Python Examples

pip install openai  # or litellm, or anthropic

from openai import OpenAI

client = OpenAI(
    api_key="sk-savegate-xxxxxxxxxxxxx",
    base_url="https://api.savegate.ai/v1"
)

def chat(message, model="gpt-4"):
    response = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": message}]
    )
    return response.choices[0].message.content

# Usage
result = chat("What is Python?")
print(result)

def chat_conversation(messages, model="gpt-4"):
    response = client.chat.completions.create(
        model=model,
        messages=messages
    )
    return response.choices[0].message.content

# Usage
conversation = [
    {"role": "system", "content": "You are a helpful coding assistant."},
    {"role": "user", "content": "How do I read a file in Python?"},
]

response = chat_conversation(conversation)
print(response)

# Continue conversation
conversation.append({"role": "assistant", "content": response})
conversation.append({"role": "user", "content": "Can you show me an example?"})

response = chat_conversation(conversation)
print(response)

import asyncio
from openai import AsyncOpenAI

client = AsyncOpenAI(
    api_key="sk-savegate-xxxxxxxxxxxxx",
    base_url="https://api.savegate.ai/v1"
)

async def process_multiple(prompts, model="gpt-4"):
    tasks = [
        client.chat.completions.create(
            model=model,
            messages=[{"role": "user", "content": prompt}]
        )
        for prompt in prompts
    ]
    responses = await asyncio.gather(*tasks)
    return [r.choices[0].message.content for r in responses]

# Usage
prompts = [
    "What is Python?",
    "What is JavaScript?",
    "What is Go?"
]

results = asyncio.run(process_multiple(prompts))
for prompt, result in zip(prompts, results):
    print(f"Q: {prompt}\nA: {result}\n")

def stream_chat(message, model="gpt-4", callback=None):
    stream = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": message}],
        stream=True
    )

    full_response = ""
    for chunk in stream:
        if chunk.choices[0].delta.content:
            content = chunk.choices[0].delta.content
            full_response += content
            if callback:
                callback(content)

    return full_response

# Usage
def print_chunk(chunk):
    print(chunk, end="", flush=True)

response = stream_chat("Tell me a short story", callback=print_chunk)
print("\n\nFull response:", response)

from openai import OpenAI, APIError, RateLimitError, APIConnectionError
import time

client = OpenAI(
    api_key="sk-savegate-xxxxxxxxxxxxx",
    base_url="https://api.savegate.ai/v1"
)

def chat_with_retry(message, model="gpt-4", max_retries=3):
    for attempt in range(max_retries):
        try:
            response = client.chat.completions.create(
                model=model,
                messages=[{"role": "user", "content": message}]
            )
            return response.choices[0].message.content

        except RateLimitError as e:
            if attempt == max_retries - 1:
                raise
            wait = 2 ** attempt
            print(f"Rate limit hit. Waiting {wait}s...")
            time.sleep(wait)

        except APIConnectionError as e:
            if attempt == max_retries - 1:
                raise
            print(f"Connection error. Retrying...")
            time.sleep(1)

        except APIError as e:
            print(f"API error: {e}")
            raise

# Usage
try:
    result = chat_with_retry("Hello!")
    print(result)
except Exception as e:
    print(f"Failed after retries: {e}")