Commit Graph

469 Commits (5c5ce8c0f7caa77c09247a103d67a5a030d70e91)

Author SHA1 Message Date
Luneye 2f539d0601
Indicated support of message history in Bing.py 8 months ago
Luneye e93887aff8
Indicated support of message history in ChatBase.py 8 months ago
Luneye 7a2c8e4cd3
Indicated support of message history in FreeGpt.py 8 months ago
Luneye 0b43c13268
Indicated support of message history in GPTalk.py 8 months ago
Luneye c43f82e966
Indicated support of message history in Yqcloud.py 8 months ago
Luneye c839597c6d
Indicated support of message history in You.py 8 months ago
Luneye aee8d5e628
Indicated support of message history in FakeGpt.py 8 months ago
Luneye 7f6d85f861
Indicated support of message history in ChatForAi.py 8 months ago
Luneye dc798b520d
Indicated support of message history in ChatgptX.py 8 months ago
abc 01585ba9cd ~ | g4f `v-0.1.7.7` 8 months ago
Tekky 6363353670
Merge pull request #1146 from AndPim4912/GetGpt-debian-compat
Update GetGpt provider for Debian python3-pycryptodome compatibility
8 months ago
Tekky 4c276c7ed6
Merge pull request #1145 from AndPim4912/chatbase-invalid-response
Add support for detecting incorrect responses in ChatBase API requests.
8 months ago
Heiner Lohaus 979904166f
Update MyShell.py 8 months ago
razrab 87f8007345 Update GetGpt provider for Debian python3-pycryptodome compatibility
Try to import AES from Cryptodome.Cipher if Crypto.Cipher caused error.
8 months ago
razrab fd2b52823b Add support for detecting incorrect responses in ChatBase API requests. 8 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.
8 months ago
Shubh Gajjar f0f5cb05f9
Update FreeGpt.py
Changed older domain url with the working new url
8 months ago
abc 4f29ef5833 ~ | g4f `v-0.1.7.6` 9 months ago
Tekky aa95d30732
Merge pull request #1120 from AndPim4912/api-ignore-providers
Added code to ignore certain providers in the API
9 months ago
AndPim4912 8d7ad98fcb
Merge branch 'main' into api-ignore-providers 9 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.
9 months ago
Heiner Lohaus 9eee45023e
Debug config in api 9 months ago
razrab 36fe869a81 Refactor API initialization to accept a list of ignored providers. 9 months ago
ⲘrṨhส∂ow 3982f39424
'Refactored by Sourcery' (#1125)
Co-authored-by: Sourcery AI <>
9 months ago
abc b1dbf66587 ~ | g4f `v-0.1.7.5` 9 months ago
Tekky 955fb4bbaa
Merge pull request #1124 from hlohaus/fake
Improve helper
9 months ago
Tekky 33fcf907b6
Merge pull request #1122 from Luneye/patch-2
Major Update for Bing - Supports latest bundle version and image analysis
9 months ago
Heiner Lohaus 598255fa26 Debug logging support
Async browse access token
9 months ago
Heiner Lohaus 3ae90b57ed Improve get_cookies helper 9 months ago
abc ff88afa1da ~ | g4f `v-0.1.7.4` 9 months ago
Heiner Lohaus fc15181110 Fix ChatgptAi Provider 9 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!
