add python api

rlcube/cube2.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 1,
    "id": "dff864f2",
    "metadata": {},
    "outputs": [],
@@ -240,7 +240,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": 2,
    "id": "624c83c1",
    "metadata": {},
    "outputs": [],
@@ -269,6 +269,49 @@
     "        return obs, reward, terminated, truncated, _"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a81c85a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[0. 0. 1. 0. 0. 0.]\n",
+      " [1. 0. 0. 0. 0. 0.]\n",
+      " [0. 0. 0. 0. 0. 1.]\n",
+      " [0. 0. 0. 0. 0. 1.]\n",
+      " [0. 0. 0. 1. 0. 0.]\n",
+      " [0. 1. 0. 0. 0. 0.]\n",
+      " [0. 0. 0. 0. 1. 0.]\n",
+      " [0. 0. 0. 0. 1. 0.]\n",
+      " [0. 0. 1. 0. 0. 0.]\n",
+      " [0. 1. 0. 0. 0. 0.]\n",
+      " [0. 0. 1. 0. 0. 0.]\n",
+      " [0. 1. 0. 0. 0. 0.]\n",
+      " [1. 0. 0. 0. 0. 0.]\n",
+      " [1. 0. 0. 0. 0. 0.]\n",
+      " [0. 0. 0. 1. 0. 0.]\n",
+      " [0. 0. 0. 1. 0. 0.]\n",
+      " [0. 0. 0. 0. 1. 0.]\n",
+      " [0. 0. 0. 0. 1. 0.]\n",
+      " [1. 0. 0. 0. 0. 0.]\n",
+      " [0. 0. 1. 0. 0. 0.]\n",
+      " [0. 0. 0. 0. 0. 1.]\n",
+      " [0. 0. 0. 0. 0. 1.]\n",
+      " [0. 1. 0. 0. 0. 0.]\n",
+      " [0. 0. 0. 1. 0. 0.]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "env = RewardWrapper(Cube2())\n",
+    "obs, _ = env.reset()\n",
+    "print(env.state())"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -516,7 +559,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "dev",
+   "display_name": ".venv",
    "language": "python",
    "name": "python3"
   },
@@ -530,7 +573,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.13.5"
+   "version": "3.12.11"
   }
  },
  "nbformat": 4,

rlcube/main.py

@@ -0,0 +1,23 @@
+from typing import List
+from fastapi import FastAPI
+from pydantic import BaseModel
+from fastapi import HTTPException
+
+app = FastAPI()
+
+
+class StateArgs(BaseModel):
+    state: List[List[int]]
+
+
+@app.post("/solve")
+def solve(body: StateArgs):
+    state = body.state
+    if not (
+        isinstance(state, list)
+        and len(state) == 6
+        and all(isinstance(row, list) and len(row) == 4 for row in state)
+    ):
+        raise HTTPException(status_code=400, detail="state must be a 6x4 matrix")
+
+    return {"steps": [1, 2, 1, 1]}

rlcube/pyproject.toml

@@ -5,7 +5,8 @@ description = "Reinforcement Learning for Rubik's Cube"
 readme = "README.md"
 requires-python = ">=3.12"
 dependencies = [
+    "fastapi[standard]>=0.116.2",
     "gymnasium>=1.2.0",
+    "ipykernel>=6.30.1",
     "numpy>=2.3.2",
-    "stable-baselines3>=2.7.0",
 ]