A better approach is to use the `.join()` method of strings, which reduces string concatenation operations and improves performance.
Additionally, using formatted strings (f-strings) makes the code cleaner and more readable.
I've created a `document GPT`(chatPDF) which is based on "`langchain`" and "`gpt4free`".
The project initially utilized the Langchain to invoke the OpenAI model for implementing document GPT.
Now, it offers the option to use the gpt4free model, coupled with Hugging Face embedding.
**This integration enables users to use the document GPT app completely free**, without the need to input any API keys!
The [link](https://github.com/Lin-jun-xiang/docGPT-streamlit) has been added.
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
I've created a project that uses `gpt4free` for **auto translation** task.
This action will automatically update and push README.md for different language. For example:
1. push `README.zh-TW.md` (zh-tw version)
2. use `gpt4free` to translate
3. generate the `README.md` (en version)
4. auto commit and push translating version.
The [link](https://github.com/Lin-jun-xiang/action-translate-readme) has been added.