Collect features for public interface of plugin

[iboB]

We need concrete new features for the public interface.

Try recreating existing AI apps using the llama.cpp interface. Collect features: new apis, changes to existing apis, etc.

List suggestions as responses in this issue

[iboB]

From @Tzvetomir-Kaydjiev

Initial AlpacaCore HTTP API

The most commonly used endpoints for LLM servers contain /api/generate and /api/chat. The first is primarily used for simple one time generations like code completaion with models that supports Fill-in-the-Middle. Second is used for more complicated interaction like chatting and interacting with a model. Let's start with reduced implementation of Ollama api that is easier to implement and easier to use.
For ease-of-use let's have the following versions of these:
The generation to be available on /simple-text/generate via HTTP POST

Example request body:

{
  "prompt": "def gcd(a, b",
  "suffix": "  return result"
}

Example responce body:

{
  "response": "):\n and so on ..."
}

Request body format:

{
  "$schema": "http://json-schema.org/draft-04/schema#",
  "description": "",
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string"
    },
    "suffix": {
      "type": "string"
    }
  },
  "required": [
    "prompt"
  ]
}

Responce body format:

{
  "$schema": "http://json-schema.org/draft-04/schema#",
  "description": "",
  "type": "object",
  "properties": {
    "response": {
      "type": "string"
    }
  },
  "required": [
    "response"
  ]
}

The chat to be available on /simple-text/chat via HTTP POST
Example request body:

{
  "messages": [
    {
      "role": "user",
      "content": "why is the sky blue?"
    },
    {
      "role": "assistant",
      "content": "due to rayleigh scattering."
    },
    {
      "role": "user",
      "content": "how is that different than mie scattering?"
    }
  ]
}

Example responce body:

{
  "role": "assistant",
  "content": "Whatever"
}

Request body format:

{
  "$schema": "http://json-schema.org/draft-04/schema#",
  "description": "",
  "type": "object",
  "properties": {
    "messages": {
      "type": "array",
      "items": {
        "required": [
          "role",
          "content"
        ],
        "properties": {
          "role": {
            "type": "string",
            "enum": ["user", "assistant", "other"]
          },
          "content": {
            "type": "string"
          }
        }
      }
    }
  },
  "required": [
    "messages"
  ]
}

Responce body format:

{
  "$schema": "http://json-schema.org/draft-04/schema#",
  "description": "",
  "type": "object",
  "properties": {
    "role": {
      "type": "string",
      "enum": ["user", "assistant", "other"]
    },
    "content": {
      "type": "string"
    }
  },
  "required": [
    "role",
    "content"
  ]
}