Obsługa strumieni za pomocą Python SDK

Klienci synchroniczni a asynchroniczni do strumieniowania

# Synchronous client (simple scripts)
from openai import OpenAI
client = OpenAI()

# Asynchronous client (web servers, concurrent workloads)
from openai import AsyncOpenAI
async_client = AsyncOpenAI()

# The async client has the same API surface as the sync client
# but all methods are coroutines that must be awaited

Asynchroniczne strumieniowanie za pomocą AsyncOpenAI

import asyncio
from openai import AsyncOpenAI

async_client = AsyncOpenAI()

async def async_stream_completion(prompt: str) -> str:
    stream = await async_client.chat.completions.create(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': prompt}],
        stream=True,
    )

    full_text = ''
    async for chunk in stream:
        delta = chunk.choices[0].delta.content
        if delta:
            print(delta, end='', flush=True)
            full_text += delta
    print()
    return full_text

# Run the coroutine
asyncio.run(async_stream_completion('Explain what async/await does in Python'))

Korzystanie z menedżera kontekstu strumienia

from openai import AsyncOpenAI
import asyncio

async def stream_with_context_manager(prompt: str):
    async with async_client.chat.completions.stream(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': prompt}],
    ) as stream:
        # text_stream filters None deltas automatically
        async for text in stream.text_stream:
            print(text, end='', flush=True)

    # Access final completion after stream ends
    completion = await stream.get_final_completion()
    print(f'\nUsage: {completion.usage}')
    return completion

asyncio.run(stream_with_context_manager('What are the benefits of async I/O?'))

Elegancka obsługa błędów występujących w trakcie strumieniowania

import openai

async def resilient_stream(prompt: str):
    try:
        stream = await async_client.chat.completions.create(
            model='gpt-4o-mini',
            messages=[{'role': 'user', 'content': prompt}],
            stream=True,
        )
        accumulated = ''
        async for chunk in stream:
            delta = chunk.choices[0].delta.content
            if delta:
                accumulated += delta
                yield delta  # async generator

    except openai.RateLimitError:
        yield '[Rate limit reached — please wait and retry]'
    except openai.APIConnectionError:
        yield '[Connection error — check your network]'
    except openai.APIStatusError as e:
        yield f'[API error {e.status_code}]'
    except Exception as e:
        yield f'[Unexpected error: {type(e).__name__}]'

Generator asynchroniczny do strumieniowania

from typing import AsyncGenerator

async def token_stream(
    messages: list[dict],
    model: str = 'gpt-4o-mini',
) -> AsyncGenerator[str, None]:
    stream = await async_client.chat.completions.create(
        model=model,
        messages=messages,
        stream=True,
    )
    async for chunk in stream:
        delta = chunk.choices[0].delta.content
        if delta:
            yield delta

# Consumer 1: print to terminal
async def print_stream(messages):
    async for token in token_stream(messages):
        print(token, end='', flush=True)

# Consumer 2: collect to string
async def collect_stream(messages) -> str:
    return ''.join([t async for t in token_stream(messages)])

Współbieżne żądania strumieniowania

import asyncio

async def run_parallel_streams(queries: list[str]) -> list[str]:
    async def collect(query):
        messages = [{'role': 'user', 'content': query}]
        return ''.join([t async for t in token_stream(messages)])

    results = await asyncio.gather(*[collect(q) for q in queries])
    return results

queries = [
    'What is RAG?',
    'What is a vector database?',
    'What is BM25?',
]

async def main():
    answers = await run_parallel_streams(queries)
    for q, a in zip(queries, answers):
        print(f'Q: {q}\nA: {a[:100]}\n')

asyncio.run(main())

Limity czasu i anulowanie

import asyncio

async def stream_with_timeout(messages, timeout_seconds: float = 30.0):
    try:
        async with asyncio.timeout(timeout_seconds):
            stream = await async_client.chat.completions.create(
                model='gpt-4o-mini',
                messages=messages,
                stream=True,
                timeout=timeout_seconds,  # HTTP-level timeout
            )
            async for chunk in stream:
                delta = chunk.choices[0].delta.content
                if delta:
                    yield delta
    except asyncio.TimeoutError:
        yield '\n[Stream timed out after {:.0f}s]'.format(timeout_seconds)

Buforowanie niepełnych wierszy

async def buffered_line_stream(messages):
    buffer = ''
    flush_on = {'.', '!', '?', '\n'}

    async for token in token_stream(messages):
        buffer += token
        if any(c in buffer for c in flush_on):
            # Find the last sentence-ending position
            for i, c in enumerate(reversed(buffer)):
                if c in flush_on:
                    split_pos = len(buffer) - i
                    yield buffer[:split_pos]
                    buffer = buffer[split_pos:]
                    break

    if buffer:  # flush remainder
        yield buffer

Rejestrowanie opóźnienia strumienia w środowisku produkcyjnym

import time
from dataclasses import dataclass

@dataclass
class StreamMetrics:
    prompt_chars: int
    ttft_ms: float
    total_ms: float
    token_count: int

async def instrumented_stream(messages) -> tuple[str, StreamMetrics]:
    t_start = time.perf_counter()
    t_first = None
    token_count = 0
    full_text = ''

    stream = await async_client.chat.completions.create(
        model='gpt-4o-mini', messages=messages, stream=True
    )
    async for chunk in stream:
        delta = chunk.choices[0].delta.content
        if delta:
            if t_first is None:
                t_first = time.perf_counter()
            token_count += 1
            full_text += delta

    t_end = time.perf_counter()
    prompt_len = sum(len(m.get('content', '')) for m in messages)
    metrics = StreamMetrics(
        prompt_chars=prompt_len,
        ttft_ms=(t_first - t_start) * 1000 if t_first else 0,
        total_ms=(t_end - t_start) * 1000,
        token_count=token_count,
    )
    return full_text, metrics

Testowanie kodu asynchronicznego strumieniowania

# pip install pytest pytest-asyncio
import pytest
from unittest.mock import AsyncMock, MagicMock

async def fake_stream(tokens: list[str]):
    for token in tokens:
        chunk = MagicMock()
        chunk.choices[0].delta.content = token
        yield chunk

@pytest.mark.asyncio
async def test_stream_accumulates_correctly(monkeypatch):
    mock_create = AsyncMock(return_value=fake_stream(['Hello', ', ', 'world', '!']))
    monkeypatch.setattr(async_client.chat.completions, 'create', mock_create)

    result = await collect_stream([{'role': 'user', 'content': 'Hi'}])
    assert result == 'Hello, world!'

Pomocnicze elementy SDK: stream.text i stream.final_message

async def clean_streaming_example(prompt: str):
    async with async_client.chat.completions.stream(
        model='gpt-4o-mini',
        messages=[{'role': 'user', 'content': prompt}],
    ) as stream:
        # Iterate only over text tokens, None deltas filtered automatically
        async for text in stream.text_stream:
            print(text, end='', flush=True)

    # After context exit, get accumulated result
    final = await stream.get_final_completion()
    return final.choices[0].message.content

Szybki test

Podsumowanie lekcji