Update app.py

app.py

@@ -1,39 +1,117 @@
+import os
+import sys
 import streamlit as st
-import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Initialize the model via Hugging Face Inference API
+# -------------------------------------------------
+# 1. Model Selection (DeepSeek-R1-Distill-Qwen-7B)
+# -------------------------------------------------
 MODEL_NAME = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
 client = InferenceClient(MODEL_NAME)
 
-# Streamlit UI for displaying project information
-st.title("Project Guidance AI Chatbot")
-st.subheader("This chatbot is powered by DeepSeek-R1-Distill-Qwen-7B")
-
-# Display the roadmap and rules from files
+# -------------------------------------------------
+# 2. Load Roadmap and Rules
+# -------------------------------------------------
 def load_file(filename):
+    """Reads a text file and returns its content."""
     try:
         with open(filename, "r", encoding="utf-8") as file:
             return file.read()
     except FileNotFoundError:
         return f"⚠️ Error: {filename} not found!"
 
+# Load project guidance files
 roadmap_content = load_file("roadmap.txt")
 rules_content = load_file("rules.txt")
 
-st.write("### Project Roadmap")
-st.text(roadmap_content)
+# -------------------------------------------------
+# 3. Chatbot Response Function (With Project Guidance)
+# -------------------------------------------------
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    temperature,
+    top_p,
+):
+    """
+    Generates an AI response while considering project roadmap and rules.
+    """
+    # System message includes roadmap and rules for AI context
+    full_system_message = f"{system_message}\n\nProject Roadmap:\n{roadmap_content}\n\nProject Rules:\n{rules_content}"
+
+    messages = [{"role": "system", "content": full_system_message}]
+
+    for val in history:
+        if val[0]:  # User message
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:  # AI response
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    try:
+        for message in client.chat_completion(
+            messages,
+            max_tokens=None,  # 🚀 No token limit
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = message.choices[0].delta.content
+
+            if token:
+                response += token
+                yield response  # Stream response live
+    except Exception as e:
+        yield f"⚠️ Error: {str(e)}"  # Show error messages
+
+# -------------------------------------------------
+# 4. Set up the Streamlit UI
+# -------------------------------------------------
+
+st.title("Project Guidance AI Chatbot")
+st.write("Chat with the AI to get project guidance based on the roadmap and rules.")
+
+# Display the roadmap and rules text
+st.subheader("Project Roadmap:")
+st.write(roadmap_content)
+st.subheader("Project Rules:")
+st.write(rules_content)
+
+# -----------------------------------
+# Create a chat history state
+# -----------------------------------
+if "history" not in st.session_state:
+    st.session_state.history = []
+
+# -----------------------------------
+# Input and Chat Display
+# -----------------------------------
+user_input = st.text_input("You:", "")
+
+if user_input:
+    st.session_state.history.append(("You", user_input))
+
+    # Set system message (helps guide the conversation)
+    system_message = "You are an AI assistant helping with project guidance based on a roadmap and rules."
 
-st.write("### Project Rules")
-st.text(rules_content)
+    # Generate response
+    ai_response = ""
+    for resp in respond(user_input, st.session_state.history, system_message, temperature=0.7, top_p=0.95):
+        ai_response = resp
 
-# Gradio component for model interaction (as part of Streamlit)
-def generate_response(user_input):
-    system_message = f"Project Roadmap:\n{roadmap_content}\n\nProject Rules:\n{rules_content}"
-    messages = [{"role": "system", "content": system_message},
-                {"role": "user", "content": user_input}]
-    
-    response = client.chat_completion(messages)
-    return response.choices[0].delta.content
+    # Update chat history with AI response
+    st.session_state.history.append(("AI", ai_response))
 
-gr.Interface(fn=generate_response, inputs="text", outputs="text").launch(share=True)
+# -----------------------------------
+# Display the chat history
+# -----------------------------------
+if st.session_state.history:
+    for chat in st.session_state.history:
+        if chat[0] == "You":
+            st.write(f"**You**: {chat[1]}")
+        else:
+            st.write(f"**AI**: {chat[1]}")