9 months ago
Heiner Lohaus 78f93bb737 Add rate limit error messages 9 months ago
Heiner Lohaus 63cda8d779 Fix increase timeout
Add Hashnode Provider
Fix Yqcloud Provider
9 months ago
Heiner Lohaus 4225a39a49 Enable Liaobots and ChatForAi again 9 months ago
Heiner Lohaus 13e89d6ab9 Fix MyShell Provider 9 months ago
Heiner Lohaus a3af9fac3e Add FakeGpt Provider
Update providers in models
9 months ago
late 0e93d841ba fix bug - Cannot assign requested address 9 months ago
abc 2ac711ed89 ~ | g4f `v-0.1.7.2`
fix tiktok not found error
9 months ago
abc ae8dae82cf ~ | g4f `v-0.1.7.2`
patch / unpatch providers
9 months ago
abc 29e2302fb2 ~ | g4f v-0.1.7.0
quick fix
9 months ago
abc d01c2afe47 ~ | 0.1.7.0 9 months ago
abc 603b5b85a4 ~ | g4f v-0.1.6.9 9 months ago
abc dad69d24ce ~
minor changes
9 months ago
abc 0ddfe57431 ~ | quick fix 9 months ago
abc 8e7e694d81 ~ | updated g4f.api
new api and requirements
9 months ago
abc 04edb66065 ~
fix gui errors on iOS
9 months ago
abc 5b52d5a2ee ~ | g4f `v-0.1.6.8`
some quick fixes
9 months ago
abc 32c55a2fc2 ~ | g4f v-0.1.6.7 9 months ago
abc d4ab83a45b ~
automatic models fetching in GUI.
9 months ago
abc 76083c5a17 ~ 9 months ago
hs_junxiang 042ee7633b Fix: debug.logging not work in retry provider 9 months ago
ostix360 24f7495f24 Add timeout 9 months ago
abc 9776545ab0 ~ | g4f `v-0.1.6.6` 9 months ago
abc c1fbb13edc ~ | update working providers list & gpt-4 providers 9 months ago
abc 5b240665fb ~ | add `g4f.Provider.GeekGpt` 9 months ago
abc d93b0fe7eb ~ | g4f `v-0.1.6.5` 9 months ago
abc 4a3b663ccd ~ | remove non-working providers 9 months ago
Heiner Lohaus c1adfbee8e Add Llama2 and NoowAi Provider 9 months ago
abc 7e7ab3d066 ~ | g4f `v-0.1.6.4` 9 months ago
Tekky 8bdbb9e9cd
~ | Merge pull request #1068 from hlohaus/fre
Fix Opchatgpts and ChatForAi Provider
9 months ago
abc 1f8293250e ~
fix chatbase (bad) and remove from auto selection
9 months ago
Heiner Lohaus 13ffdcd61a Fix Opchatgpts and ChatForAi Provider
Deprecate Vitalentum and Aivvm Provider
9 months ago
abc 5d443b1aa7 g4f `v-0.1.6.3` 9 months ago
Tekky a917c8ea8e
~ | Merge pull request #1065 from adeyinkaezra123/typo-fixes
fix: minor typo fixes across multiple files
9 months ago
Tekky 99bc58ab99
~ | Merge pull request #1060 from hlohaus/don
Add ChatgptLogin, ChatgptFree and GptChatly Provider
9 months ago
Ezra Adeyinka 6a74fc3a95 fix: remove typo in readme and configs 9 months ago
hs_junxiang c84ff59145 feat: ignore providers(#1014) 9 months ago
Heiner Lohaus 5048f01e26 Deprecate ChatForAi 9 months ago
Heiner Lohaus 1e8bbaaaa9 Add ChatgptLogin, ChatgptFree and GptChatly Provider 9 months ago
abc 5a64e238c8 ~ | g4f `v-0.1.6.2` 9 months ago
abc aa4824b6a2 ~ 9 months ago
abc dc502a22de ~ 9 months ago
Tekky 86248b44bc
~ | Merge pull request #1051 from ahobsonsayers/unify-g4f-cli
Unify g4f tools (gui and api) into one CLI
9 months ago
hs_junxiang 19346ba9ba Fix: GptGo json.decoder.JSONDecodeError 9 months ago
Arran Hobson Sayers 77697be333 Unify g4f tools into one CLI 9 months ago
abc f74ca10fbd ~ | g4f v-0.1.6.1
some bug fixes
9 months ago
Tekky c433863f30
~ | Merge pull request #1044 from Lin-jun-xiang/main
Fix: TypeError: unsupported operand type(s) for |:...
