Archives/gpt4free
2
0
Fork 0
mirror of https://github.com/xtekky/gpt4free.git synced 2024-11-05 00:01:00 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,666 Commits 6 Branches 158 Tags 181 MiB
9aeae65b9b
Commit Graph

386 Commits

Author SHA1 Message Date
Heiner Lohaus
d743ee0c26 Add error classes 
Move version check to debug
 2023-12-11 00:56:06 +01:00
Heiner Lohaus
62397ad112 Remove needs_auth, add proxy support in VoiGpt 2023-12-10 23:43:48 +01:00
Meshwa428
983d17cb7b
Added a new provider voigpt.com (#1328) 
* added the new VoiGpt provider

* fixed the voigpt and moved it to needs_auth

* added auth detail and doc to voiGpt provider
 2023-12-10 23:22:58 +01:00
H Lohaus
c3ccc4e819
Fix llama2 provider, Update TOC in readme (#1325) 2023-12-08 20:07:28 +01:00
Heiner Lohaus
bb34642fcb Update readme. Add docker hub 2023-12-07 14:30:55 +01:00
H Lohaus
484b96d850
Add websearch to gui (#1314) 
* Add websearch to gui
* Fix version_check config
* Add version badge in README.md
* Show version in gui
* Add docker hub build
* Fix gui backend, improve style
 2023-12-07 07:18:05 +01:00
H Lohaus
5862d55abf
Update Pi.py 2023-12-06 13:47:22 +01:00
Heiner Lohaus
3576dee75a Add selenium to dockerfile 
Load model and provider list in gui
Remove needs_auth in HuggingChat
Add default model and login url in gui
 2023-12-06 09:35:36 +01:00
Heiner Lohaus
2157ccbcdb Add get_session_from_browser as cloudflare bypass 2023-12-02 05:40:07 +01:00
Heiner Lohaus
cd6ccdd03b Add proxy support / fix streaming 2023-12-02 00:34:05 +01:00
Heiner Lohaus
e74af803e7 Update pi provider 2023-12-01 23:56:12 +01:00
madonchik123
b0276f6c9e
Added new provider PI (Hacky way to use) (#1291) 
* Added new provider PI (Hacky way to use)

