Minor code updates

app.py

@@ -10,28 +10,7 @@ import gradio as gr
 hf_api_key = os.environ.get('HF_API_KEY')
 client = OpenAI()  # Assumes OPENAI_API_KEY is set in environment
 
-
-class Agent:
-    def __init__(self, system=""):
-        self.system = system
-        self.messages = []
-        if self.system:
-            self.messages.append({"role": "system", "content": system})
-
-    def __call__(self, message):
-        self.messages.append({"role": "user", "content": message})
-        result = self.execute()
-        self.messages.append({"role": "assistant", "content": result})
-        return result
-
-    def execute(self):
-        completion = client.chat.completions.create(
-                        model="gpt-4o", 
-                        temperature=0,
-                        messages=self.messages)
-        return completion.choices[0].message.content
-
-
+# Default system prompt
 prompt = """
 You run in a loop of Thought, Action, PAUSE, Observation.
 At the end of the loop you output an Answer
@@ -65,6 +44,27 @@ You then output:
 Answer: A bulldog weights 51 lbs
 """.strip()
 
+class Agent:
+    def __init__(self, system=""):
+        self.system = system
+        self.messages = []
+        if self.system:
+            self.messages.append({"role": "system", "content": system})
+
+    def __call__(self, message):
+        self.messages.append({"role": "user", "content": message})
+        result = self.execute()
+        self.messages.append({"role": "assistant", "content": result})
+        return result
+
+    def execute(self):
+        completion = client.chat.completions.create(
+                        model="gpt-4o", 
+                        temperature=0,
+                        messages=self.messages)
+        return completion.choices[0].message.content
+
+# Tools
 def calculate(what):
     return eval(what)
 
@@ -78,11 +78,13 @@ def average_dog_weight(name):
     else:
         return("An average dog weights 50 lbs")
 
+# Available actions
 known_actions = {
     "calculate": calculate,
     "average_dog_weight": average_dog_weight
 }
 
+# First manual example, use of LLM agent answering a query
 abot = Agent(prompt)
 
 result = abot("How much does a toy poodle weigh?")
@@ -98,6 +100,7 @@ abot(next_prompt)
 
 print(abot.messages)
 
+# Second manual example, use of LLM agent answering a query
 abot = Agent(prompt)
 
 question = """I have 2 dogs, a border collie and a scottish terrier. \
@@ -124,6 +127,7 @@ action_re = re.compile('^Action: (\w+): (.*)$')   # python regular expression to
 @spaces.GPU(duration=120) # Designed to be effect-free in non-ZeroGPU environments, ensuring compatibility across different setups.
 def query(question, max_turns=5):
     i = 0
+    # Create agent based on default system prompt
     bot = Agent(prompt)
     next_prompt = question
     while i < max_turns:
@@ -144,8 +148,6 @@ def query(question, max_turns=5):
             return result
     return "Max turns reached"
 
-#question = """I have 2 dogs, a border collie and a scottish terrier. What is their combined weight"""
-#query(question)
 
 # Gradio interface
 def process_question(question):
@@ -153,7 +155,7 @@ def process_question(question):
 
 iface = gr.Interface(
     fn=process_question,
-    inputs=gr.Textbox(label="Enter your question"),
+    inputs=gr.Textbox(label="Enter your question"), # e.g. I have 2 dogs, a border collie and a scottish terrier. What is their combined weight
     outputs=gr.Textbox(label="Answer"),
     title="Dog Weight Calculator",
     description="Ask about dog weights or perform calculations."