| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
| |
Error checking is done for Vercel's create_completion to avoid interruption caused by UnicodeDecodeError.
|
|
|
|
| |
Fix many providers
Add selenium-wire to requierments
|
| |
|
|
|
|
|
|
|
| |
* New minimum requirements
* Add ConversationStyleOptionSets to Bing
* Add image.ImageRequest
* Improve python version support
* Improve unittests
|
|
|
|
|
|
|
|
|
| |
Add AbstractProvider class
Add ProviderType type
Add get_last_provider function
Add version module and VersionUtils
Display used provider in gui
Fix error response in api
|
| |
|
| |
|
|
|
| |
Co-authored-by: Sourcery AI <>
|
| |
|
|
|
|
| |
patch / unpatch providers
|
|
|
|
| |
automatic models fetching in GUI.
|
| |
|
|
|
|
|
|
| |
Add support for "nest_asyncio",
Reuse event_loops with event_loop_policy
Support for "create_async" with synchron provider
|
|
|
|
| |
Reduced chunksize to better text completion
|
|
|
|
|
|
|
|
|
|
|
| |
added `.Completion.create` class.
```py
response = g4f.Completion.create(
model='text-davinci-003', prompt="Hello")
print(response)
```
|
| |
|
| |
|
|
|
|
|
|
|
| |
- Fix endless loop
- Add proxy, async support
- Add default model
Fix HuggingChat Provider
|
| |
|
|
|
|
|
|
| |
Somwhat fix Aivvm provider, which looks to have a working gpt-4
kinda unstable
|
| |
|
| |
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Use `from __future__ import annotations avoid `dict` and `list` cause "TypeErro: 'type' object is not subscriptable".
Refer to the following Stack Overflow discussions for more information:
1.
https://stackoverflow.com/questions/75202610/typeerror-type-object-is-not-subscriptable-python
2.
https://stackoverflow.com/questions/59101121/type-hint-for-a-dict-gives-typeerror-type-object-is-not-subscriptable
|
| |
|
|
|