* Updated models endpoint made it show real info about the model.py

* Added cloudscraper to the requirements

* Fixed some bugs aka made streaming also return role
 2023-12-01 23:11:52 +01:00
abc
1ade1d959c ~ 
chatgptx not working
 2023-11-24 14:20:22 +00:00
abc
10a3832458 ~ 
fix DeepInfra
 2023-11-24 14:16:00 +00:00
Heiner Lohaus
4cec1ed9aa Fix ChatgptAi Provider 2023-11-22 21:21:57 +01:00
Heiner Lohaus
ebb6427100 Add GptTalkRu Provider 2023-11-22 21:21:29 +01:00
Heiner Lohaus
fc74c8f350 Disable ChatgptDemoAi, ChatAnywhere and Berlin 2023-11-22 21:20:46 +01:00
Heiner Lohaus
ea3cb0d5e9 Fix Phind and GptGo Provider 2023-11-22 15:22:36 +01:00
abc
063696630c ~ | g4f v-0.1.8.9 2023-11-20 19:00:56 +00:00
abc
9140541179 ~ | improve compatibility 2023-11-20 18:40:55 +00:00
Tekky
4f7ebdab73
Merge branch 'main' into webdriver 2023-11-20 18:27:30 +00:00
H Lohaus
a2b803a56c
Update AItianhu.py 2023-11-20 17:35:18 +01:00
H Lohaus
ad78589843
Update GptGo.py 2023-11-20 17:34:21 +01:00
Heiner Lohaus
08e308348b Add webdriver module 2023-11-20 14:00:40 +01:00
Heiner Lohaus
702837a33a Add auto support params method 2023-11-20 13:59:14 +01:00
razrab
cd4207a146 Fix tupo in GptGo 2023-11-20 09:22:20 +03:00
abc
d4c8f3e8d5 ~ | 
trying to improve compability with python versions < 3.8
 2023-11-19 23:14:30 +00:00
Tekky
eeb26036ca
Merge pull request #1269 from hlohaus/any 
Add Response Handler to OpenaiChat
 2023-11-19 22:42:50 +00:00
Heiner Lohaus
9239cadd8b Add Response Handler to OpenaiChat 
Update Providers with WebDriver
Add WebDriverSession helper
Use native streaming in curl_cffi
 2023-11-19 05:36:04 +01:00
Tekky
2fcb3f949b
Merge pull request #1267 from hlohaus/any 
Add AiChatOnline, ChatgptDemoAi, ChatgptNext Providers
 2023-11-18 11:24:39 +00:00
Heiner Lohaus
cadc507fad Add AiChatOnline, ChatgptDemoAi, ChatgptNext Providers 
Add OnlineGpt and TalkAi Provider
Add get_random_string and get_random_hex helper
Remove funcaptcha package
 2023-11-18 04:38:31 +01:00
Tekky
ca3eaaffee
Merge pull request #1264 from hlohaus/any 
Improve providers
 2023-11-18 02:40:09 +00:00
Heiner Lohaus
e4caf1d0ca Improve providers 2023-11-17 11:16:49 +01:00
Tekky
053cfa6630
Merge pull request #1262 from hlohaus/any 
Update Readme / Headless Mode
 2023-11-17 08:28:55 +00:00
Heiner Lohaus
2ebbcdf0b8 Remove virtualdisplay and add headless mode 2023-11-17 04:50:37 +01:00
H Lohaus
f57fa3a43f
Merge pull request #1261 from hlohaus/any 
Add Poe Provider, Update AItianhuSpace Porvider
 2023-11-17 03:21:50 +01:00
Heiner Lohaus
92908b4347 Add Poe Provider, Update AItianhuSpace Porvider 2023-11-17 03:19:27 +01:00
Tekky
8393b2bd56
Merge pull request #1260 from hlohaus/any 
Update Phind and PerplexityAi - GPT-4 Providers
 2023-11-16 20:48:26 +00:00
H Lohaus
235dabf2cc
Update Liaobots.py 2023-11-16 19:46:25 +01:00
H Lohaus
56db205111
Update MyShell.py 2023-11-16 19:41:31 +01:00
H Lohaus
29df5a21a8
Update Bard.py 2023-11-16 19:28:59 +01:00
H Lohaus
79c9051743
Update Phind.py 2023-11-16 19:24:15 +01:00
H Lohaus
e0541c513f
Update Phind.py 2023-11-16 19:02:53 +01:00
H Lohaus
aa12716974
Update MyShell.py 2023-11-16 18:54:59 +01:00
H Lohaus
5c5235671e
Update MyShell.py 2023-11-16 18:51:24 +01:00
H Lohaus
0625bd0a06
Update PerplexityAi.py 2023-11-16 18:47:20 +01:00
H Lohaus
cbc08d6014
Update helper.py 2023-11-16 18:39:34 +01:00
H Lohaus
51a6669210
Update Phind.py 2023-11-16 18:35:22 +01:00
H Lohaus
840157abaa
Update helper.py 2023-11-16 18:31:39 +01:00
H Lohaus
293337db98
Update helper.py 2023-11-16 18:29:07 +01:00
Heiner Lohaus
510f534c0a Fix Bard Provider 2023-11-16 18:10:19 +01:00
Heiner Lohaus
0c4e5e5127 Fix Phind and PerplexityAi - GPT-4 Providers 
Fix MyShell Provider
Refactor Provider __init__
Add ChatAnywhere Provider
Update models list
 2023-11-16 16:56:23 +01:00
H Lohaus
6a793e782c
Merge pull request #1258 from AndPim4912/chatbase 
Add back crutch of incorrect responses to ChatBase
 2023-11-16 12:12:37 +01:00
hs_junxiang
5c16856c3f fix: GPTalk can only use 5 times (#1255) 2023-11-16 17:13:35 +08:00
razrab
1906b5fd06 Add back crutch of incorrect responses to ChatBase 2023-11-16 12:05:53 +03:00
H Lohaus
52545369c5
Update OpenaiChat.py 2023-11-15 23:08:58 +01:00
Heiner Lohaus
2f64bc99ef Fix Chatgpt4Online Provider 2023-11-13 18:58:52 +01:00
Heiner Lohaus
2fb932220d Add Berlin and Koala Provider 2023-11-12 18:03:04 +01:00
Heiner Lohaus
745ea57c63 Add auto_continue to OpenaiChat 
