Show HN: Rnet-OAuth-Python – Python lib for user-funded AI API access

A Python backend library for integrating RNet OAuth and AI Provider services. This library allows users to authenticate via RNet and pay for AI model token costs directly using their RNet account.

OAuth2 PKCE Support: Secure authorization code flow with automatic code verifier and challenge generation.** Token Management**: Exchange authorization codes for tokens and refresh expired tokens.** UserInfo Endpoint**: Fetch the authenticated user's RNet profile with an access token.** AI Integration**: Easy methods to chat with AI models using standard or streaming responses.

pip install rnet-oauth
python
from rnet_oauth import RNetAuth, RNetAi

auth = RNetAuth(
    client_id='client-id',
    client_secret='client-secret',
    redirect_uri='redirect-uri'
)
ai = RNetAi()
pkce = auth.generate_pkce()
verifier = pkce['verifier']
challenge = pkce['challenge']

auth_url = auth.get_authorization_url(challenge, state='optional-state')
tokens = auth.exchange_code_for_token(code, verifier)
access_token = tokens['access_token']
user_info = auth.get_user_info(access_token)
print(user_info['email'])
print(user_info['name'])

The UserInfo response comes from RNet's /userinfo

endpoint and may include: sub

, email

, email_verified

, name

, preferred_username

, user_id

, role

, and status

.

response = ai.chat({
    "contents": [
        {
            "role": "user",
            "parts": [{"text": "Hello!"}]
        }
    ]
}, access_token, "gemini-2.5-flash-lite")
for chunk in ai.chat_stream({
    "contents": [
        {
            "role": "user",
            "parts": [{"text": "Hello!"}]
        }
    ]
}, access_token, "gemini-2.5-flash-lite"):
    print(chunk)
with open("document.pdf", "rb") as f:
    file_buffer = f.read()

gemini_upload = ai.gemini_file_upload(access_token, "gemini-2.5-flash-lite", file_buffer, "application/pdf", "document.pdf")
print(gemini_upload['fileReference']) # Use this in chat payload

openai_upload = ai.openai_file_upload(access_token, "gpt-4o", file_buffer, "application/pdf", "document.pdf")
ai.openai_file_delete(access_token, "gpt-4o", openai_upload['fileReference'])
payload = {
    "contents": [
        {
            "role": "user",
            "parts": [
                { "text": "Based on this document, what is my name? Also search the web for the current weather in London." },
                { "fileData": { "fileUri": gemini_upload['fileReference'], "mimeType": gemini_upload['mimeType'] } }
            ]
        }
    ],
    "tools": [
        { "googleSearch": {} } # Enable Google Search tool
    ]
}

response = ai.chat(payload, access_token, "gemini-2.5-flash-lite")
print(response)

MIT