![248433934-7886223b-c1d1-4260-82aa-da5741f303bb](https://github.com/xtekky/gpt4free/assets/98614666/ea012c87-76e0-496a-8ac4-e2de090cc6c9)
By using this repository or any code related to it, you agree to the [legal notice](./LEGAL_NOTICE.md). The author is not responsible for any copies, forks, reuploads made by other users, or anything else related to gpt4free. This is the author's only account and repository. To prevent impersonation or irresponsible actions, please comply with the GNU GPL license this Repository uses.
- latest pypi version: [`0.1.6.4`](https://pypi.org/project/g4f/0.1.6.4)
```sh
pip install -U g4f
```
or if you just want to use the gui or interference api, install with [pipx](https://pypa.github.io/pipx/)
```sh
pipx install g4f
```
## New features
- Telegram Channel: https://t.me/g4f_channel
- g4f GUI is back !!:
Install g4f with pip and then run:
```sh
g4f gui
```
or
```sh
python -m g4f.gui.run
```
preview:
- run interference api from pypi package:
```sh
g4f api
```
or
```py
python -m g4f.interference.run
```
## Table of Contents
- [Getting Started](#getting-started)
- [Prerequisites](#prerequisites)
- [Setting up the project](#setting-up-the-project)
- [Install using pypi](#install-using-pypi)
- [Install using docker](#setting-up-with-docker)
- [Usage](#usage)
- [The `g4f` Package](#the-g4f-package)
- [interference openai-proxy api (use with openai python package)](#interference-openai-proxy-api-use-with-openai-python-package)
- [Providers](#models)
- [gpt-3.5 / gpt-4](#gpt-35--gpt-4)
- [Other Models](#other-models)
- [Related gpt4free projects](#related-gpt4free-projects)
- [Contribute](#contribute)
- [Contributors](#contributors)
- [Copyright](#copyright)
- [Star History](#star-history)
- [License](#license)
## Getting Started
#### Prerequisites:
1. [Download and install Python](https://www.python.org/downloads/) (Version 3.10+ is recommended).
#### Setting up the project:
##### Install using pypi
```
pip install -U g4f
```
##### or
1. Clone the GitHub repository:
```
git clone https://github.com/xtekky/gpt4free.git
```
2. Navigate to the project directory:
```
cd gpt4free
```
3. (Recommended) Create a Python virtual environment:
You can follow the [Python official documentation](https://docs.python.org/3/tutorial/venv.html) for virtual environments.
```
python3 -m venv venv
```
4. Activate the virtual environment:
- On Windows:
```
.\venv\Scripts\activate
```
- On macOS and Linux:
```
source venv/bin/activate
```
5. Install the required Python packages from `requirements.txt`:
```
pip install -r requirements.txt
```
6. Create a `test.py` file in the root folder and start using the repo, further Instructions are below
```py
import g4f
...
```
##### Setting up with Docker:
If you have Docker installed, you can easily set up and run the project without manually installing dependencies.
1. First, ensure you have both Docker and Docker Compose installed.
- [Install Docker](https://docs.docker.com/get-docker/)
- [Install Docker Compose](https://docs.docker.com/compose/install/)
2. Clone the GitHub repo:
```bash
git clone https://github.com/xtekky/gpt4free.git
```
3. Navigate to the project directory:
```bash
cd gpt4free
```
4. Build the Docker image:
```bash
docker compose build
```
5. Start the service using Docker Compose:
```bash
docker compose up
```
You server will now be running at `http://localhost:1337`. You can interact with the API or run your tests as you would normally.
To stop the Docker containers, simply run:
```bash
docker compose down
```
**Note:** When using Docker, any changes you make to your local files will be reflected in the Docker container thanks to the volume mapping in the `docker-compose.yml` file. If you add or remove dependencies, however, you'll need to rebuild the Docker image using `docker compose build`.