Update readme provider tables
 2023-11-12 10:12:05 +01:00
Heiner Lohaus
c796ba2253 Add py_arkose_generator in OpenaiChat 2023-11-11 10:14:39 +01:00
hs_junxiang
a3c4e63577 fix: no module named 'flask' (#1216) 2023-11-07 10:18:17 +08:00
H Lohaus
363daeaab2
Merge pull request #1207 from hlohaus/win 
Fix NotImplementedError on WIn
 2023-11-05 10:23:22 +01:00
Luneye
23127acab2
Update Bing.py - Removed unnecessary "await" statements that could potentially lead to errors 2023-11-04 17:52:59 +01:00
Heiner Lohaus
dfefd22aa1 Add exec_js helper def 2023-11-03 22:24:35 +01:00
Heiner Lohaus
65b5227500 Fix NotImplementedError on WIn 2023-11-03 21:36:50 +01:00
H Lohaus
85ca16d77f
Merge pull request #1181 from hlohaus/arkose 
Use asyncio subprocess in OpenaiChat
 2023-10-29 19:58:56 +01:00
Luneye
b993bc00fa
Update ChatBase.py - Added jailbreak (enabled by default), Removed list incorrect responses 2023-10-29 18:34:12 +01:00
Heiner Lohaus
cc301a3dd8 Use asyncio subprocess in OpenaiChat 2023-10-28 19:02:39 +02:00
Heiner Lohaus
dc04ca9306 Add arkose_token to OpenaiChat 2023-10-28 07:21:00 +02:00
Heiner Lohaus
79cf039a88 Update config supports_message_history 2023-10-27 22:59:14 +02:00
Heiner Lohaus
0d1ae405cc Add Llama2 Providers / Models 2023-10-26 21:43:20 +02:00
Tekky
ffa36c49e4
Merge pull request #1153 from AndPim4912/ChatBase-incorrect-responses 
Extract keywords from incorrect responses
 2023-10-25 16:55:36 +01:00
Tekky
a167970d76
Merge pull request #1149 from Luneye/patch-4 
[suggestion] Adding new parameter to check if a provider 'natively' supports mesage history
 2023-10-25 14:07:40 +01:00
razrab
5ad48d9181 Extract keywords from incorrect responses 
The text of error responses is dynamically created by LLM. Need determine by keywords for more precise identification.
 2023-10-25 13:04:34 +03:00
Luneye
4bb751d989
Indicated support of message history in GptForLove.py 2023-10-24 23:46:54 +02:00
Luneye
2f539d0601
Indicated support of message history in Bing.py 2023-10-24 23:44:44 +02:00
Luneye
e93887aff8
Indicated support of message history in ChatBase.py 2023-10-24 23:43:08 +02:00
Luneye
7a2c8e4cd3
Indicated support of message history in FreeGpt.py 2023-10-24 23:42:16 +02:00
Luneye
0b43c13268
Indicated support of message history in GPTalk.py 2023-10-24 23:41:08 +02:00
Luneye
c43f82e966
Indicated support of message history in Yqcloud.py 2023-10-24 23:40:15 +02:00
Luneye
c839597c6d
Indicated support of message history in You.py 2023-10-24 23:39:29 +02:00
Luneye
aee8d5e628
Indicated support of message history in FakeGpt.py 2023-10-24 23:37:59 +02:00
Luneye
7f6d85f861
Indicated support of message history in ChatForAi.py 2023-10-24 23:36:48 +02:00
Luneye
dc798b520d
Indicated support of message history in ChatgptX.py 2023-10-24 23:30:07 +02:00
Tekky
6363353670
Merge pull request #1146 from AndPim4912/GetGpt-debian-compat 
Update GetGpt provider for Debian python3-pycryptodome compatibility
 2023-10-24 19:42:11 +01:00
Tekky
4c276c7ed6
Merge pull request #1145 from AndPim4912/chatbase-invalid-response 
Add support for detecting incorrect responses in ChatBase API requests.
 2023-10-24 19:41:56 +01:00
Heiner Lohaus
979904166f
Update MyShell.py 2023-10-24 18:58:12 +02:00
razrab
87f8007345 Update GetGpt provider for Debian python3-pycryptodome compatibility 
Try to import AES from Cryptodome.Cipher if Crypto.Cipher caused error.
 2023-10-24 19:30:57 +03:00
razrab
fd2b52823b Add support for detecting incorrect responses in ChatBase API requests. 2023-10-24 18:30:24 +03:00
Luneye
63ae5bb2cd
[suggestion] Adding new parameter to check if provider supports message history 
What are your thoughts on introducing a parameter that allows us to promptly verify whether the provider supports message history? I also considered adding a parameter to indicate whether a provider can perform web searches.
 2023-10-24 16:35:45 +02:00
Shubh Gajjar
f0f5cb05f9
Update FreeGpt.py 
Changed older domain url with the working new url
 2023-10-24 13:47:55 +05:30
Luneye
21e56a1af8
Bugfix Bing.py - Resolved Issues with system prompt, Bing personalities and enabled all supported user requests 
I used this repository (https://github.com/waylaidwanderer/node-chatgpt-api/) as a reference to fix all the bugs related to Bing "personality." I included all the required fields in the allowedMessageTypes and optionsSets (as well as sliceIds) to allow it to respond to any requests it actually supports.

