Heiner Lohaus
9239cadd8b
Add Response Handler to OpenaiChat
...
Update Providers with WebDriver
Add WebDriverSession helper
Use native streaming in curl_cffi
11 months ago
Tekky
2fcb3f949b
Merge pull request #1267 from hlohaus/any
...
Add AiChatOnline, ChatgptDemoAi, ChatgptNext Providers
11 months ago
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
11 months ago
Tekky
ca3eaaffee
Merge pull request #1264 from hlohaus/any
...
Improve providers
11 months ago
Heiner Lohaus
e4caf1d0ca
Improve providers
11 months ago
Tekky
053cfa6630
Merge pull request #1262 from hlohaus/any
...
Update Readme / Headless Mode
11 months ago
Heiner Lohaus
2ebbcdf0b8
Remove virtualdisplay and add headless mode
11 months ago
H Lohaus
f57fa3a43f
Merge pull request #1261 from hlohaus/any
...
Add Poe Provider, Update AItianhuSpace Porvider
11 months ago
Heiner Lohaus
92908b4347
Add Poe Provider, Update AItianhuSpace Porvider
11 months ago
Tekky
8393b2bd56
Merge pull request #1260 from hlohaus/any
...
Update Phind and PerplexityAi - GPT-4 Providers
11 months ago
H Lohaus
235dabf2cc
Update Liaobots.py
11 months ago
H Lohaus
56db205111
Update MyShell.py
11 months ago
H Lohaus
29df5a21a8
Update Bard.py
11 months ago
H Lohaus
79c9051743
Update Phind.py
11 months ago
H Lohaus
e0541c513f
Update Phind.py
11 months ago
H Lohaus
aa12716974
Update MyShell.py
11 months ago
H Lohaus
5c5235671e
Update MyShell.py
11 months ago
H Lohaus
0625bd0a06
Update PerplexityAi.py
11 months ago
H Lohaus
cbc08d6014
Update helper.py
11 months ago
H Lohaus
51a6669210
Update Phind.py
11 months ago
H Lohaus
840157abaa
Update helper.py
11 months ago
H Lohaus
293337db98
Update helper.py
11 months ago
Heiner Lohaus
510f534c0a
Fix Bard Provider
11 months ago
Heiner Lohaus
0c4e5e5127
Fix Phind and PerplexityAi - GPT-4 Providers
...
Fix MyShell Provider
Refactor Provider __init__
Add ChatAnywhere Provider
Update models list
11 months ago
H Lohaus
6a793e782c
Merge pull request #1258 from AndPim4912/chatbase
...
Add back crutch of incorrect responses to ChatBase
11 months ago
hs_junxiang
5c16856c3f
fix: GPTalk can only use 5 times ( #1255 )
11 months ago
razrab
1906b5fd06
Add back crutch of incorrect responses to ChatBase
11 months ago
H Lohaus
52545369c5
Update OpenaiChat.py
11 months ago
Heiner Lohaus
2f64bc99ef
Fix Chatgpt4Online Provider
11 months ago
Heiner Lohaus
2fb932220d
Add Berlin and Koala Provider
11 months ago
Heiner Lohaus
745ea57c63
Add auto_continue to OpenaiChat
...
Update readme provider tables
11 months ago
Heiner Lohaus
c796ba2253
Add py_arkose_generator in OpenaiChat
11 months ago
hs_junxiang
a3c4e63577
fix: no module named 'flask' ( #1216 )
11 months ago
H Lohaus
363daeaab2
Merge pull request #1207 from hlohaus/win
...
Fix NotImplementedError on WIn
11 months ago
Luneye
23127acab2
Update Bing.py - Removed unnecessary "await" statements that could potentially lead to errors
11 months ago
Heiner Lohaus
dfefd22aa1
Add exec_js helper def
11 months ago
Heiner Lohaus
65b5227500
Fix NotImplementedError on WIn
11 months ago
H Lohaus
85ca16d77f
Merge pull request #1181 from hlohaus/arkose
...
