.slice(6);
    if (data === "[DONE]") {               // 4. the end of the stream
      done = true;
      break read;
    }
    const chunk = JSON.parse(data);
    if (chunk.error) throw new Error(chunk.error.message);   // 5. a failure inside the stream
    const choice = chunk.choices[0];
    if (choice.delta.content) answer += choice.delta.content;
    if (chunk.usage) console.log(choice.finish_reason, chunk.usage);
  }
}

if (!done) throw new Error("the stream ended before [DONE]");
console.log(answer);