Will also finish the code to fully implement the image generation functionality.
 2023-10-23 14:00:36 +02:00
ⲘrṨhส∂ow
3982f39424
'Refactored by Sourcery' (#1125) 
Co-authored-by: Sourcery AI <>
 2023-10-23 09:46:25 +02:00
Tekky
955fb4bbaa
Merge pull request #1124 from hlohaus/fake 
Improve helper
 2023-10-22 22:55:32 +01:00
Tekky
33fcf907b6
Merge pull request #1122 from Luneye/patch-2 
Major Update for Bing - Supports latest bundle version and image analysis
 2023-10-22 22:54:14 +01:00
Heiner Lohaus
598255fa26 Debug logging support 
Async browse access token
 2023-10-22 23:53:18 +02:00
Heiner Lohaus
3ae90b57ed Improve get_cookies helper 2023-10-22 20:01:14 +02:00
Heiner Lohaus
fc15181110 Fix ChatgptAi Provider 2023-10-22 17:13:13 +02:00
Luneye
c400d02024
Major Update for Bing - Supports latest bundle version and image analysis 
Here it is, a much-needed update to this service which offers numerous functionalities that the old code was unable to deliver to us.

As you may know, ChatGPT Plus subscribers now have the opportunity to request image analysis directly from GPT within the chat bar. Bing has also integrated this feature into its chatbot. With this new code, you can now provide an image using a data URI, with all the following supported extensions: jpg, jpeg, png, and gif!

**What is a data URI and how can I provide an image to Bing?**

Just to clarify, a data URI is a method for encoding data directly into a URI (Uniform Resource Identifier). It is typically used for embedding small data objects like images, text, or other resources within web pages or documents. Data URIs are widely used in web applications.

To provide an image from your desktop and retrieve it as a data URI, you can use this code: [GitHub link](https://gist.github.com/jsocol/1089733).

Now, here is a code snippet you can use to provide images to Bing:

```python
import g4f

provider = g4f.Provider.Bing
user_message = [{"role": "user", "content": "Hi, describe this image."}]

response = g4f.ChatCompletion.create(
    model = g4f.models.gpt_4,
    provider = g4f.provider,  # Corrected the provider value
    messages = user_message,
    stream = True,
    image = "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQEASABIAAD/4RiSRXhpZgAASUkqAAg..."  # Insert your full data URI image here
)

for message in response:
    print(message, flush=True, end='')
```

If you don't want to analyze the image, just do not specify the image parameter.

Regarding the implementation, the image is preprocessed within the Bing.py code, which can be resource-intensive for a server-side implementation. When using the Bing chatbot in your web browser, the image is preprocessed on your computer before being sent to the server. This preprocessing includes tasks like image rotation and compression. Although this implementation works, it would be more efficient to delegate image preprocessing to the client as it happens in reality. I will try to provide a JavaScript code for that at a later time.