Use asyncio subprocess in OpenaiChat
11 months ago
Luneye
b993bc00fa
Update ChatBase.py - Added jailbreak (enabled by default), Removed list incorrect responses
11 months ago
Heiner Lohaus
cc301a3dd8
Use asyncio subprocess in OpenaiChat
11 months ago
Heiner Lohaus
dc04ca9306
Add arkose_token to OpenaiChat
11 months ago
Heiner Lohaus
79cf039a88
Update config supports_message_history
11 months ago
Heiner Lohaus
0d1ae405cc
Add Llama2 Providers / Models
11 months ago
Tekky
ffa36c49e4
Merge pull request #1153 from AndPim4912/ChatBase-incorrect-responses
...
Extract keywords from incorrect responses
11 months ago
Tekky
a167970d76
Merge pull request #1149 from Luneye/patch-4
...
[suggestion] Adding new parameter to check if a provider 'natively' supports mesage history
11 months ago
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.
11 months ago
Luneye
4bb751d989
Indicated support of message history in GptForLove.py
12 months ago
Luneye
2f539d0601
Indicated support of message history in Bing.py
12 months ago
Luneye
e93887aff8
Indicated support of message history in ChatBase.py
12 months ago
Luneye
7a2c8e4cd3
Indicated support of message history in FreeGpt.py
12 months ago
Luneye
0b43c13268
Indicated support of message history in GPTalk.py
12 months ago
Luneye
c43f82e966
Indicated support of message history in Yqcloud.py
12 months ago
Luneye
c839597c6d
Indicated support of message history in You.py
12 months ago
Luneye
aee8d5e628
Indicated support of message history in FakeGpt.py
12 months ago
Luneye
7f6d85f861
Indicated support of message history in ChatForAi.py
12 months ago
Luneye
dc798b520d
Indicated support of message history in ChatgptX.py
12 months ago
Tekky
6363353670
Merge pull request #1146 from AndPim4912/GetGpt-debian-compat
...
Update GetGpt provider for Debian python3-pycryptodome compatibility
12 months ago
Tekky
4c276c7ed6
Merge pull request #1145 from AndPim4912/chatbase-invalid-response
...
Add support for detecting incorrect responses in ChatBase API requests.
12 months ago
Heiner Lohaus
979904166f
Update MyShell.py
12 months ago
razrab
87f8007345
Update GetGpt provider for Debian python3-pycryptodome compatibility
...
Try to import AES from Cryptodome.Cipher if Crypto.Cipher caused error.
12 months ago
razrab
fd2b52823b
Add support for detecting incorrect responses in ChatBase API requests.
12 months ago
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.
12 months ago
Shubh Gajjar
f0f5cb05f9
Update FreeGpt.py
...
Changed older domain url with the working new url
12 months ago
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.
12 months ago
ⲘrṨhส∂ow
3982f39424
'Refactored by Sourcery' ( #1125 )
...
Co-authored-by: Sourcery AI <>
12 months ago
Tekky
955fb4bbaa
Merge pull request #1124 from hlohaus/fake
...
Improve helper
12 months ago
Tekky
33fcf907b6
Merge pull request #1122 from Luneye/patch-2
...
Major Update for Bing - Supports latest bundle version and image analysis
12 months ago
Heiner Lohaus
598255fa26
Debug logging support
...
Async browse access token
12 months ago
Heiner Lohaus
3ae90b57ed
Improve get_cookies helper
12 months ago
Heiner Lohaus
fc15181110
Fix ChatgptAi Provider
12 months ago
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!
12 months ago
Heiner Lohaus
78f93bb737
Add rate limit error messages
12 months ago
Heiner Lohaus
63cda8d779
Fix increase timeout
...
Add Hashnode Provider
Fix Yqcloud Provider
12 months ago
Heiner Lohaus
4225a39a49
Enable Liaobots and ChatForAi again
12 months ago
Heiner Lohaus
13e89d6ab9
Fix MyShell Provider
12 months ago
Heiner Lohaus
a3af9fac3e
Add FakeGpt Provider
...
Update providers in models
12 months ago
abc
ae8dae82cf
~ | g4f `v-0.1.7.2`
...
patch / unpatch providers
12 months ago
abc
dad69d24ce
~
...
minor changes
12 months ago
abc
d4ab83a45b
~
...
automatic models fetching in GUI.
