instructor/docs/concepts/logging.md

In order to see the requests made to OpenAI and the responses, you can set logging to DEBUG. This will show the requests and responses made to OpenAI. This can be useful for debugging and understanding the requests and responses made to OpenAI. I would love some contributions that make this a lot cleaner, but for now this is the fastest way to see the prompts.

import instructor
import openai
import logging

from pydantic import BaseModel


# Set logging to DEBUG
logging.basicConfig(level=logging.DEBUG)

client = instructor.patch(openai.OpenAI())


class UserDetail(BaseModel):
    name: str
    age: int


user = client.chat.completions.create(
    model="gpt-3.5-turbo",
    response_model=UserDetail,
    messages=[
        {"role": "user", "content": "Extract Jason is 25 years old"},
    ],
)  # type: ignore

""" 
DEBUG:httpx:load_ssl_context verify=True cert=None trust_env=True http2=False
DEBUG:httpx:load_verify_locations cafile='/Users/jasonliu/dev/instructor/.venv/lib/python3.11/site-packages/certifi/cacert.pem'
DEBUG:instructor:Patching `client.chat.completions.create` with mode=<Mode.FUNCTIONS: 'function_call'>
DEBUG:instructor:max_retries: 1
DEBUG:openai._base_client:Request options: {'method': 'post', 'url': '/chat/completions', 'files': None, 'json_data': {'messages': [{'role': 'user', 'content': 'Extract Jason is 25 years old'}], 'model': 'gpt-3.5-turbo', 'function_call': {'name': 'UserDetail'}, 'functions': [{'name': 'UserDetail', 'description': 'Correctly extracted `UserDetail` with all the required parameters with correct types', 'parameters': {'properties': {'name': {'title': 'Name', 'type': 'string'}, 'age': {'title': 'Age', 'type': 'integer'}}, 'required': ['age', 'name'], 'type': 'object'}}]}}
DEBUG:httpcore.connection:connect_tcp.started host='api.openai.com' port=443 local_address=None timeout=5.0 socket_options=None
DEBUG:httpcore.connection:connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x105062c90>
DEBUG:httpcore.connection:start_tls.started ssl_context=<ssl.SSLContext object at 0x100748680> server_hostname='api.openai.com' timeout=5.0
DEBUG:httpcore.connection:start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x101caa150>
DEBUG:httpcore.http11:send_request_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_headers.complete
DEBUG:httpcore.http11:send_request_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:send_request_body.complete
DEBUG:httpcore.http11:receive_response_headers.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Mon, 12 Feb 2024 14:55:45 GMT'), (b'Content-Type', b'application/json'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'access-control-allow-origin', b'*'), (b'Cache-Control', b'no-cache, must-revalidate'), (b'openai-model', b'gpt-3.5-turbo-0613'), (b'openai-organization', b'scribe-ai'), (b'openai-processing-ms', b'483'), (b'openai-version', b'2020-10-01'), (b'strict-transport-security', b'max-age=15724800; includeSubDomains'), (b'x-ratelimit-limit-requests', b'10000'), (b'x-ratelimit-limit-tokens', b'2000000'), (b'x-ratelimit-remaining-requests', b'9999'), (b'x-ratelimit-remaining-tokens', b'1999975'), (b'x-ratelimit-reset-requests', b'6ms'), (b'x-ratelimit-reset-tokens', b'0s'), (b'x-request-id', b'req_f0fa476897ae165fc50fa90b7968595b'), (b'CF-Cache-Status', b'DYNAMIC'), (b'Set-Cookie', b'__cf_bm=e2_yCrwo4frh6Oq4ZufCEhNJ4lSGJ2.MMtk45X8lrMM-1707749745-1-AfWk8CyACc7aZo6GpCI82FBfI/wmPEFZLNO/Cr3eavTW3xKVFCS7G9jvwYTFLXjJr0cttYsXeLAnjwipw18R0Vo=; path=/; expires=Mon, 12-Feb-24 15:25:45 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), (b'Set-Cookie', b'_cfuvid=PyVVCGSMxTg1p.woYvHVVC9E3n69faOs5FOxaDdjXOM-1707749745711-0-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None'), (b'Server', b'cloudflare'), (b'CF-RAY', b'8545aca30c1fa22f-YYZ'), (b'Content-Encoding', b'gzip'), (b'alt-svc', b'h3=":443"; ma=86400')])
INFO:httpx:HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
DEBUG:httpcore.http11:receive_response_body.started request=<Request [b'POST']>
DEBUG:httpcore.http11:receive_response_body.complete
DEBUG:httpcore.http11:response_closed.started
DEBUG:httpcore.http11:response_closed.complete
DEBUG:openai._base_client:HTTP Request: POST https://api.openai.com/v1/chat/completions "200 OK"
DEBUG:httpcore.connection:close.started
DEBUG:httpcore.connection:close.complete
"""