As you saw, I did mention in the title that it is in Beta. The way the code is written, Bing can sometimes mess up its answers. Indeed, Bing does not really stream its responses as the other providers do. Bing sends its answers like this on each iteration:

"Hi,"
"Hi, this,"
"Hi, this is,"
"Hi, this is Bing."

Instead of sending each segment one at a time, it already adds them on each iteration. So, to simulate a normal streaming response, other contributors made the code wait for the next iteration to retrieve the newer segments and yield them. However, this method ignores something that Bing does.

Bing processes its responses in a markdown detector, which searches for links while the AI answers. If it finds a link, it saves it and waits until the AI finishes its answer to put all the found links at the very end of the answer. So if the AI is writing a link, but then on the next iteration, it finishes writing this link, it will then be deleted from the answer and appear later at the very end. Example:

"Here is your link reference ["
"Here is your link reference [^"
"Here is your link reference [^1"
"Here is your link reference [^1^"

And then the response would get stuck there because the markdown detector would have deleted this link reference in the next response and waited until the AI is finished to put it at the very end.

For this reason, I am working on an update to anticipate the markdown detector.
So please, if you guys notice any bugs with this new implementation, I would greatly appreciate it if you could report them on the issue tab of this repo. Thanks in advance, and I hope that all these explanations were clear to you!
 2023-10-22 15:59:56 +02:00
Heiner Lohaus
78f93bb737 Add rate limit error messages 2023-10-22 15:15:43 +02:00
Heiner Lohaus
63cda8d779 Fix increase timeout 
Add Hashnode Provider
Fix Yqcloud Provider
 2023-10-22 14:22:33 +02:00
Heiner Lohaus
4225a39a49 Enable Liaobots and ChatForAi again 2023-10-22 09:04:14 +02:00
Heiner Lohaus
13e89d6ab9 Fix MyShell Provider 2023-10-22 08:57:31 +02:00
Heiner Lohaus
a3af9fac3e Add FakeGpt Provider 
Update providers in models
 2023-10-22 01:22:25 +02:00
abc
ae8dae82cf ~ | g4f v-0.1.7.2 
patch / unpatch providers
 2023-10-21 00:52:19 +01:00
abc
dad69d24ce ~ 
minor changes
 2023-10-20 19:28:46 +01:00
abc
d4ab83a45b ~ 
automatic models fetching in GUI.
 2023-10-19 15:14:48 +01:00
hs_junxiang
042ee7633b Fix: debug.logging not work in retry provider 2023-10-19 10:15:38 +08:00
ostix360
24f7495f24 Add timeout 2023-10-17 09:29:12 +02:00
abc
5b240665fb ~ | add g4f.Provider.GeekGpt 2023-10-16 14:34:00 +01:00
abc
4a3b663ccd ~ | remove non-working providers 2023-10-16 00:47:10 +01:00
Heiner Lohaus
c1adfbee8e Add Llama2 and NoowAi Provider 2023-10-15 19:10:25 +02:00
Tekky
8bdbb9e9cd
~ | Merge pull request #1068 from hlohaus/fre 
Fix Opchatgpts and ChatForAi Provider
 2023-10-14 14:36:47 +01:00
abc
1f8293250e ~ 
fix chatbase (bad) and remove from auto selection
 2023-10-14 14:36:24 +01:00
Heiner Lohaus
13ffdcd61a Fix Opchatgpts and ChatForAi Provider 
Deprecate Vitalentum and Aivvm Provider
 2023-10-14 00:31:48 +02:00
Heiner Lohaus
5048f01e26 Deprecate ChatForAi 2023-10-12 21:02:51 +02:00
Heiner Lohaus