12 months ago
hs_junxiang
042ee7633b
Fix: debug.logging not work in retry provider
12 months ago
ostix360
24f7495f24
Add timeout
12 months ago
abc
5b240665fb
~ | add `g4f.Provider.GeekGpt`
12 months ago
abc
4a3b663ccd
~ | remove non-working providers
12 months ago
Heiner Lohaus
c1adfbee8e
Add Llama2 and NoowAi Provider
12 months ago
Tekky
8bdbb9e9cd
~ | Merge pull request #1068 from hlohaus/fre
...
Fix Opchatgpts and ChatForAi Provider
12 months ago
abc
1f8293250e
~
...
fix chatbase (bad) and remove from auto selection
12 months ago
Heiner Lohaus
13ffdcd61a
Fix Opchatgpts and ChatForAi Provider
...
Deprecate Vitalentum and Aivvm Provider
12 months ago
Heiner Lohaus
5048f01e26
Deprecate ChatForAi
12 months ago
Heiner Lohaus
1e8bbaaaa9
Add ChatgptLogin, ChatgptFree and GptChatly Provider
12 months ago
hs_junxiang
19346ba9ba
Fix: GptGo json.decoder.JSONDecodeError
12 months ago
abc
f74ca10fbd
~ | g4f v-0.1.6.1
...
some bug fixes
12 months ago
abc
c9c573a6e6
~ | remove DeepAi
12 months ago
abc
8964d15dc3
~ | g4f `v-0.1.5.8`
12 months ago
Tekky
e06012ae06
~ | Merge pull request #1029 from hlohaus/die
...
Some small fixes
12 months ago
Commenter123321
a77848429e
make user agent easily changeable in deepai
12 months ago
Commenter123321
e049176324
fix deepai :)
12 months ago
Commenter123321
4d4ad976ec
remove unused import in Bing.py
12 months ago
Commenter123321
3de672d023
Aivvm is the best provider no cap
12 months ago
Commenter123321
0e4297494d
Merge remote-tracking branch 'origin/main'
...
# Conflicts:
# g4f/Provider/Aivvm.py
# g4f/models.py
12 months ago
Heiner Lohaus
53192b86b1
Some small fixes
12 months ago
Commenter123321
417ce27422
Update Aivvm.py
12 months ago
abc
1883d55147
~
...
Conversion from str Provider to g4f.Provider
1 year ago
Commenter123321
58c45522ea
add cool testing for gpt-3.5 and and gpt-4
1 year ago
Commenter123321
119817c963
Merge remote-tracking branch 'origin/main'
...
# Conflicts:
# g4f/Provider/Aivvm.py
1 year ago
Heiner Lohaus
c6b33e527c
Add Proxy Support and Create Provider to Readme
...
Add proxy support to many providers
1 year ago
Heiner Lohaus
e46b5fe043
Add proxy support to all providers
1 year ago
Heiner Lohaus
6401084fd0
Add Messages and AsyncResult typing
...
Add system_message in Yqcloud
1 year ago
Heiner Lohaus
4a9d7714ad
Add Cromicle to provider list
1 year ago
abc
92e1ec6f4f
~ | `v-0.1.5.5`
...
Aiivm working again
1 year ago
Heiner Lohaus
3430b04f87
Remove Aivvm from working providers
1 year ago
Heiner Lohaus
dfdb759639
Improve code with ai
1 year ago
Heiner Lohaus
f7bb30036e
Improve code by AI
1 year ago
Heiner Lohaus
4fa6e9c0f5
Add GptGod Provider
...
Remove timeout from aiohttp providers
Disable Opchatgpts and ChatgptLogin provider
1 year ago
Heiner Lohaus
1238d9a638
Add GPTalk and GptForLove Provider
1 year ago
Heiner Lohaus
af9ed889c1
Fix timeout in create_async
1 year ago
abc
c8835b15d4
~
1 year ago
hs_junxiang
dbf54769e0
Fix: TypeError: 'type' object is not subscriptable
1 year ago
Tekky
6dc2502740
Merge branch 'main' into bom
1 year ago
Heiner Lohaus
88d2cbff09
Add AiAsk, Chatgpt4Online, ChatgptDemo
...
and ChatgptX Provider
Fix Bing, Liaobots and ChatgptAi Provider
Add "gpt_35_long" model and custom timeout
1 year ago
Hexye
3b418e8cc5
Update Cromicle.py
1 year ago
Hexye
eb13f3b01d
Create Cromicle.py
1 year ago
abc
0bd5730bcd
~ | g4f v-0.1.4.8 - Fixed `g4f.Provider.Bing`
...
implemented new "X-Sydney-EncryptedConversationSignature" found in headers from "turing/conversation/create"
1 year ago
Tekky
6eb3fa3e5f
~ | Merge pull request #982 from hlohaus/fetch
...
