Stream responses and manage conversations

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["LLM_SG_API_KEY"],
    base_url="https://api.llm.sg/v1",
)
stream = client.chat.completions.create(
    model=os.environ["LLM_SG_MODEL"],
    messages=[{"role": "user", "content": "Explain model routing briefly."}],
    stream=True,
)
try:
    for chunk in stream:
        if chunk.choices:
            content = chunk.choices[0].delta.content
            if content:
                print(content, end="", flush=True)
finally:
    stream.close()
print()

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["LLM_SG_API_KEY"],
    base_url="https://api.llm.sg/v1",
)
model = os.environ["LLM_SG_MODEL"]
messages = [{"role": "user", "content": "What is an API?"}]
first = client.chat.completions.create(model=model, messages=messages)
answer = first.choices[0].message.content
if not answer:
    raise RuntimeError("This example requires a text response")
print(answer)

messages.append({"role": "assistant", "content": answer})
messages.append({"role": "user", "content": "Give a restaurant analogy."})
second = client.chat.completions.create(model=model, messages=messages)
print(second.choices[0].message.content)