1e8bbaaaa9 Add ChatgptLogin, ChatgptFree and GptChatly Provider 2023-10-12 20:28:54 +02:00
hs_junxiang
19346ba9ba Fix: GptGo json.decoder.JSONDecodeError 2023-10-12 10:53:30 +08:00
abc
f74ca10fbd ~ | g4f v-0.1.6.1 
some bug fixes
 2023-10-11 18:56:53 +01:00
abc
c9c573a6e6 ~ | remove DeepAi 2023-10-10 22:04:42 +01:00
abc
8964d15dc3 ~ | g4f v-0.1.5.8 2023-10-10 15:48:56 +01:00
Tekky
e06012ae06
~ | Merge pull request #1029 from hlohaus/die 
Some small fixes
 2023-10-10 15:30:05 +01:00
Commenter123321
a77848429e make user agent easily changeable in deepai 2023-10-10 15:21:38 +02:00
Commenter123321
e049176324 fix deepai :) 2023-10-10 15:18:41 +02:00
Commenter123321
4d4ad976ec remove unused import in Bing.py 2023-10-10 14:49:25 +02:00
Commenter123321
3de672d023 Aivvm is the best provider no cap 2023-10-10 14:22:13 +02:00
Commenter123321
0e4297494d Merge remote-tracking branch 'origin/main' 
# Conflicts:
#	g4f/Provider/Aivvm.py
#	g4f/models.py
 2023-10-10 14:15:12 +02:00
Heiner Lohaus
53192b86b1 Some small fixes 2023-10-10 09:49:29 +02:00
Commenter123321
417ce27422
Update Aivvm.py 2023-10-10 09:13:18 +02:00
abc
1883d55147 ~ 
Conversion from str Provider to g4f.Provider
 2023-10-09 23:45:29 +01:00
Commenter123321
58c45522ea add cool testing for gpt-3.5 and and gpt-4 2023-10-09 20:53:31 +02:00
Commenter123321
119817c963 Merge remote-tracking branch 'origin/main' 
# Conflicts:
#	g4f/Provider/Aivvm.py
 2023-10-09 18:02:06 +02:00
Heiner Lohaus
c6b33e527c Add Proxy Support and Create Provider to Readme 
Add proxy support to many providers
 2023-10-09 13:33:20 +02:00
Heiner Lohaus
e46b5fe043 Add proxy support to all providers 2023-10-09 10:22:17 +02:00
Heiner Lohaus
6401084fd0 Add Messages and AsyncResult typing 
Add system_message in Yqcloud
 2023-10-08 13:59:56 +02:00
Heiner Lohaus
4a9d7714ad Add Cromicle to provider list 2023-10-08 11:39:19 +02:00
abc
92e1ec6f4f ~ | v-0.1.5.5 
Aiivm working again
 2023-10-07 21:21:34 +01:00
Heiner Lohaus
3430b04f87 Remove Aivvm from working providers 2023-10-07 19:10:26 +02:00
Heiner Lohaus
dfdb759639 Improve code with ai 2023-10-07 19:00:45 +02:00
Heiner Lohaus
f7bb30036e Improve code by AI 2023-10-07 10:17:43 +02:00
Heiner Lohaus
4fa6e9c0f5 Add GptGod Provider 
Remove timeout from aiohttp providers
Disable Opchatgpts and ChatgptLogin provider
 2023-10-07 09:02:48 +02:00
Heiner Lohaus
1238d9a638 Add GPTalk and GptForLove Provider 2023-10-07 04:03:36 +02:00
Heiner Lohaus
af9ed889c1 Fix timeout in create_async 2023-10-06 18:21:56 +02:00
abc
c8835b15d4 ~ 2023-10-06 12:21:42 +01:00
hs_junxiang
dbf54769e0 Fix: TypeError: 'type' object is not subscriptable 2023-10-06 15:50:16 +08:00
Tekky
6dc2502740
Merge branch 'main' into bom 2023-10-05 19:02:06 +01:00
Heiner Lohaus
88d2cbff09 Add AiAsk, Chatgpt4Online, ChatgptDemo 
and ChatgptX Provider
Fix Bing, Liaobots and ChatgptAi Provider
Add "gpt_35_long" model and custom timeout
 2023-10-05 05:13:37 +02:00
Hexye
3b418e8cc5
Update Cromicle.py 2023-10-04 22:51:41 +02:00
Hexye
eb13f3b01d
Create Cromicle.py 2023-10-04 22:45:34 +02:00
abc
0bd5730bcd ~ | g4f v-0.1.4.8 - Fixed g4f.Provider.Bing 
implemented new "X-Sydney-EncryptedConversationSignature" found in headers from "turing/conversation/create"
 2023-10-04 21:04:31 +01:00