Setup for reccomender

.gitignore

@@ -1 +1,4 @@
-frontend/node_modules
+frontend/node_modules
+Recommender/.idea
+Recommender/venv
+backend/venv

backend/loadmodel.py

@@ -0,0 +1,10 @@
+import tensorflow as tf
+import numpy as np
+
+
+model = tf.keras.models.load_model("model.keras")
+#../Recommender/model1acc=0.6855000257492065/saved_model
+# model.summary()
+content = [1, 1, 1, 1, 0, 0, 0, 3, 2, 0, 2, 3, 3, 2, 1, 1, 2, 1, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0]
+pred = model.predict(np.array([content]))
+print(pred)

backend/requirements.txt

@@ -0,0 +1,56 @@
+absl-py==2.1.0
+annotated-types==0.6.0
+anyio==4.3.0
+astunparse==1.6.3
+blinker==1.7.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+distro==1.9.0
+exceptiongroup==1.2.1
+Flask==3.0.3
+Flask-Cors==4.0.0
+flatbuffers==24.3.25
+gast==0.5.4
+google-pasta==0.2.0
+grpcio==1.62.2
+h11==0.14.0
+h5py==3.11.0
+httpcore==1.0.5
+httpx==0.27.0
+idna==3.7
+itsdangerous==2.2.0
+Jinja2==3.1.3
+keras==3.2.1
+libclang==18.1.1
+Markdown==3.6
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+ml-dtypes==0.3.2
+namex==0.0.8
+numpy==1.26.4
+openai==1.23.2
+opt-einsum==3.3.0
+optree==0.11.0
+packaging==24.0
+protobuf==4.25.3
+pydantic==2.7.0
+pydantic_core==2.18.1
+Pygments==2.17.2
+python-dotenv==1.0.1
+requests==2.31.0
+rich==13.7.1
+six==1.16.0
+sniffio==1.3.1
+tensorboard==2.16.2
+tensorboard-data-server==0.7.2
+tensorflow==2.16.1
+tensorflow-io-gcs-filesystem==0.36.0
+termcolor==2.4.0
+timeout-decorator==0.5.0
+tqdm==4.66.2
+typing_extensions==4.11.0
+urllib3==2.2.1
+Werkzeug==3.0.2
+wrapt==1.16.0

backend/route.py

@@ -0,0 +1,83 @@
+from flask import Flask, request
+from flask_cors import CORS
+import multiprocessing
+import timeout_decorator
+import tensorflow as tf
+import random
+import numpy as np
+from openai import OpenAI
+from dotenv import load_dotenv
+import os
+
+# Load the environment variables from the .env file
+load_dotenv()
+
+app = Flask(__name__)
+
+CORS(app)
+
+
+def execute_code(code):
+    try:
+        exec(code, {"__name__": "__main__"})
+    except Exception as e:
+        return str(e)
+
+
+def check_python_code(code):
+    try:
+        # Check if the code compiles
+        compile(code, '<string>', 'exec')
+    except SyntaxError as e:
+        return "SyntaxError"
+
+    # Set a timeout and execute the code
+    try:
+        process = multiprocessing.Process(target=execute_code, args=(code,))
+        process.start()
+        process.join(timeout=5)  # Adjust timeout as necessary
+        if process.is_alive():
+            process.terminate()
+            process.join()
+            return "Infinite"
+    except timeout_decorator.timeout_decorator.TimeoutError:
+        return "Infinite"
+    except Exception as e:
+        return f"Error"
+
+    return "Success"
+
+
+@app.route("/run", methods=["POST"])
+def run():
+    content = f"""{request.get_json()["code"]}"""
+    return {"response": check_python_code(content)}
+
+@app.route("/llm_api", methods=["POST"])
+def llm_api():
+    content = f"""Ok, so here is the question: {request.get_json()["question"]} and here is the answer: {request.get_json()["answer"]}. Given this context, please check if this answer is correct based on the question. If it is not, please provide the correct answer. You have to give the output in the format <Correct/Incorrect> <Correct Answer/Positive Feedback>. For example in: question: print hello world statement, answer: print("hello world"), the output should be: Correct Good Job!. If the answer is incorrect, the output should be: Incorrect The correct answer is print("hello world")."""
+    # print("API Ky", os.getenv('OPENAI_API'))
+    client = OpenAI(api_key=os.getenv('OPENAI_API'))
+    response = client.chat.completions.create(model="ft:gpt-3.5-turbo-0125:personal::9GCHGPWm", messages=[{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": content}])
+    msg = response.choices[0].message.content
+    return {"response": msg.split(" ")[0], "feedback": " ".join(msg.split(" ")[1:])}
+
+@app.route("/llm_chatbot", methods=["POST"])
+def llm_chatbot_msg():
+    client = OpenAI(api_key=os.getenv('OPENAI_API'))
+    response = client.chat.completions.create(model="ft:gpt-3.5-turbo-0125:personal::9GCHGPWm", messages=[{"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": request.get_json()["message"]}])
+    msg = response.choices[0].message.content
+    return {"feedback": msg}
+
+
+@app.route("/recommend_question", methods=['POST'])
+def recommend():
+    content = request.get_json()["data"]
+    loaded = tf.keras.models.load_model("model.keras")
+    prediction = loaded.predict(np.array([content]))[0]
+    questions = [i for i in range(1, 22)]
+    choice = random.choices(questions, prediction, k=1)
+    return choice
+
+if __name__ == "__main__":
+    app.run(port=3002, debug=True)