Update app.py

app.py

@@ -1,58 +1,43 @@
-import faiss
-import numpy as np
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
-
-# Set paths
-FAISS_PATH = "asa_faiss.index"
-DATASET_PATH = "responses.txt"  # Ensure this file contains indexed responses
-
-# Load FAISS index
-print(f"Loading FAISS index from {FAISS_PATH}...")
-faiss_index = faiss.read_index(FAISS_PATH)
-print("✅ FAISS index loaded successfully!")
-
-# Load dataset responses
-with open(DATASET_PATH, "r", encoding="utf-8") as f:
-    dataset = f.readlines()
-print("✅ Responses dataset loaded!")
-
-# Load model & tokenizer (Ensure model path is correct)
-MODEL_NAME = "Futuresony/future_ai_12_10_2024.gguf"  # Change this if using a local model
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
-model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
-
-# Set FAISS threshold (Adjust based on FAISS distance values)
-THRESHOLD = 100  # Lower threshold to improve response accuracy
-
-
-def embed(text):
-    """Convert text to FAISS-compatible vector (Ensure same embeddings as FAISS training)."""
-    tokens = tokenizer.encode(text, add_special_tokens=True)
-    return np.array(tokens, dtype=np.float32).reshape(1, -1)
-
-
-def chatbot_response(user_query):
-    """Fetches response from FAISS or falls back to the model."""
-    query_vector = embed(user_query)  # Convert input to vector
-    D, I = faiss_index.search(query_vector, k=1)  # Search FAISS
-
-    print(f"Closest FAISS match index: {I[0][0]}, Distance: {D[0][0]}")  # Debugging info
-
-    if D[0][0] < THRESHOLD:  # Check if FAISS result is relevant
-        response = dataset[I[0][0]].strip()  # Fetch matched response
-        print("✅ FAISS response used!")
-    else:
-        # Fallback to model-generated response
-        print("⚠️ FAISS match too weak, using model instead.")
-        inputs = tokenizer(user_query, return_tensors="pt")
-        outputs = model.generate(**inputs, max_new_tokens=150)
-        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-    return response
-
-
-# Gradio UI
-iface = gr.Interface(fn=chatbot_response, inputs="text", outputs="text", title="ASA Microfinance Chatbot")
-iface.launch()
+from huggingface_hub import InferenceClient
+
+client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
+
+def format_alpaca_prompt(user_input, system_prompt):
+    """Formats input in Alpaca/LLaMA style"""
+    prompt = f"""{system_prompt}
+
+### Instruction:
+{user_input}
+
+### Response:
+"""
+    return prompt
+
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    formatted_prompt = format_alpaca_prompt(message, system_message)
+
+    response = client.text_generation(
+        formatted_prompt,
+        max_new_tokens=max_tokens,
+        temperature=temperature,
+        top_p=top_p,
+    )
+
+    # ✅ Extract only the response
+    cleaned_response = response.split("### Response:")[-1].strip()
+    
+    yield cleaned_response  # ✅ Output only the answer
+
+demo = gr.ChatInterface(
+    respond,
+    additional_inputs=[
+        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Slider(minimum=1, maximum=250, value=128, 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)"),
+    ],
+)
+
+if __name__ == "__main__":
+    demo.launch()