OpenAI SDK Integration

GateFlow is fully compatible with the OpenAI SDK. Just change the base URL and use your GateFlow API key.

Installation

Python

pip install openai

Node.js

npm install openai

Go

go get github.com/sashabaranov/go-openai

Configuration

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.gateflow.ai/v1",
    api_key="gw_prod_your_key_here"
)

TypeScript/Node.js

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.gateflow.ai/v1',
  apiKey: 'gw_prod_your_key_here',
});

Environment Variables

export OPENAI_BASE_URL="https://api.gateflow.ai/v1"
export OPENAI_API_KEY="gw_prod_your_key_here"

Then in code:

from openai import OpenAI
client = OpenAI()  # Uses environment variables

Usage Examples

Chat Completions

response = client.chat.completions.create(
    model="gpt-4o",  # Or claude-3-5-sonnet, gemini-1.5-pro, etc.
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is GateFlow?"}
    ]
)

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

Streaming

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

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

Embeddings

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="Hello world"
)

embedding = response.data[0].embedding

Function Calling

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "What's the weather in Paris?"}],
    tools=[{
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string"}
                },
                "required": ["location"]
            }
        }
    }]
)

GateFlow Extensions

Pass GateFlow-specific options via extra_body:

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[...],
    extra_body={
        "gateflow": {
            "cache": "skip",           # Bypass cache
            "fallbacks": ["claude-3-5-sonnet"],  # Custom fallbacks
            "tags": {"team": "support"}  # Analytics tags
        }
    }
)

Response Metadata

GateFlow adds metadata to responses:

response = client.chat.completions.create(...)

# Access GateFlow metadata (if using raw response)
gateflow_meta = response.model_extra.get("gateflow", {})
print(f"Provider: {gateflow_meta.get('provider')}")
print(f"Cost: ${gateflow_meta.get('cost', {}).get('total')}")
print(f"Cache hit: {gateflow_meta.get('cache', {}).get('hit')}")

Error Handling

from openai import OpenAI, APIError, RateLimitError

client = OpenAI(
    base_url="https://api.gateflow.ai/v1",
    api_key="gw_prod_..."
)

try:
    response = client.chat.completions.create(...)
except RateLimitError as e:
    print(f"Rate limited. Retry after: {e.response.headers.get('Retry-After')}")
except APIError as e:
    print(f"API error: {e.code} - {e.message}")

Migration from Direct OpenAI

Migrating existing code is simple:

# Before (direct OpenAI)
from openai import OpenAI
client = OpenAI(api_key="sk-...")

# After (via GateFlow)
from openai import OpenAI
client = OpenAI(
    base_url="https://api.gateflow.ai/v1",
    api_key="gw_prod_..."
)

# All your existing code works unchanged!

Next Steps

• LangChain Integration - Use with LangChain
• Vercel AI SDK - Use with Next.js
• API Reference - Full API documentation