## Usage
### The `g4f` Package
#### ChatCompletion
```py
import g4f
g4f.logging = True # enable logging
g4f.check_version = False # Disable automatic version checking
print(g4f.version) # check version
print(g4f.Provider.Ails.params) # supported args
# Automatic selection of provider
# streamed completion
response = g4f.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hello"}],
stream=True,
)
for message in response:
print(message, flush=True, end='')
# normal response
response = g4f.ChatCompletion.create(
model=g4f.models.gpt_4,
messages=[{"role": "user", "content": "Hello"}],
) # alterative model setting
print(response)
```
##### Completion
```py
import g4f
allowed_models = [
'code-davinci-002',
'text-ada-001',
'text-babbage-001',
'text-curie-001',
'text-davinci-002',
'text-davinci-003'
]
response = g4f.Completion.create(
model = 'text-davinci-003',
prompt = 'say this is a test')
print(response)
```
##### Providers:
```py
import g4f
from g4f.Provider import (
AItianhu,
Acytoo,
Aichat,
Ails,
Bard,
Bing,
ChatBase,
ChatgptAi,
H2o,
HuggingChat,
OpenAssistant,
OpenaiChat,
Raycast,
Theb,
Vercel,
Vitalentum,
Ylokh,
You,
Yqcloud,
)
# Set with provider
response = g4f.ChatCompletion.create(
model="gpt-3.5-turbo",
provider=g4f.Provider.Aichat,
messages=[{"role": "user", "content": "Hello"}],
stream=True,
)
for message in response:
print(message)
```
##### Cookies Required:
Cookies are essential for the proper functioning of some service providers.
It is imperative to maintain an active session, typically achieved by logging into your account.
When running the g4f package locally, the package automatically retrieves cookies from your web browser using the `get_cookies` function. However, if you're not running it locally, you'll need to provide the cookies manually by passing them as parameters using the `cookies` parameter.
```py
import g4f
from g4f.Provider import (
Bard,
Bing,
HuggingChat,
OpenAssistant,
OpenaiChat,
)
# Usage:
response = g4f.ChatCompletion.create(
model=g4f.models.default,
messages=[{"role": "user", "content": "Hello"}],
provider=Bard,
#cookies=g4f.get_cookies(".google.com"),
cookies={"cookie_name": "value", "cookie_name2": "value2"},
auth=True
)
```
##### Async Support:
To enhance speed and overall performance, execute providers asynchronously.
The total execution time will be determined by the duration of the slowest provider's execution.
```py
import g4f, asyncio
_providers = [
g4f.Provider.Aichat,
g4f.Provider.ChatBase,
g4f.Provider.Bing,
g4f.Provider.GptGo,
g4f.Provider.You,
g4f.Provider.Yqcloud,
]
async def run_provider(provider: g4f.Provider.BaseProvider):
try:
response = await g4f.ChatCompletion.create_async(
model=g4f.models.default,
messages=[{"role": "user", "content": "Hello"}],
provider=provider,
)
print(f"{provider.__name__}:", response)
except Exception as e:
print(f"{provider.__name__}:", e)
async def run_all():
calls = [
run_provider(provider) for provider in _providers
]
await asyncio.gather(*calls)
asyncio.run(run_all())
```
##### Proxy Support:
All providers support specifying a proxy in the create function.
```py
import g4f
response = await g4f.ChatCompletion.create(
model=g4f.models.default,
messages=[{"role": "user", "content": "Hello"}],
proxy="http://host:port",
# or socks5://user:pass@host:port
)
print(f"Result:", response)
```
### interference openai-proxy api (use with openai python package)
#### run interference api from pypi package:
```py
from g4f.api import run_api
run_api()
```
#### run interference api from repo:
If you want to use the embedding function, you need to get a huggingface token. You can get one at https://huggingface.co/settings/tokens make sure your role is set to write. If you have your token, just use it instead of the OpenAI api-key.
