Update app.py

app.py

@@ -2,6 +2,7 @@ import os
 from flask import Flask, render_template, request, jsonify
 from huggingface_hub import InferenceClient  # Import InferenceClient correctly
 from dotenv import load_dotenv
+import json
 
 # Load environment variables from .env file
 load_dotenv()
@@ -18,6 +19,9 @@ client = InferenceClient(HUGGINGFACE_API_KEY)
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
     
+    # Ensure history is a list of tuples
+    history = json.loads(history) if isinstance(history, str) else history
+
     # Include message history (FAQs)
     for val in history:
         if val[0]:
@@ -26,18 +30,21 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
             messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
-    
+
     # Get response from Hugging Face API (for FAQ)
     response = ""
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
+    try:
+        # Use the correct method depending on the Hugging Face model you're using
+        result = client.completion(
+            model="gpt-3.5-turbo",  # Example, adjust to your model
+            inputs=messages,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+        )
+        response = result['choices'][0]['text']
+    except Exception as e:
+        response = str(e)
 
     return response