Removed history and parameters requirements

app.py

@@ -4,24 +4,21 @@ from huggingface_hub import InferenceClient
 app = Flask(__name__)
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-def generate_response(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]})
+DEFAULT_MAX_TOKENS = 512
+DEFAULT_TEMPERATURE = 0.7
+DEFAULT_TOP_P = 0.95
 
+def generate_response(message, system_message):
+    messages = [{"role": "system", "content": system_message}]
     messages.append({"role": "user", "content": message})
+    
     response = ""
-
     for message in client.chat_completion(
         messages,
-        max_tokens=max_tokens,
+        max_tokens=DEFAULT_MAX_TOKENS,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
+        temperature=DEFAULT_TEMPERATURE,
+        top_p=DEFAULT_TOP_P,
     ):
         token = message.choices[0].delta.content
         response += token
@@ -39,15 +36,15 @@ def generate_journal_suggestion(current_page):
         [{"role": "user", "content": suggestion_prompt}],
         max_tokens=150,
         stream=True,
-        temperature=0.7,
-        top_p=0.9,
+        temperature=DEFAULT_TEMPERATURE,
+        top_p=DEFAULT_TOP_P,
     ):
         token = message.choices[0].delta.content
         suggestion_response += token
 
     return suggestion_response
 
-@app.route("/", methods=["POST","GET"])
+@app.route("/", methods=["POST", "GET"])
 def home():
     return "Hi!"
 
@@ -56,17 +53,13 @@ def chat():
     try:
         data = request.json
         message = data.get("message", "")
-        history = data.get("history", [])
         system_message = data.get("system_message", "You are a friendly chatbot.")
-        max_tokens = data.get("max_tokens", 512)
-        temperature = data.get("temperature", 0.7)
-        top_p = data.get("top_p", 0.95)
         journal_page = data.get("journal_page", "")
 
-        if not isinstance(history, list) or not all(isinstance(pair, list) for pair in history):
-            return jsonify({"error": "Invalid history format. It should be a list of [message, response] pairs."}), 400
+        if not message:
+            return jsonify({"error": "Message is required."}), 400
 
-        response = generate_response(message, history, system_message, max_tokens, temperature, top_p)
+        response = generate_response(message, system_message)
 
         suggestion = ""
         if journal_page: