The idea is:
My use case:
- I have lite-llm as OpenAI compatible proxies to multi backend AI model.
- Currently I can’t use OpenAI Chat node with custom Base URL custom property, because it seems the URL is always hardcoded to openai.com
- I can use HTTP request and craft own API call to lite-llm.
- However HTTP Request node cannot be connected to Basic LLM Chain node.
Hence I suggest that HTTP Request support different activation, we can connect to Basic LLM Chain. For example, Basic LLM Chain has activation type Model , then the HTTP request node can have activation type Generic.
I think it would be beneficial to add this because:
In the future, when the prebuilt node is not available; we can always use HTTP Request node as fallback. And since HTTP Request node has generic activation type, it will connect to any type node, example can be used to replace OpenAI Chat Model or any other nodes that require different type of activation.