Update app.py

app.py

@@ -1,70 +1,81 @@
-import os
 import gradio as gr
-from sentence_transformers import SentenceTransformer
-from memory_store import MemoryStore
+import os, json, numpy as np
+from agent_core import AgentCore
 from graph_reasoner import GraphReasoner
+from context_graph import ContextGraph
 from graph_view import visualize_reasoned_graph
+from memory_store import MemoryStore
 
-# --- Initialize Environment ---
+# === Setup ===
 os.environ["TRANSFORMERS_CACHE"] = "/home/user/.cache"
-model = SentenceTransformer("all-MiniLM-L6-v2")
-memory = MemoryStore()
-reasoner = GraphReasoner()
+MEMORY_PATH = "/home/user/app/memory.json"
 
-# --- Core Logic ---
-def process_input(user_input, history):
-    if not user_input.strip():
-        return history + [("User input empty.", "Please type something meaningful.")]
-
-    # Encode input
-    vector = model.encode(user_input)
+# === Initialize Core Systems ===
+agent = AgentCore()
+reasoner = GraphReasoner()
+graph = ContextGraph()
+memory = MemoryStore(path=MEMORY_PATH)
 
-    # Store memory
-    save_status = memory.add_memory(user_input, vector)
+# === Core Chat Function ===
+def process_input(user_input, history=[]):
+    """Main conversational and memory loop."""
+    # Step 1: Embed input
+    vector = agent.embed_text(user_input)
+    
+    # Step 2: Save to memory
+    memory.add_memory(user_input, vector)
 
-    # Retrieve related memories
-    related = memory.retrieve_relevant(vector)
-    recall_text = "\n".join([f"• {r[0]} (score: {round(r[1], 4)})" for r in related])
+    # Step 3: Reasoning
+    reasoning = reasoner.reason(user_input)
+    response = f"[Aventra Response]: {reasoning}"
 
-    # Build response
-    response = f"{save_status}\n\nHere’s what I recall that’s most relevant:\n{recall_text if related else 'No related context yet.'}"
+    # Step 4: Update history
     history.append((user_input, response))
-    return history
+    return history, history
 
+# === Visualize Memory Function ===
 def visualize_memory():
-    # Get all stored memories
+    """Render memory graph visualization inline."""
     memories = memory.memories
-
-    # Build relationships between memories (using simple semantic matching)
     relationships = []
+
     for i, (text1, vec1) in enumerate(memories):
         for j, (text2, vec2) in enumerate(memories):
             if i != j:
-                # Cosine similarity threshold
                 similarity = np.dot(vec1, vec2) / (np.linalg.norm(vec1) * np.linalg.norm(vec2))
-                if similarity > 0.35:  # threshold for linking related memories
+                if similarity > 0.35:
                     relationships.append((text1, text2, float(similarity)))
 
     # Generate visualization
     output_html = visualize_reasoned_graph(memories, relationships)
-
-    # Print confirmation and show output path
     print(f"✅ Visualization created at: {output_html}")
+
+    # Return graph inline
     if os.path.exists(output_html):
-        return f"✅ Memory graph generated successfully!\n\nYou can open it here: {output_html}"
+        with open(output_html, "r") as f:
+            html_content = f.read()
+        return gr.HTML.update(value=html_content)
     else:
-        return "⚠️ Visualization failed — file not found."
-# --- UI Layout ---
-with gr.Blocks(title="Aventra OS — Memory Engine") as demo:
-    gr.Markdown("## 🧠 Aventra Memory Interface")
-    chatbot = gr.Chatbot(label="Aventra Conversation", height=400)
-    user_input = gr.Textbox(label="Message", placeholder="Type something like 'My name is Tirrek'...")
+        return gr.HTML.update(value="⚠️ Visualization failed — file not found.")
+
+# === Clear Memory ===
+def clear_memory():
+    memory.memories = []
+    memory.save()
+    return "🧹 Memory cleared successfully."
+
+# === Build Gradio Interface ===
+with gr.Blocks(title="Aventra OS") as demo:
+    gr.Markdown("## 🧠 **Aventra OS — Context Graph Memory Engine**")
+    chatbot = gr.Chatbot(label="Aventra Chat")
+    msg = gr.Textbox(label="Type a message")
     send_btn = gr.Button("Send")
-    graph_btn = gr.Button("Visualize Memory")
-    clear_btn = gr.Button("Clear Chat")
+    visualize_btn = gr.Button("Visualize Memory 🕸️")
+    clear_btn = gr.Button("Clear Memory 🧹")
+    graph_html = gr.HTML(label="Memory Graph")
 
-    send_btn.click(process_input, inputs=[user_input, chatbot], outputs=[chatbot])
-    graph_btn.click(visualize_memory, inputs=None, outputs=None)
-    clear_btn.click(lambda: None, None, chatbot, queue=False)
+    send_btn.click(process_input, inputs=[msg, chatbot], outputs=[chatbot, chatbot])
+    visualize_btn.click(visualize_memory, outputs=[graph_html])
+    clear_btn.click(clear_memory, outputs=[])
 
 demo.launch(server_name="0.0.0.0", server_port=7860)