Fix fetch_access_token in openai
1 year ago
Heiner Lohaus
6a61cf8116
Sort providers in new dirs
1 year ago
Heiner Lohaus
136770e05b
Use custom user dir
1 year ago
Heiner Lohaus
5b2efa4aaf
Fix fetch_access_token in openai
1 year ago
Tekky
d9e527eb32
Merge pull request #975 from hlohaus/mmm
...
Bing Updates:
1 year ago
Heiner Lohaus
be9b8f796c
Add streaming in openai chat
...
Fetch access token with chromedriver
1 year ago
Heiner Lohaus
252f595b6a
Bing Updates:
...
Add retry create conversation
Removed get_cookies fallback
Add creative tone parameter
1 year ago
Tekky
c915050ac7
Merge pull request #971 from Giancarlo-Ma/main
...
feat: allow to add custom header to deepai
1 year ago
Heiner Lohaus
ff4d9ae584
Add Phind Provider
...
Add release_curl in url_cffi requets
Support create image response in Bing
1 year ago
Giancarlo-Ma
ba7d5015dc
feat: add custom header to deepai
1 year ago
Tekky
c9e4c9ce00
~ | Merge pull request #968 from st4rted/patch-1
...
fix typo in payload
1 year ago
Heiner Lohaus
d116f04322
Fix: There is no current event loop in thread
1 year ago
Heiner Lohaus
2dbeb54608
Remove fake_useragent module
1 year ago
Heiner Lohaus
eb0e2c6a93
+Curl +Async +Stream Requests
...
Update Model List
1 year ago
st4rted
3485e357ac
fix typo in payload
1 year ago
Heiner Lohaus
7b9ad21de8
Change event loop policy on windows
...
Support more versions from curl_cffi
1 year ago
Commenter123321
f8411aa1e1
aivvm's no life creator keeps patching it, but I'm just better 😉
1 year ago
Heiner Lohaus
bb481a03ab
Disable Wewordle Provider
...
Update Ylokh Provider
Improve StreamRequest
1 year ago
Heiner Lohaus
261fac86dc
Disable PerplexityAi Provider
1 year ago
Heiner Lohaus
98895e5b09
Update HuggingChat to new api
...
Impersonate Aivvm Provider
Add ChatForAi and FreeGpt Provider
Update AItianhuSpace Provider
Improve StreamRequest Support
Update get_event_loop Helper
1 year ago
Commenter123321
7181f2897b
Fix Aivvm and add new models in models.py
1 year ago
Heiner Lohaus
3c2755bc72
Add ChatgptDuo and Aibn Provider
...
Add support for "nest_asyncio",
Reuse event_loops with event_loop_policy
Support for "create_async" with synchron provider
1 year ago
Heiner Lohaus
72c3ff7a25
AItianhuSpace Provider with GPT 4 added
...
Reduced chunksize to better text completion
1 year ago
Heiner Lohaus
348670fe35
"create_async" support for BaseProvider,
...
by using ThreadPoolExecutor
Default Model for Vercel
1 year ago
Heiner Lohaus
f1b6880f7e
Add Myshell Provider
...
Remove auto proxy prefix
1 year ago
Heiner Lohaus
4edd7518de
Fix: Aivvm: KeyError: ''
...
and TypeError: issubclass() arg 1 must be a class
1 year ago
abc
bf78b4d033
~ | improve Vercel & g4f.Completion.create
1 year ago
abc
6c2e3cc53c
~ | improve Vercel & g4f.Completion.create
...
added `.Completion.create` class.
```py
response = g4f.Completion.create(
model='text-davinci-003', prompt="Hello")
print(response)
```
1 year ago