import gradio as gr
from huggingface_hub import InferenceClient
import faiss
import numpy as np
import os
import time
import threading  # ✅ Run embeddings in parallel

# ✅ Ensure FAISS is installed
os.system("pip install faiss-cpu")

def log(message):
    print(f"✅ {message}")

# ✅ Step 1: Run Embeddings in a Separate Thread
def run_embeddings():
    log("🚀 Running embeddings script in background...")
    import embeddings  # ✅ This will automatically run embeddings.py
    log("✅ Embeddings process finished.")

embedding_thread = threading.Thread(target=run_embeddings)
embedding_thread.start()  # ✅ Start embedding in background

# ✅ Step 2: Check FAISS index
def check_faiss():
    index_path = "my_embeddings.faiss"  # Ensure file has .faiss extension

    if not os.path.exists(index_path):
        return "⚠️ No FAISS index found! Embeddings might still be processing."

    try:
        index = faiss.read_index(index_path)
        num_vectors = index.ntotal
        dim = index.d
        return f"📊 FAISS index contains {num_vectors} vectors.\n✅ Embedding dimension: {dim}"
    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")

def respond(message, history, system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            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
    ):
        token = message["choices"][0]["delta"]["content"]
        response += token
        yield response

# ✅ 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)"),
    ],
)

log("✅ All systems go! Launching chatbot...")
if __name__ == "__main__":
    demo.launch()