updating app.py to auto run scripts

app.py

@@ -1,42 +1,58 @@
-import os
 import gradio as gr
 from huggingface_hub import InferenceClient
 from datasets import load_dataset
-import time
 import faiss
 import numpy as np
+import os
+import time
 
-# ✅ Install FAISS if missing
+# ✅ Ensure FAISS is installed
 os.system("pip install faiss-cpu")
 
 def log(message):
     print(f"✅ {message}")
 
-
 # ✅ Load the datasets
+log("📥 Loading datasets...")
 datasets = {
     "sales": load_dataset("goendalf666/sales-conversations", trust_remote_code=True),
     "blended": load_dataset("blended_skill_talk", trust_remote_code=True),
     "dialog": load_dataset("daily_dialog", trust_remote_code=True),
     "multiwoz": load_dataset("multi_woz_v22", trust_remote_code=True),
 }
+log("✅ Datasets loaded.")
+
+# ✅ Step 1: Run Embedding Script (Import and Run)
+log("🚀 Running embeddings script...")
+import embeddings  # This will automatically run embeddings.py
 
-# Optional: Print dataset names and sizes
-for name, dataset in datasets.items():
-    print(f"{name}: {len(dataset['train'])} examples")
+time.sleep(5)  # Wait for embeddings to be created
 
-# Initialize the model client (use correct model for chatbot)
+# ✅ Step 2: Check FAISS index
+def check_faiss():
+    index_path = "my_embeddings"  # Adjust if needed
+
+    try:
+        index = faiss.read_index(index_path)
+        num_vectors = index.ntotal
+        dim = index.d
+
+        if num_vectors > 0:
+            return f"📊 FAISS index contains {num_vectors} vectors.\n✅ Embedding dimension: {dim}"
+        else:
+            return "⚠️ No embeddings found in FAISS index!"
+
+    except Exception as e:
+        return f"❌ ERROR: Failed to load FAISS index - {e}"
+
+log("🔍 Checking FAISS embeddings...")
+faiss_status = check_faiss()
+log(faiss_status)
+
+# ✅ Step 3: Initialize chatbot
 client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
 
-# Chatbot response function
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
 
     for val in history:
@@ -46,81 +62,27 @@ def respond(
             messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
-
     response = ""
 
     for message in client.chat_completions(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
+        messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p
     ):
         token = message["choices"][0]["delta"]["content"]
         response += token
         yield response
 
-
-# Gradio interface for chatbot
+# ✅ Step 4: Start Chatbot Interface
 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)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-def start_embedding():
-    # Include your embedding logic here (from embeddings.py)
-    log("Embedding started...")
-    time.sleep(2)  # Simulating embedding process
-    log("Embedding process finished.")
-
-# Create Gradio interface with a button to start the embedding
-demo = gr.Interface(
-    fn=start_embedding,
-    inputs=None,
-    outputs="text",
-    live=True,
-    title="Embedding Trigger"
-)
-
-
-# ✅ Function to check FAISS index
-def check_faiss():
-    index_path = "my_embeddings"  # Adjust if needed
-
-    try:
-        index = faiss.read_index(index_path)
-        num_vectors = index.ntotal
-        dim = index.d
-
-        if num_vectors > 0:
-            sample_vectors = index.reconstruct_n(0, min(5, num_vectors))  # Get first 5 embeddings
-            return f"📊 FAISS index contains {num_vectors} vectors.\n✅ Embedding dimension: {dim}\n🧐 Sample: {sample_vectors[:2]} ..."
-        else:
-            return "⚠️ No embeddings found in FAISS index!"
-
-    except Exception as e:
-        return f"❌ ERROR: Failed to load FAISS index - {e}"
-
-# ✅ Add a Gradio button to trigger FAISS check
-with gr.Blocks() as demo:
-    gr.Markdown("### 🔍 FAISS Embedding Check")
-    
-    check_button = gr.Button("🔎 Check FAISS Embeddings")
-    output_text = gr.Textbox(label="FAISS Status", interactive=False)
-
-    check_button.click(fn=check_faiss, outputs=output_text)
-
-# Launch Gradio app
+log("✅ All systems go! Launching chatbot...")
 if __name__ == "__main__":
     demo.launch()
+