Skip to content
Glitch

Python SDK

Use the official OpenAI Python SDK with Glitch by configuring the base URL and adding your Glitch API key.

Basic Setup

Section titled “Basic Setup”
import os
from openai import OpenAI


# Point to Glitch sensor instead of OpenAI directly
client = OpenAI(
    api_key=os.environ["GLITCH_API_KEY"],  # Your Glitch API key
    base_url="https://api.golabrat.ai/v1",  # Glitch sensor URL
)


# Use exactly like the standard OpenAI SDK
response = client.chat.completions.create(
    model="gpt-4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)


print(response.choices[0].message.content)

Error Handling

Section titled “Error Handling”

Handle Glitch security blocks gracefully:

from openai import OpenAI, APIStatusError
import os


client = OpenAI(
    api_key=os.environ["GLITCH_API_KEY"],
    base_url="https://api.golabrat.ai/v1",
)


try:
    response = client.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": user_input}]
    )
    return response.choices[0].message.content
except APIStatusError as e:
    if e.status_code == 403:
        # Security block - handle gracefully
        return "I can't process that request."
    raise

Accessing Security Headers

Section titled “Accessing Security Headers”

The OpenAI Python SDK doesn’t expose response headers directly. Use httpx for direct HTTP calls to access security metadata from /v1/chat/completions responses:

import httpx
import os


response = httpx.post(
    "https://api.golabrat.ai/v1/chat/completions",
    headers={
        "Authorization": f"Bearer {os.environ['GLITCH_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "model": "gpt-4",
        "messages": [{"role": "user", "content": "Hello"}]
    }
)


# Access security headers
blocked = response.headers.get("X-Risk-Blocked", "false") == "true"
categories = response.headers.get("X-Risk-Categories", "")
confidence = float(response.headers.get("X-Risk-Confidence", "0"))


if categories:
    print(f"Flagged: {categories} (confidence: {confidence})")

Streaming Support

Section titled “Streaming Support”

Glitch fully supports streaming responses:

from openai import OpenAI
import os


client = OpenAI(
    api_key=os.environ["GLITCH_API_KEY"],
    base_url="https://api.golabrat.ai/v1",
)


stream = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Write a poem"}],
    stream=True
)


for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Next Steps

Section titled “Next Steps”