Update model load to download it from huggingface repo if doesnt exists. Also update readme

.env.example

@@ -1,7 +1,8 @@
+FLASK_DEBUG = 'true'
+HF_MODEL_REPO_NAME = "org/repo_name"
 RS_FIREBASE_CREDENTIALS_PATH = 'firebase-credentials.json'
 RS_WORDLE_USER = '[email protected]'
 RS_WORDLE_URL = 'http://localhost:3000'
 RS_WORDLE_MODEL_NAME = 'the_best_ai_model_saved.pth'
 RS_WORDLE_PASSWORD = 'myemailpassword'
-FLASK_DEBUG = 'true'
 SECRET_KEY = 'asecretkey4flask'

README.md

@@ -1,3 +1,14 @@
+---
+title: Wordle Solver
+emoji: 🔠
+colorFrom: green
+colorTo: yellow
+sdk: streamlit
+sdk_version: 1.25.0
+pinned: false
+app_file: streamlit.py
+---
+
 # Wordle Solver with RL
 
 A model that solves Wordle using reinforcement learning
@@ -12,7 +23,7 @@ And then, on the project root, execute:
 
 `pip install -r requirements.txt`
 
-## Running and execution modes
+## CLI Running and execution modes
 To run the program, on the project root execute:
 
 `python main.py [ENV][MODE] [PARAMETERS]`
@@ -68,20 +79,32 @@ For word suggestion, run:
     * a 2 if the letter was in the word and in the correct position
 * --model_name [MODEL_NAME] --> Name of the pretrained model file which will play the game
 
+## Play Wordle with the help of an AI using Streamlit
+To run a Streamlit app to play wordle with the help of an AI assistant you need to:
+
+* Have a pretrained model that knows how to play wordle:
+  1. You need to create a `.env` file in the project root with `RS_WORDLE_MODEL_NAME` property.
+  2. Download the pretrained model and put it under `checkpoints` dir, to do that you have two options:
+     * **Option 1**: Download it manually from our [Huggingface repo](https://huggingface.co/rootstrap-org/wordle-solver).
+     * **Option 2**: Let it download automatically by setting an `HF_MODEL_REPO_NAME` property with value `rootstrap-org/wordle-solver` in the `.env` file. You have to be authenticated in huggingface with huggingface_cli to do that.
+  3. Set the `RS_WORDLE_MODEL_NAME` property in `.env` with the model filename.
+* Run the app by executing `streamlit run streamlit.py`
+
 ## Make the model play RS-Wordle alone!
 It is possible to make the model play the Rootstrap version of Wordle. To do that, you need to:
 
 * Have a Rootstrap mail account
 * Get access to the Firebase database of the RS-Wordle instance and a private key obtained from the Service accounts Project Setting. This is for authentication and has to be stored as a JSON file.
-* Use a pre-trained model that will play the game.
+* Use a pre-trained model that will play the game, and put it under `checkpoints` dir, to do that you have two options:
+     * **Option 1**: Download it manually from our [Huggingface repo](https://huggingface.co/rootstrap-org/wordle-solver).
+     * **Option 2**: Let it download automatically by setting an `HF_MODEL_REPO_NAME` property with value `rootstrap-org/wordle-solver` in the `.env` file. You have to be authenticated in Huggingface with huggingface_cli to do that.
 
-Then, you need to create a .env file in the project root with the following properties:
+Then, you need to add to the .env file the following properties:
 
 ```
 RS_FIREBASE_CREDENTIALS_PATH=path/to/private_key.json
 RS_WORDLE_USER=rootstrap_mail_user
 RS_WORDLE_URL=rs_wordle_instance_url
-RS_WORDLE_MODEL_NAME=pretrained_model_path
 RS_WORDLE_PASSWORD=rootstrap_mail_password
 ```
 

a3c/play.py

@@ -2,6 +2,7 @@ import os
 
 import torch
 from dotenv import load_dotenv
+from huggingface_hub import hf_hub_download
 
 from wordle_env.state import update_from_mask
 
@@ -10,12 +11,13 @@ from .utils import v_wrap
 
 load_dotenv()
 
-PLAY_MODEL_NAME = os.getenv("RS_WORDLE_MODEL_NAME")
+MODEL_NAME = os.getenv("RS_WORDLE_MODEL_NAME")
+HF_MODEL_REPO_NAME = os.getenv("HF_MODEL_REPO_NAME")
+MODEL_CHECKPOINT_DIR = "checkpoints"
 
 
 def get_play_model_path():
-    model_checkpoint_dir = "checkpoints"
-    return os.path.join(model_checkpoint_dir, PLAY_MODEL_NAME)
+    return os.path.join(MODEL_CHECKPOINT_DIR, MODEL_NAME)
 
 
 def get_net(env, pretrained_model_path):
@@ -24,6 +26,10 @@ def get_net(env, pretrained_model_path):
     words_list = env.words
     word_width = len(env.words[0])
     net = GreedyNet(n_s, n_a, words_list, word_width)
+    if not os.path.exists(pretrained_model_path):
+        pretrained_model_path = hf_hub_download(
+            HF_MODEL_REPO_NAME, MODEL_NAME, local_dir=MODEL_CHECKPOINT_DIR
+        )
     net.load_state_dict(torch.load(pretrained_model_path))
     return net
 

requirements.txt

@@ -5,6 +5,7 @@ Flask-Cors==3.0.10
 Flask-Static-Digest==0.2.1
 gunicorn==20.1.0
 gym==0.21.0
+huggingface_hub
 matplotlib==3.6.3
 python-dotenv==1.0.0
 selenium==4.8.2