run server:
```sh
g4f api
```
or
```sh
python -m g4f.api
```
```py
import openai
openai.api_key = "Empty if you don't use embeddings, otherwise your hugginface token"
openai.api_base = "http://localhost:1337"
def main():
chat_completion = openai.ChatCompletion.create(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "write a poem about a tree"}],
stream=True,
)
if isinstance(chat_completion, dict):
# not stream
print(chat_completion.choices[0].message.content)
else:
# stream
for token in chat_completion:
content = token["choices"][0]["delta"].get("content")
if content != None:
print(content, end="", flush=True)
if __name__ == "__main__":
main()
```
## Models
### gpt-3.5 / gpt-4
| Website| Provider| gpt-3.5 | gpt-4 | Streaming | Asynchron | Status | Auth |
| ------ | ------- | ------- | ----- | --------- | --------- | ------ | ---- |
| [www.aitianhu.com](https://www.aitianhu.com) | `g4f.Provider.AItianhu` | ✔️ | ❌ | ❌ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [chat.acytoo.com](https://chat.acytoo.com) | `g4f.Provider.Acytoo` | ✔️ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [chat-gpt.org](https://chat-gpt.org/chat) | `g4f.Provider.Aichat` | ✔️ | ❌ | ❌ | ✔️ | ![Unknown](https://img.shields.io/badge/Unknown-grey) | ❌ |
| [ai.ls](https://ai.ls) | `g4f.Provider.Ails` | ✔️ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [bard.google.com](https://bard.google.com) | `g4f.Provider.Bard` | ❌ | ❌ | ❌ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ✔️ |
| [bing.com](https://bing.com/chat) | `g4f.Provider.Bing` | ❌ | ✔️ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [www.chatbase.co](https://www.chatbase.co) | `g4f.Provider.ChatBase` | ✔️ | ✔️ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [chatgpt.ai](https://chatgpt.ai/) | `g4f.Provider.ChatgptAi` | ✔️ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [opchatgpts.net](https://opchatgpts.net) | `g4f.Provider.ChatgptLogin` | ✔️ | ❌ | ❌ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [ava-ai-ef611.web.app](https://ava-ai-ef611.web.app) | `g4f.Provider.CodeLinkAva` | ✔️ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [gptgo.ai](https://gptgo.ai) | `g4f.Provider.GptGo` | ✔️ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [gpt-gm.h2o.ai](https://gpt-gm.h2o.ai) | `g4f.Provider.H2o` | ❌ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [huggingface.co](https://huggingface.co/chat/) | `g4f.Provider.HuggingChat` | ❌ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ✔️ |
| [opchatgpts.net](https://opchatgpts.net) | `g4f.Provider.Opchatgpts` | ✔️ | ❌ | ❌ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [open-assistant.io](https://open-assistant.io/chat) | `g4f.Provider.OpenAssistant` | ❌ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ✔️ |
| [chat.openai.com](https://chat.openai.com) | `g4f.Provider.OpenaiChat` | ✔️ | ❌ | ❌ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ✔️ |
| [www.perplexity.ai](https://www.perplexity.ai) | `g4f.Provider.PerplexityAi` | ✔️ | ❌ | ❌ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [raycast.com](https://raycast.com) | `g4f.Provider.Raycast` | ✔️ | ✔️ | ✔️ | ❌ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ✔️ |
| [theb.ai](https://theb.ai) | `g4f.Provider.Theb` | ✔️ | ❌ | ✔️ | ❌ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ✔️ |
| [sdk.vercel.ai](https://sdk.vercel.ai) | `g4f.Provider.Vercel` | ✔️ | ❌ | ✔️ | ❌ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [app.vitalentum.io](https://app.vitalentum.io) | `g4f.Provider.Vitalentum` | ✔️ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [wewordle.org](https://wewordle.org) | `g4f.Provider.Wewordle` | ✔️ | ❌ | ❌ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [chat.ylokh.xyz](https://chat.ylokh.xyz) | `g4f.Provider.Ylokh` | ✔️ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [you.com](https://you.com) | `g4f.Provider.You` | ✔️ | ❌ | ❌ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [chat9.yqcloud.top](https://chat9.yqcloud.top/) | `g4f.Provider.Yqcloud` | ✔️ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [cromicle.top](https://cromicle.top) | `g4f.Provider.Cromicle` | ✔️ | ❌ | ✔️ | ✔️ | ![Active](https://img.shields.io/badge/Active-brightgreen) | ❌ |
