adapter_chat

Runnable HTTP server example adapter_chat.

from openai import OpenAI
import httpx
import textwrap
import json


def log_response(response: httpx.Response):
    request = response.request
    print(f"Request: {request.method} {request.url}")
    print("  Headers:")
    for key, value in request.headers.items():
        if key.lower() == "authorization":
            value = "[...]"
        if key.lower() == "cookie":
            value = value.split("=")[0] + "=..."
        print(f"    {key}: {value}")
    print("  Body:")
    try:
        request_body = json.loads(request.content)
        print(textwrap.indent(json.dumps(request_body, indent=2), "    "))
    except json.JSONDecodeError:
        print(textwrap.indent(request.content.decode(), "    "))
    print(f"Response: status_code={response.status_code}")
    print("  Headers:")
    for key, value in response.headers.items():
        if key.lower() == "set-cookie":
            value = value.split("=")[0] + "=..."
        print(f"    {key}: {value}")


client = OpenAI(api_key="foobar", base_url="http://localhost:1234/v1/")

# Enable this to log requests and responses
# client._client = httpx.Client(
#     event_hooks={"request": [print], "response": [log_response]}
# )

messages = []
prompt = input("Enter system prompt >>> ")
if len(prompt) > 0:
    messages.append({"role": "system", "content": prompt})


while True:
    prompt = input(">>> ")
    adapter = input("Active adapter >>> ")
    messages.append({"role": "user", "content": prompt})
    completion = client.chat.completions.create(
        model="default",
        messages=messages,
        max_tokens=256,
        frequency_penalty=1.0,
        top_p=0.1,
        temperature=0,
        extra_body={"adapters": [adapter]},
    )
    resp = completion.choices[0].message.content
    print(resp)
    messages.append({"role": "assistant", "content": resp})

Source: examples/server/adapter_chat.py