Update app.py

app.py

@@ -1,65 +1,61 @@
-import gradio as gr
+from flask import Flask, render_template, request, jsonify
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
+# Initialize the Flask app
+app = Flask(__name__)
+
+# Initialize the Hugging Face Inference Client (Replace with your actual model identifier)
 client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
 
+# Parameters from the image
+MAX_TOKENS = 1520
+TEMPERATURE = 0.7
+TOP_P = 0.95
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# In-memory storage for active chats (to maintain chat history)
+chat_history = {}
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+@app.route("/")
+def home():
+    return render_template("editor.html")
 
-    messages.append({"role": "user", "content": message})
+@app.route("/generate_code", methods=["POST"])
+def generate_code():
+    # Get the user ID (or session) and the prompt
+    user_id = request.json.get("user_id")
+    prompt = request.json.get("prompt")
 
-    response = ""
+    # Get chat history for the user or initialize it
+    if user_id not in chat_history:
+        chat_history[user_id] = []
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    # Append the user's prompt to the chat history
+    chat_history[user_id].append({"role": "user", "content": prompt})
 
-        response += token
-        yield response
+    # System message
+    system_message = "You are a friendly chatbot."
 
+    # Build the messages for the model
+    messages = [{"role": "system", "content": system_message}]
+    messages.extend(chat_history[user_id])  # Add previous conversation history
+
+    # Generate the response
+    generated_code = ""
+    for msg in client.chat_completion(
+        messages=messages,
+        max_tokens=MAX_TOKENS,
+        temperature=TEMPERATURE,
+        top_p=TOP_P,
+        stream=True,
+    ):
+        token = msg.choices[0].delta.content
+        generated_code += token
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    # Save the assistant's response to the chat history
+    chat_history[user_id].append({"role": "assistant", "content": generated_code})
 
+    return jsonify({"code": generated_code})
 
 if __name__ == "__main__":
-    demo.launch()
+    app.run(debug=True, port=7860)