Update app.py

live an dworking

app.py

@@ -1,7 +1,3 @@
-# app.py — NVIDIA NIM + Tool Calling + Gradio Chatbot
-# Model: meta/llama3-8b-instruct (supports OpenAI-style tools)
-# Works with your nvapi-xxxx key on HuggingFace Spaces.
-
 import os
 import json
 import requests
@@ -9,10 +5,7 @@ from pypdf import PdfReader
 from openai import OpenAI
 import gradio as gr
 
-# ===============================
-# ENVIRONMENT CONFIG
-# ===============================
-OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")   # your nvapi-xxxx key
+OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
 BASE_URL = "https://integrate.api.nvidia.com/v1"
 MODEL = "meta/llama3-8b-instruct"
 
@@ -21,10 +14,6 @@ PUSHOVER_USER = os.environ.get("PUSHOVER_USER")
 
 client = OpenAI(api_key=OPENAI_API_KEY, base_url=BASE_URL)
 
-
-# ===============================
-# OPTIONAL: Pushover notification
-# ===============================
 def push(text):
     try:
         if not PUSHOVER_TOKEN or not PUSHOVER_USER:
@@ -42,27 +31,17 @@ def push(text):
     except Exception as e:
         print("Pushover failed:", e)
 
-
-# ===============================
-# TOOL IMPLEMENTATIONS
-# ===============================
 def record_user_details(email, name="Name not provided", notes="not provided"):
-    push(f"Lead captured → {name} | {email} | Notes: {notes}")
+    push(f"Lead → {name} | {email} | {notes}")
     return {"status": "ok", "email": email, "name": name, "notes": notes}
 
 def record_unknown_question(question):
-    push(f"Unknown question: {question}")
+    push(f"Unknown → {question}")
     return {"status": "ok", "question": question}
 
-
-# Register tools globally
 globals()["record_user_details"] = record_user_details
 globals()["record_unknown_question"] = record_unknown_question
 
-
-# ===============================
-# TOOL JSON DEFINITIONS
-# ===============================
 tools = [
     {
         "type": "function",
@@ -84,7 +63,7 @@ tools = [
         "type": "function",
         "function": {
             "name": "record_unknown_question",
-            "description": "Record any question the assistant cannot answer.",
+            "description": "Record an unknown question.",
             "parameters": {
                 "type": "object",
                 "properties": {
@@ -96,66 +75,48 @@ tools = [
     }
 ]
 
-
-# ===============================
-# MAIN ASSISTANT CLASS
-# ===============================
 class Me:
     def __init__(self):
         self.name = "Ayush Tyagi"
         self.summary = ""
         self.linkedin_text = ""
 
-        # Load summary file
         if os.path.exists("me/summary.txt"):
             self.summary = open("me/summary.txt", "r", encoding="utf-8").read()
 
-        # Load PDF if exists
         pdf_path = "me/Ayush_linkdin.pdf"
         if os.path.exists(pdf_path):
             text = []
             reader = PdfReader(pdf_path)
             for page in reader.pages:
-                page_text = page.extract_text()
-                if page_text:
-                    text.append(page_text)
+                t = page.extract_text()
+                if t:
+                    text.append(t)
             self.linkedin_text = "\n\n".join(text)
 
     def system_prompt(self):
         return f"""
-You are acting as {self.name}. You answer questions about his background,
-skills, experience, portfolio, and career.
-
-If you DO NOT know something:
-➡ Use the tool: record_unknown_question
-
-If the user is interested in working with Ayush:
-➡ Ask for their email and call: record_user_details
+You are acting as {self.name}. You answer questions about his background, skills and experience. 
+If you don't know something, use record_unknown_question. 
+If user is interested, ask for email and use record_user_details.
 
-Be friendly, confident, and professional.
-
-### Summary:
+Summary:
 {self.summary}
 
-### LinkedIn Extract:
+LinkedIn:
 {self.linkedin_text}
 """
 
-    # ===============================
-    # CHAT LOOP WITH TOOL CALLING
-    # ===============================
     def chat(self, message, history):
         messages = [{"role": "system", "content": self.system_prompt()}]
 
-        # FIXED: Handle both tuple-history & dict-history
         for item in history:
             if isinstance(item, (list, tuple)) and len(item) == 2:
-                user_msg, bot_msg = item
-                if user_msg:
-                    messages.append({"role": "user", "content": user_msg})
-                if bot_msg:
-                    messages.append({"role": "assistant", "content": bot_msg})
-
+                u, a = item
+                if u:
+                    messages.append({"role": "user", "content": u})
+                if a:
+                    messages.append({"role": "assistant", "content": a})
             elif isinstance(item, dict) and "role" in item and "content" in item:
                 messages.append({"role": item["role"], "content": item["content"]})
 
@@ -174,34 +135,22 @@ Be friendly, confident, and professional.
             finish = choice.finish_reason
             msg = choice.message
 
-            # ---- TOOL CALL ----
             if finish == "tool_calls":
                 messages.append(msg.dict())
-
                 for tool_call in msg.tool_calls:
                     func = tool_call.function
                     name = func.name
                     args = json.loads(func.arguments)
-
-                    tool_fn = globals().get(name)
-                    result = tool_fn(**args)
-
+                    result = globals()[name](**args)
                     messages.append({
                         "role": "tool",
                         "tool_call_id": tool_call.id,
                         "content": json.dumps(result)
                     })
-
-                # Let model continue after tool execution
                 continue
 
-            # ---- NORMAL RESPONSE ----
             return msg.content
 
-
-# ===============================
-# GRADIO APP
-# ===============================
 me = Me()
 
 ui = gr.ChatInterface(