Free & Unlimited Unofficial OpenAI API Python SDK - Supports all OpenAI Models & Endpoints
An Free & Unlimited unofficial Python SDK for the OpenAI API, providing seamless integration and easy-to-use methods for interacting with OpenAI's latest powerful AI models, including GPT-4o (Including gpt-4o-audio-preview & gpt-4o-realtime-preview Models), GPT-4, GPT-3.5 Turbo, DALL·E 3, Whisper & Text-to-Speech (TTS) models for Free
gpt-4o-audio-preview to receive both audio and text responses.Install the package via pip:
pip install -U openai-unofficial
from openai_unofficial import OpenAIUnofficial
# Initialize the client
client = OpenAIUnofficial()
# Basic chat completion
response = client.chat.completions.create(
messages=[{"role": "user", "content": "Say hello!"}],
model="gpt-4o"
)
print(response.choices[0].message.content)
from openai_unofficial import OpenAIUnofficial
client = OpenAIUnofficial()
models = client.list_models()
print("Available Models:")
for model in models['data']:
print(f"- {model['id']}")
from openai_unofficial import OpenAIUnofficial
client = OpenAIUnofficial()
response = client.chat.completions.create(
messages=[{"role": "user", "content": "Tell me a joke."}],
model="gpt-4o"
)
print("ChatBot:", response.choices[0].message.content)
from openai_unofficial import OpenAIUnofficial
client = OpenAIUnofficial()
response = client.chat.completions.create(
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "What's in this image?"},
{
"type": "image_url",
"image_url": {
"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
}
},
],
}],
model="gpt-4o-mini-2024-07-18"
)
print("Response:", response.choices[0].message.content)
from openai_unofficial import OpenAIUnofficial
client = OpenAIUnofficial()
completion_stream = client.chat.completions.create(
messages=[{"role": "user", "content": "Write a short story in 3 sentences."}],
model="gpt-4o-mini-2024-07-18",
stream=True
)
for chunk in completion_stream:
content = chunk.choices[0].delta.content
if content:
print(content, end='', flush=True)
from openai_unofficial import OpenAIUnofficial
client = OpenAIUnofficial()
audio_data = client.audio.create(
input_text="This is a test of the TTS capabilities!",
model="tts-1-hd",
voice="nova"
)
with open("tts_output.mp3", "wb") as f:
f.write(audio_data)
print("TTS Audio saved as tts_output.mp3")
from openai_unofficial import OpenAIUnofficial
client = OpenAIUnofficial()
response = client.chat.completions.create(
messages=[{"role": "user", "content": "Tell me a fun fact."}],
model="gpt-4o-audio-preview",
modalities=["text", "audio"],
audio={"voice": "fable", "format": "wav"}
)
message = response.choices[0].message
print("Text Response:", message.content)
if message.audio and 'data' in message.audio:
from base64 import b64decode
with open("audio_preview.wav", "wb") as f:
f.write(b64decode(message.audio['data']))
print("Audio saved as audio_preview.wav")
from openai_unofficial import OpenAIUnofficial
client = OpenAIUnofficial()
response = client.image.create(
prompt="A futuristic cityscape at sunset",
model="dall-e-3",
size="1024x1024"
)
print("Image URL:", response.data[0].url)
from openai_unofficial import OpenAIUnofficial
client = OpenAIUnofficial()
with open("speech.mp3", "rb") as audio_file:
transcription = client.audio.transcribe(
file=audio_file,
model="whisper-1"
)
print("Transcription:", transcription.text)
The SDK supports OpenAI's function calling capabilities, allowing you to define and use tools/functions in your conversations. Here are examples of function calling & tool usage:
⚠️ Important Note: In the current version (0.1.2), complex or multiple function calling is not yet fully supported. The SDK currently supports basic function calling capabilities. Support for multiple function calls and more complex tool usage patterns will be added in upcoming releases.
from openai_unofficial import OpenAIUnofficial
import json
client = OpenAIUnofficial()
# Define your functions as tools
tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g., San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit"
}
},
"required": ["location"]
}
}
}
]
# Function to actually get weather data
def get_current_weather(location: str, unit: str = "celsius") -> str:
# This is a mock function - replace with actual weather API call
return f"The current weather in {location} is 22°{unit[0].upper()}"
# Initial conversation message
messages = [
{"role": "user", "content": "What's the weather like in London?"}
]
# First API call to get function calling response
response = client.chat.completions.create(
model="gpt-4o-mini-2024-07-18",
messages=messages,
tools=tools,
tool_choice="auto"
)
# Get the assistant's message
assistant_message = response.choices[0].message
messages.append(assistant_message.to_dict())
# Check if the model wants to call a function
if assistant_message.tool_calls:
# Process each tool call
for tool_call in assistant_message.tool_calls:
function_name = tool_call.function.name
function_args = json.loads(tool_call.function.arguments)
# Call the function and get the result
function_response = get_current_weather(**function_args)
# Append the function response to messages
messages.append({
"role": "tool",
"tool_call_id": tool_call.id,
"name": function_name,
"content": function_response
})
# Get the final response from the model
final_response = client.chat.completions.create(
model="gpt-4o-mini-2024-07-18",
messages=messages
)
print("Final Response:", final_response.choices[0].message.content)
Contributions are welcome! Please follow these steps:
git checkout -b feature/my-feature.git commit -am 'Add new feature'.git push origin feature/my-feature.Please ensure your code adheres to the project's coding standards and passes all tests.
This project is licensed under the MIT License - see the LICENSE file for details.
Note: This SDK is unofficial and not affiliated with OpenAI.
If you encounter any issues or have suggestions, please open an issue on GitHub.
Here's a partial list of models that the SDK currently supports. For Complete list, check out the /models endpoint:
Chat Models:
gpt-4gpt-4-turbogpt-4ogpt-4o-minigpt-3.5-turbogpt-3.5-turbo-16kgpt-3.5-turbo-instructgpt-4o-realtime-previewgpt-4o-audio-previewImage Generation Models:
dall-e-2dall-e-3Text-to-Speech (TTS) Models:
tts-1tts-1-hdtts-1-1106tts-1-hd-1106Audio Models:
whisper-1Embedding Models:
text-embedding-ada-002text-embedding-3-smalltext-embedding-3-largeFAQs
Free & Unlimited Unofficial OpenAI API Python SDK - Supports all OpenAI Models & Endpoints
We found that openai-unofficial demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
Security News
Malicious npm package postcss-optimizer delivers BeaverTail malware, targeting developer systems; similarities to past campaigns suggest a North Korean connection.
Security News
CISA's KEV data is now on GitHub, offering easier access, API integration, commit history tracking, and automated updates for security teams and researchers.
Security News
Opengrep forks Semgrep to preserve open source SAST in response to controversial licensing changes.