summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--README.md97
-rw-r--r--g4f/Provider/retry_provider.py2
-rw-r--r--g4f/gui/server/backend.py4
3 files changed, 42 insertions, 61 deletions
diff --git a/README.md b/README.md
index 5d0d94d8..8c41231b 100644
--- a/README.md
+++ b/README.md
@@ -6,11 +6,13 @@
> 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, re-uploads 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.
> [!Note]
-Lastet version:
->> [![PyPI version](https://badge.fury.io/py/g4f.svg)](https://pypi.org/project/g4f)
+<sup><strong>Lastet version:</strong></sup> [![PyPI version](https://img.shields.io/pypi/v/g4f?color=blue)](https://pypi.org/project/g4f) [![Docker version](https://img.shields.io/docker/v/hlohaus789/g4f?label=docker&color=blue)](https://hub.docker.com/r/hlohaus789/g4f)
```sh
pip install -U g4f
```
+```sh
+docker pull hlohaus789/g4f:latest
+```
## 🆕 What's New
- <a href="./README-DE.md"><img src="https://img.shields.io/badge/öffnen in-🇩🇪 deutsch-bleu.svg" alt="Öffnen en DE"></a>
@@ -55,19 +57,35 @@ pip install -U g4f
## 🛠️ Getting Started
-#### Prerequisites:
+#### Docker container
-1. [Download and install Python](https://www.python.org/downloads/) (Version 3.10+ is recommended).
+##### Quick start:
+
+1. [Download and install Docker](https://docs.docker.com/get-docker/)
+2. Pull lastet image and run the container:
+
+```sh
+docker pull hlohaus789/g4f:latest
+docker run -p 8080:80 -p 1337:1337 -p 7900:7900 --shm-size="2g" hlohaus789/g4f:latest
+```
+5. Open the included gui on: [http://localhost:8080/chat/](http://localhost:8080/chat/)
+or set the api base in your client to: [http://localhost:1337/v1](http://localhost:1337/v1)
+6. (Optional) If you need to log in to your provider, you can open the desktop in the container here: http://localhost:7900/?autoconnect=1&resize=scale&password=secret.
+
+#### Use python package
-#### Setting up the project:
+##### Prerequisites:
-##### Install using pypi
+1. [Download and install Python](https://www.python.org/downloads/) (Version 3.10+ is recommended).
+2. [Install Google Chrome](https://www.google.com/chrome/) for providers with webdriver
+
+##### Install using pypi:
```
pip install -U g4f
```
-##### or
+##### or:
1. Clone the GitHub repository:
@@ -108,11 +126,10 @@ pip install -r requirements.txt
```py
import g4f
-
...
```
-##### Setting up with Docker:
+#### Docker for Developers
If you have Docker installed, you can easily set up and run the project without manually installing dependencies.
@@ -165,23 +182,21 @@ docker-compose down
```python
import g4f
-g4f.debug.logging = True # Enable logging
+g4f.debug.logging = True # Enable debug logging
g4f.debug.check_version = False # Disable automatic version checking
-print(g4f.Provider.Ails.params) # Supported args
-
-# Automatic selection of provider
+print(g4f.Provider.Bing.params) # Print supported args for Bing
-# Streamed completion
+# Using automatic a provider for the given model
+## 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
+## Normal response
response = g4f.ChatCompletion.create(
model=g4f.models.gpt_4,
messages=[{"role": "user", "content": "Hello"}],
@@ -217,27 +232,20 @@ print(response)
```python
import g4f
-from g4f.Provider import (
- AItianhu,
- Aichat,
- Bard,
- Bing,
- ChatBase,
- ChatgptAi,
- OpenaiChat,
- Vercel,
- You,
- Yqcloud,
-)
+# Print all available providers
+print([
+ provider.__name__
+ for provider in g4f.Provider.__providers__
+ if provider.working
+])
-# Set with provider
+# Execute with a specific 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)
```
@@ -254,7 +262,6 @@ from g4f.Provider import (
Poe,
AItianhuSpace,
MyShell,
- Phind,
PerplexityAi,
)
@@ -264,7 +271,7 @@ webdriver = Chrome(options=options, headless=True)
for idx in range(10):
response = g4f.ChatCompletion.create(
model=g4f.models.default,
- provider=g4f.Provider.Phind,
+ provider=g4f.Provider.MyShell,
messages=[{"role": "user", "content": "Suggest me a name."}],
webdriver=webdriver
)
@@ -272,32 +279,6 @@ for idx in range(10):
webdriver.quit()
```
-##### 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.
-
-```python
-import g4f
-
-from g4f.Provider import (
- Bing,
- HuggingChat,
- OpenAssistant,
-)
-
-# Usage
-response = g4f.ChatCompletion.create(
- model=g4f.models.default,
- messages=[{"role": "user", "content": "Hello"}],
- provider=Bing,
- #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.
diff --git a/g4f/Provider/retry_provider.py b/g4f/Provider/retry_provider.py
index 5979e15b..6fdefe0f 100644
--- a/g4f/Provider/retry_provider.py
+++ b/g4f/Provider/retry_provider.py
@@ -10,7 +10,6 @@ from .. import debug
class RetryProvider(AsyncProvider):
__name__: str = "RetryProvider"
- working: bool = True
supports_stream: bool = True
def __init__(
@@ -20,6 +19,7 @@ class RetryProvider(AsyncProvider):
) -> None:
self.providers: List[Type[BaseProvider]] = providers
self.shuffle: bool = shuffle
+ self.working = True
def create_completion(
self,
diff --git a/g4f/gui/server/backend.py b/g4f/gui/server/backend.py
index 082e31b2..b0c55c8a 100644
--- a/g4f/gui/server/backend.py
+++ b/g4f/gui/server/backend.py
@@ -1,4 +1,5 @@
import g4f
+from g4f.Provider import __providers__
from flask import request
from .internet import get_search_message
@@ -45,8 +46,7 @@ class Backend_Api:
def providers(self):
return [
- provider.__name__ for provider in g4f.Provider.__providers__
- if provider.working and provider is not g4f.Provider.RetryProvider
+ provider.__name__ for provider in __providers__ if provider.working
]
def version(self):