Deploy an ML model and make it accessible as an API

Beginners
1

Hello,

Can anyone recommend a cost-effective platform to deploy our RAG model and make it available as an API for ongoing use?

1 Like
2

Would it be something like this?

3

Yes, I’m implementing this, but instead of deploying it as a web app or chatbot, I want to use it purely as an API.

4

If so, the cheapest way is to deploy it as a web app and use it from the Gradio client.
The Endpoint API is probably faster and smarter, but there is a fee.

5

can we make an API using LangServe and use that API in c# code …???

6

Gradio can be used from curl, for example, so of course you can get by with C#…
About Endpoint, I’ve never used Endpoint, but maybe you can?

7

Yes, Thanks

But do you have any idea about Lang Serve using which we can create an Fast API and also use it as an REST API, actually i am not sure about this want some guidance on this

8

I don’t know anything about Lang Serve, but from my search, it seems to be intended for use with Cloud Run and the like. Or maybe Amazon AWS?
I’m not familiar with cloud services…
As for FastAPI, the backend of Gradio should also be FastAPI, so it should be basically the same for HF.

1 Like
9

I hope this will give some extra information:

1 Like
10

Thanks, this information helps me a lot.

1 Like
11

This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.