Can support llm by api?

[skytodmoon]

Greate project, we want use this in our production dev. And use dify chat api as below:
http://192.168.32.241:8088/
Request POST /chat-messages curl -X POST 'http://192.168.32.241:8088/v1/chat-messages' \ --header 'Authorization: Bearer {api_key}' \ --header 'Content-Type: application/json' \ --data-raw '{ "inputs": {}, "query": "What are the specs of the iPhone 13 Pro Max?", "response_mode": "streaming", "conversation_id": "", "user": "abc-123", "files": [ { "type": "image", "transfer_method": "remote_url", "url": "https://cloud.dify.ai/logo/logo-site.png" } ] }'
Cant this be supported?

[SinlinLi]

Strongly support. If the standard OpenAI API is supported, it will facilitate our use of large-parameter language models. This would be extremely convenient.

[andimarafioti]

I like this idea as well 💡It would probably add delay though, but it would be a good way to help people get this into prod.

I will add it to the ideas. If you want to work on it, we welcome contributions :)

[jpysh]

current blocker for me. thank you.

[rchan26]

I'm happy to have a go at including OpenAI API support 😊

[rchan26]

ah, just seen there's already a PR for this in #81

[MattiPaivike]

Bump, this would be perfect addition!

[eustlb]

Hey there, the OpenAI API PR (#81) is now merged!
Give ti a go simply adding the following parameters: --llm open_api --open_api_api_key YOUR_API_KEY --open_api_init_chat_prompt "You are an helpfull AI assistant" --open_api_stream True --open_api_model_name gpt-3.5-turbo