9 months ago
hs_junxiang 50ecd887c8 Fix: TypeError: unsupported operand type(s) for |:... 9 months ago
Ikko Eltociear Ashimine 7e6df02367
fix typo in backend.py
occured -> occurred
9 months ago
abc fbd983f628 ~ | g4f `v-0.1.5.9`(remove deepai.org) 9 months ago
abc c9c573a6e6 ~ | remove DeepAi 9 months ago
abc 8964d15dc3 ~ | g4f `v-0.1.5.8` 9 months ago
Tekky e06012ae06
~ | Merge pull request #1029 from hlohaus/die
Some small fixes
9 months ago
Commenter123321 be41898736 fix html 9 months ago
Commenter123321 86f7ea6b08 what 9 months ago
Commenter123321 d3040b0c14 change discord icon to telegram icon on gui 9 months ago
Commenter123321 a77848429e make user agent easily changeable in deepai 9 months ago
Commenter123321 e049176324 fix deepai :) 9 months ago
Commenter123321 9239c57200 fix provider thing in gui x2 9 months ago
Commenter123321 2c105cb595 fix provider thing in gui 9 months ago
Commenter123321 4d4ad976ec remove unused import in Bing.py 9 months ago
Commenter123321 d719860e2a make internet searching better 9 months ago
Commenter123321 3de672d023 Aivvm is the best provider no cap 9 months ago
Commenter123321 0e4297494d Merge remote-tracking branch 'origin/main'
# Conflicts:
#	g4f/Provider/Aivvm.py
#	g4f/models.py
9 months ago
Heiner Lohaus 53192b86b1 Some small fixes 9 months ago
Commenter123321 417ce27422
Update Aivvm.py 9 months ago
abc e05987ace3 ~ | g4f `v-0.1.5.7` [Set Provider in GUI] + Provider Proxy 9 months ago
abc abc2fa2ca1 ~
Command line arguments for GUI
9 months ago
abc 7f8526a122 ~
New system for str to Provider
9 months ago
abc f9355ad5fc ~
remove chatforai
9 months ago
abc 1883d55147 ~
Conversion from str Provider to g4f.Provider
9 months ago
Commenter123321 58c45522ea add cool testing for gpt-3.5 and and gpt-4 9 months ago
Commenter123321 119817c963 Merge remote-tracking branch 'origin/main'
# Conflicts:
#	g4f/Provider/Aivvm.py
9 months ago
Heiner Lohaus c6b33e527c Add Proxy Support and Create Provider to Readme
Add proxy support to many providers
9 months ago
Heiner Lohaus e46b5fe043 Add proxy support to all providers 9 months ago
abc 64fe0ee487 ~ | g4f `v-0.1.5.6`
gui & interference can now be run with:

python -m g4f.gui.run

and

python -m g4f.interference.run
9 months ago
Heiner Lohaus 6401084fd0 Add Messages and AsyncResult typing
Add system_message in Yqcloud
9 months ago
Heiner Lohaus 4a9d7714ad Add Cromicle to provider list 9 months ago
abc 92e1ec6f4f ~ | `v-0.1.5.5`
Aiivm working again
9 months ago
abc 570f71c21e ~ | g4f `v-0.1.5.5` 9 months ago
Heiner Lohaus 3430b04f87 Remove Aivvm from working providers 9 months ago
Heiner Lohaus dfdb759639 Improve code with ai 9 months ago
Heiner Lohaus f7bb30036e Improve code by AI 9 months ago
Heiner Lohaus 4fa6e9c0f5 Add GptGod Provider
Remove timeout from aiohttp providers
Disable Opchatgpts and ChatgptLogin provider
9 months ago
Heiner Lohaus 1238d9a638 Add GPTalk and GptForLove Provider 9 months ago
abc 395fbc70e0 ~ | g4f `v-0.1.5.4` [new gui & interference]
+ version fix
9 months ago
abc 6b2ac63cd9 ~ | g4f `v-0.1.5.3` [new gui & interference] 9 months ago
abc 44eb804cc5 ~ | new instructions for gui & interference + telegram channel 9 months ago
