| Commit message (Collapse) | Author | Files | Lines |
|
* Improve download of generated images, serve images in the api
* Add support for conversation handling in the api
* Add orginal prompt to image response
* Add download images option in gui, fix loading model list in Airforce
* Support speech synthesize in Openai generator
|
|
* Improve download of generated images, serve images in the api
Add support for conversation handling in the api
* Add orginal prompt to image response
* Add download images option in gui, fix loading model list in Airforce
* Add download images option in gui, fix loading model list in Airforce
|
|
* Fix image generation in OpenaiChat
* Add PollinationsAI provider with image and text generation
|
|
* Fix api streaming, fix AsyncClient, Improve Client class, Some providers fixes, Update models list, Fix some tests, Update model list in Airforce provid
er, Add OpenAi image generation url to api, Fix reload and debug in api arguments, Fix websearch in gui
* Fix Cloadflare and Pi and AmigoChat provider
* Fix conversation support in DDG provider, Add cloudflare bypass with nodriver
* Fix unittests without curl_cffi
|
|
add fix_url ( replace ' ' by '+' (to be markdown compliant))
|
|
|
|
|
|
|
|
Use AsyncClient in API, add web_search parameter in API
Improve error messages in Openai
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Add more models and image generation in You provider
Use You as second default image provider
|
|
|
|
Set min version for duckduckgo
Make duckduckgo search async
Remove get_lastet_version
|
|
Fix: async generator ignored GeneratorExit
Fix: ResourceWarning: unclosed event loop
|
|
Add set_cookies helper, Show last used model
|
|
* New minimum requirements
* Add ConversationStyleOptionSets to Bing
* Add image.ImageRequest
* Improve python version support
* Improve unittests
|
|
|
|
|
|
|
|
Fix typo in latest_version
Fix Phind Provider
Add unittest worklow and main tests
|
|
Add doctypes to many functions
Add file upload for text files
Add alternative url to FreeChatgpt
Add webp to allowed image types
|
|
Add image upload to OpenaiChat
Add image response to OpenaiChat
Improve ChatGPT Plus Support
Remove unused requirements
|
|
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
|
|
|
|
fix DeepInfra
|
|
|
|
|
|
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.
|
|
|
|
|
|
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
|
|
- Fix endless loop
- Add proxy, async support
- Add default model
Fix HuggingChat Provider
|
|
Add PerplexityAi Provider
|
|
|
|
|
|
Add create_async function in ChatCompletion
Use SelectorEventLoop on windows
|
|
|
|
|
|
|
|
|
|
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
|
|
Add format_prompt helper
Fix create_completion in AsyncGeneratorProvider
Move get_cookies from constructor to function
Add ow HuggingChat implement
Remove need auth form Liabots
Add staic cache for access_token in OpenaiChat
Add OpenAssistant provider
Support stream and async in You
Support async and add userId in Yqcloud
Add log_time module
|
|
|
|
Add tests for providers with auth
Improve async support / 2x faster
Shared get_cookies by domain function
|
|
g4f.Provider.FastGpt & g4f.Provider.Equing
gpt-3.5-turbo-0613
|
|
|