refactor app.py to integrate multi-agent AI functionality and add chat endpoint for investment queries

Author: yashksaini-coder

app.py

@@ -1,15 +1,14 @@
+# API imports
 from fastapi import FastAPI
 import groq
-from agno.agent import Agent
-from agno.models.groq import Groq
-from agno.tools.yfinance import YFinanceTools
-from agno.tools.duckduckgo import DuckDuckGoTools
-from agno.agent import Agent, RunResponse
 import os
 from dotenv import load_dotenv
-# Load API key from .env file
 from fastapi.middleware.cors import CORSMiddleware
 from topStocks import get_top_stocks
+from agents import multi_ai
+from agno.agent import RunResponse
+
+
 load_dotenv(dotenv_path=".env")
 GROQ_API_KEY = os.getenv("api_key")
 
@@ -28,59 +27,35 @@
     allow_headers=["*"],  
 )
 
-web_search_agent = Agent(
-    name="web_agent",
-    role="search the web for information based on the user given input",
-    model=Groq(id="llama-3.3-70b-specdec",api_key=GROQ_API_KEY),
-    tools=[
-        DuckDuckGoTools(search=True, news=True),
-
-    ],
-    instructions=[
-        "You are a very professional web search AI agent",
-        "your job is to search the web for information based on the user given input",
-        "provide exact information to the user available on the web",
-    ],
-    structured_outputs=False,
-    markdown=True,
-)
-financial_agent = Agent(
-    name="financial_agent",
-    role="get financial information",
-    model=Groq(id="llama-3.3-70b-specdec",api_key=GROQ_API_KEY),
-    tools=[
-        YFinanceTools(stock_price=True,
-                    analyst_recommendations=True,
-                    stock_fundamentals=True, 
-                    company_info=True, 
-                    technical_indicators=True, 
-                    historical_prices=True,
-                    key_financial_ratios = True,
-                    income_statements = True,
-                    ),
-    ],
-    instructions=[
-        "You are a very professional financial advisor AI agent",
-        "your job is to provide financial information to users",
-        "you can provide stock price, analyst recommendations, and stock fundamentals",
-        "you can also provide information about companies, industries, and financial terms",
-    ],
-    structured_outputs=False,
-    markdown=True,
-)
-
-multi_ai = Agent(
-    team=[web_search_agent, financial_agent],
-    model=Groq(id="llama-3.3-70b-specdec",api_key=GROQ_API_KEY),
-    markdown=True,
-)
-
 @app.get("/top-stocks")
 async def read_top_stocks():
     top_stocks = ['AAPL', 'GOOGL', 'MSFT', 'AMZN', 'TSLA']
     stock_info = get_top_stocks(top_stocks)
     return stock_info
 
+
+@app.get("/chat")
+def chat(query: str):
+    """
+    API endpoint to handle user investment-related questions and return AI-generated insights.
+    """
+    if not query:
+        return {"error": "Query parameter is required"}
+    
+    try:
+        response = groq_client.chat.completions.create(
+            model="llama-3.3-70b-versatile", 
+            messages=[{"role": "system", "content": "You are an AI investment assistant."},
+                      {"role": "user", "content": query}]
+        )
+        
+        answer = response.choices[0].message.content
+        return {"question": query, "answer": answer}
+    
+    except Exception as e:
+        return {"error": str(e)}
+
+
 @app.get("/ask")
 def ask(query: str):
     """
@@ -90,7 +65,6 @@ def ask(query: str):
         return {"error": "Query parameter is required"}
 
     try:
-        # response = financial_agent.print_response(query)
         response: RunResponse = multi_ai.run(query)
         answer = response.content