abc 59e573b6df ~ | g4f `v-0.1.5.1` [*new gui & interference*] 9 months ago
abc 012a1fa0c7 ~ | g4f `v-0.1.5.1` [*new gui & interference**] 9 months ago
abc d862dbf85f ~ | gpt-3.5-turbo-0613 9 months ago
abc b04ff7fb53 ~ | new interference 9 months ago
abc 7e4e374f62 ~ | new g4f GUI 9 months ago
Heiner Lohaus af9ed889c1 Fix timeout in create_async 9 months ago
abc f73bc2d593 ~ | g4f v-0.1.5.0 9 months ago
abc c8835b15d4 ~ 9 months ago
abc a4b5f5a6fd ~ | fix gpt-3.5-turbo models 9 months ago
Tekky f50e97810b
~ | Merge pull request #991 from ostix360/main
fix import in models
9 months ago
hs_junxiang dbf54769e0 Fix: TypeError: 'type' object is not subscriptable 9 months ago
ostix360 5f509e4545 import fixed 9 months ago
abc 2d2cfcd894 ~ | g4f v-0.1.4.9 [major updates and patches] 9 months ago
Tekky 6dc2502740
Merge branch 'main' into bom 9 months 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
9 months ago
Hexye 3f0a738fe7
Merge pull request #1 from HexyeDEV/patch-3
Update models.py
9 months ago
Hexye 3077671470
Update models.py 9 months ago
Hexye 3b418e8cc5
Update Cromicle.py 9 months ago
Hexye eb13f3b01d
Create Cromicle.py 9 months 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"
9 months ago
abc 8471ada090 ~ | g4f v-0.1.4.7 `pip install -U g4f` 9 months ago
Tekky 6eb3fa3e5f
~ | Merge pull request #982 from hlohaus/fetch
Fix fetch_access_token in openai
9 months ago
Heiner Lohaus 6a61cf8116 Sort providers in new dirs 9 months ago
Heiner Lohaus 136770e05b Use custom user dir 9 months ago
Heiner Lohaus 5b2efa4aaf Fix fetch_access_token in openai 9 months ago
abc 896d040c3e ~ | g4f v-0.1.4.6 `pip install -U g4f` 9 months ago
abc 791e0d4ec8 ~ | g4f v-0.1.4.5 `pip install -U g4f`
updated providers:

- g4f.Provider.Bing
- g4f.Provider.OpenaiChat
9 months ago
Tekky d9e527eb32
Merge pull request #975 from hlohaus/mmm
Bing Updates:
9 months ago
Heiner Lohaus be9b8f796c Add streaming in openai chat
Fetch access token with chromedriver
9 months ago
Heiner Lohaus 252f595b6a Bing Updates:
Add retry create conversation
Removed get_cookies fallback
Add creative tone parameter
9 months ago
abc da50e84dfc ~ | g4f v-0.1.4.5 `pip install -U g4f` 9 months ago
Tekky c915050ac7
Merge pull request #971 from Giancarlo-Ma/main
feat: allow to add custom header to deepai
9 months ago
Heiner Lohaus ff4d9ae584 Add Phind Provider
Add release_curl in url_cffi requets
Support create image response in Bing
9 months ago
Giancarlo-Ma ba7d5015dc
feat: add custom header to deepai 9 months ago
abc a4da030d67 ~ | g4f v-0.1.4.4
release_curl bug
9 months ago
abc 5fcf9434f4 ~ | quick fix 9 months ago
abc 98be81fef7 ~ | g4f v-`0.1.4.3` 9 months ago
Tekky c9e4c9ce00
~ | Merge pull request #968 from st4rted/patch-1
fix typo in payload
9 months ago
Heiner Lohaus d116f04322 Fix: There is no current event loop in thread 9 months ago
Heiner Lohaus 2dbeb54608 Remove fake_useragent module 9 months ago
Heiner Lohaus eb0e2c6a93 +Curl +Async +Stream Requests
Update Model List
9 months ago
st4rted 3485e357ac
fix typo in payload 9 months ago
Heiner Lohaus 7b9ad21de8 Change event loop policy on windows