| [aiservice.vercel.app](https://aiservice.vercel.app/) | `g4f.Provider.AiService` | ✔️ | ❌ | ❌ | ❌ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
| [chat.dfehub.com](https://chat.dfehub.com/) | `g4f.Provider.DfeHub` | ✔️ | ❌ | ✔️ | ❌ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
| [free.easychat.work](https://free.easychat.work) | `g4f.Provider.EasyChat` | ✔️ | ❌ | ✔️ | ❌ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
| [next.eqing.tech](https://next.eqing.tech/) | `g4f.Provider.Equing` | ✔️ | ❌ | ✔️ | ❌ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
| [chat9.fastgpt.me](https://chat9.fastgpt.me/) | `g4f.Provider.FastGpt` | ✔️ | ❌ | ✔️ | ❌ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
| [forefront.com](https://forefront.com) | `g4f.Provider.Forefront` | ✔️ | ❌ | ✔️ | ❌ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
| [chat.getgpt.world](https://chat.getgpt.world/) | `g4f.Provider.GetGpt` | ✔️ | ❌ | ✔️ | ❌ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
| [liaobots.com](https://liaobots.com) | `g4f.Provider.Liaobots` | ✔️ | ✔️ | ✔️ | ✔️ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
| [p5.v50.ltd](https://p5.v50.ltd) | `g4f.Provider.V50` | ✔️ | ❌ | ❌ | ❌ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
| [chat.wuguokai.xyz](https://chat.wuguokai.xyz) | `g4f.Provider.Wuguokai` | ✔️ | ❌ | ❌ | ❌ | ![Inactive](https://img.shields.io/badge/Inactive-red) | ❌ |
### Other Models
| Model | Base Provider | Provider | Website |
| --------------------------------------- | ------------- | ------------------- | ------------------------------------------- |
| palm | Google | g4f.Provider.Bard | [bard.google.com](https://bard.google.com/) |
| h2ogpt-gm-oasst1-en-2048-falcon-7b-v3 | Huggingface | g4f.Provider.H2o | [www.h2o.ai](https://www.h2o.ai/) |
| h2ogpt-gm-oasst1-en-2048-falcon-40b-v1 | Huggingface | g4f.Provider.H2o | [www.h2o.ai](https://www.h2o.ai/) |
| h2ogpt-gm-oasst1-en-2048-open-llama-13b | Huggingface | g4f.Provider.H2o | [www.h2o.ai](https://www.h2o.ai/) |
| claude-instant-v1 | Anthropic | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| claude-v1 | Anthropic | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| claude-v2 | Anthropic | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| command-light-nightly | Cohere | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| command-nightly | Cohere | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| gpt-neox-20b | Huggingface | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| oasst-sft-1-pythia-12b | Huggingface | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| oasst-sft-4-pythia-12b-epoch-3.5 | Huggingface | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| santacoder | Huggingface | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| bloom | Huggingface | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| flan-t5-xxl | Huggingface | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| code-davinci-002 | OpenAI | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| gpt-3.5-turbo-16k | OpenAI | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| gpt-3.5-turbo-16k-0613 | OpenAI | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| gpt-4-0613 | OpenAI | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| text-ada-001 | OpenAI | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| text-babbage-001 | OpenAI | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| text-curie-001 | OpenAI | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| text-davinci-002 | OpenAI | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| text-davinci-003 | OpenAI | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| llama13b-v2-chat | Replicate | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
| llama7b-v2-chat | Replicate | g4f.Provider.Vercel | [sdk.vercel.ai](https://sdk.vercel.ai/) |
## Related gpt4free projects
🎁 Projects | ⭐ Stars | 📚 Forks | 🛎 Issues | 📬 Pull requests |
gpt4free | gpt4free-ts | |||
Free AI API's & Potential Providers List | ||||
ChatGPT-Clone | ||||
ChatGpt Discord Bot | ||||
LangChain gpt4free | ||||
ChatGpt Telegram Bot | ||||
Action Translate Readme | ||||
Langchain Document GPT |
|
This project is licensed under GNU_GPL_v3.0. |