Allow HTTP Request Node to have Generic connection

[Riwut]

The idea is:

My use case:

1. I have lite-llm as OpenAI compatible proxies to multi backend AI model.
2. 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
3. I can use HTTP request and craft own API call to lite-llm.
4. 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.

Any resources to support this?

Are you willing to work on this?

[saman.bazrafshan]

I have more or less the same issue on several projects already and would appreciate a solution as well.

Since there are almost no upvotes on this one and also for clarification purpose I like to reference the following two issues - both addressing the same need.

How to connect an http as a LLM

Hi, I read in the forum and didn’t find an answer to this topic. I work on an offline network and I want to connect a model through an HTTP gateway that I created, and thus create communication with a language model. Is it possible to do this? Currently I see that I only have existing models and an API is required for them (and again, I’m on an offline network). Thank you very much. [image] This is image of someone that ask the same question Information on your n8n setup **n8n version:la…

How to connect an http request as a chat model?

I’m looking a way to connect an http request into the basic llm chain, as chat model, but it does not allow it, the connection between the basic llm chain and the http request is not being linked. I need to use an http request because I have a local llm that receives an client_id and client_secret and an a local url. The http request works perfectly fine but I cannot linked into the basic llm chain to set a basic chat app and later be able to connect additional information (rag like) to the exi…

If there is anything I can contribute I would be more than happy to do so.