Support more versions from curl_cffi
9 months ago
Commenter123321 f8411aa1e1 aivvm's no life creator keeps patching it, but I'm just better 😉 9 months ago
Heiner Lohaus bb481a03ab Disable Wewordle Provider
Update Ylokh Provider
Improve StreamRequest
9 months ago
Heiner Lohaus 261fac86dc Disable PerplexityAi Provider 9 months 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
9 months ago
abc 423485fda6 ~ | v-0.1.4.2 `pip install -U g4f` 9 months ago
abc 83443ee912 Merge branch 'main' of https://github.com/xtekky/gpt4free 9 months ago
abc 3ba045c9d1 ~ | pypi v-0.1.4.0 `pip install -U g4f` 9 months ago
Tekky e465899801
~ 9 months ago
Commenter123321 6ba092469a some more things 9 months ago
Commenter123321 7181f2897b Fix Aivvm and add new models in models.py 9 months ago
abc 26e1fc4a7d ~ | g4f v-0.1.4.0 (new version checking system 9 months ago
abc 32d5536450 ~ | g4f v-0.1.3.9 9 months ago
abc be293e7af7 ~ | g4f v-0.1.3.8 9 months ago
yym68686 33687740aa fixed bug: ImportError: cannot import name 'Request' from 'curl_cffi.requests.cookies' (/Users/yanyuming/opt/anaconda3/envs/chatgpt/lib/python3.11/site-packages/curl_cffi/requests/cookies.py) 9 months ago
abc c753894705 ~ | v-0.1.3.7 9 months ago
abc cc3f0bce72 ~ | add version (`g4f.version`) 9 months 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
9 months ago
Heiner Lohaus 72c3ff7a25 AItianhuSpace Provider with GPT 4 added
Reduced chunksize to better text completion
9 months ago
Heiner Lohaus 348670fe35 "create_async" support for BaseProvider,
by using ThreadPoolExecutor
Default Model for Vercel
9 months ago
Heiner Lohaus f1b6880f7e Add Myshell Provider
Remove auto proxy prefix
9 months ago
Heiner Lohaus fd5c33efb8 TypeError: issubclass() arg 1 must be a class 10 months ago
Heiner Lohaus 4edd7518de Fix: Aivvm: KeyError: ''
and TypeError: issubclass() arg 1 must be a class
10 months ago
abc bf78b4d033 ~ | improve Vercel & g4f.Completion.create 10 months 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)
```
10 months ago
abc af9fc19938 ~ 10 months ago
Tekky 1215d30bf4
Delete g4f/Provider/Vercel.py 10 months ago
Heiner Lohaus a3ecabb00e Improve Vercel Provider:
- Fix endless loop
 - Add proxy, async support
 - Add default model
 Fix HuggingChat Provider
10 months ago
abc d4acc23c0b ~ | Update Vercel Provider 10 months ago
abc 9ffed2fc33 ~ | gpt-3.5-turbo-16k-0613 10 months ago
abc 42a02c3d2d ~ | new providers
Somwhat fix Aivvm provider, which looks to have a working gpt-4

kinda unstable
10 months ago
abc d320efd2ff ~ | Fix DeepAi 10 months ago
Tekky ba287e89b5
~ | Merge pull request #924 from hlohaus/vercel
Fix async example in readme
10 months ago
abc 4d4fc98533 ~ | gpt-3.5-turbo-0613 10 months ago
Heiner Lohaus e9f96ced9c Add RetryProvider 10 months ago
Heiner Lohaus 951a1332a7 Fix create_event_loop function
Add PerplexityAi Provider
10 months ago
Heiner Lohaus f90741c10b Improve code style in async support 10 months ago
Heiner Lohaus 587f4ad2c9 Add "create_event_loop" helper 10 months ago
Heiner Lohaus 55577031d5 Add check_running_loop requirement
Add create_async function in ChatCompletion
Use SelectorEventLoop on windows
10 months ago