added fixes

app.py

@@ -7,20 +7,34 @@ from langchain.tools import Tool
 from langchain_huggingface import HuggingFacePipeline
 import os
 from dotenv import load_dotenv
-from transformers import AutoModelForCausalLM, AutoTokenizer,pipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import torch
 from langchain.prompts import PromptTemplate
 
+# Load environment variables
+load_dotenv()
+NEWSAPI_KEY = os.getenv("NEWSAPI_KEY")
+access_token = os.getenv("API_KEY")
+
+# Initialize model and pipeline
+tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", token=access_token)
+model = AutoModelForCausalLM.from_pretrained(
+    "google/gemma-2b-it",
+    torch_dtype=torch.bfloat16,
+    token=access_token
+)
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+# Define improved prompt template
 prompt_template = PromptTemplate(
     input_variables=["input"],
     template="""Answer the following question as best you can. You have access to the following tools:
 
-Stock Data Fetcher(ticker) - Fetch recent stock data for a valid stock ticker (e.g., AAPL for Apple).
+Stock Data Fetcher(ticker) - Fetch recent stock data for a valid stock ticker symbol (e.g., AAPL for Apple).
 Stock News Fetcher(ticker) - Fetch recent news articles about a stock ticker.
 Moving Average Calculator(ticker, window=5) - Calculate the moving average of a stock over a 5-day window.
 
 Use the following format:
-
 Question: the input question you must answer
 Thought: you should always think about what to do
 Action: the action to take, should be one of [Stock Data Fetcher, Stock News Fetcher, Moving Average Calculator]
@@ -30,33 +44,16 @@ Observation: the result of the action
 Thought: I now know the final answer
 Final Answer: the final answer to the original input question
 
-Begin!
+Strictly follow this format. Do not provide a Final Answer until all Observations are collected.
 
+Begin!
 Question: {input}
 """
 )
 
-
-load_dotenv()
-NEWSAPI_KEY = os.getenv("NEWSAPI_KEY")
-access_token = os.getenv("API_KEY")
-
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b-it", token = access_token)
-model = AutoModelForCausalLM.from_pretrained(
-    "google/gemma-2b-it",
-    torch_dtype=torch.bfloat16,
-    token = access_token
-)
-pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=1048)
-
-def validate_ticker(ticker):
-    # Ensure ticker is uppercase and length is reasonable (1-5 characters)
-    return ticker.strip().upper()
-
-
+# Helper functions
 def fetch_stock_data(ticker):
     try:
-        ticker = ticker.strip().upper()
         stock = yf.Ticker(ticker)
         hist = stock.history(period="1mo")
         if hist.empty:
@@ -65,7 +62,6 @@ def fetch_stock_data(ticker):
     except Exception as e:
         return {"error": str(e)}
 
-
 def fetch_stock_news(ticker, NEWSAPI_KEY):
     api_url = f"https://newsapi.org/v2/everything?q={ticker}&apiKey={NEWSAPI_KEY}"
     response = requests.get(api_url)
@@ -81,15 +77,13 @@ def calculate_moving_average(ticker, window=5):
     hist[f"{window}-day MA"] = hist["Close"].rolling(window=window).mean()
     return hist[["Close", f"{window}-day MA"]].tail(5)
 
-llm = HuggingFacePipeline(pipeline=pipe)
-
+# Tools
 stock_data_tool = Tool(
     name="Stock Data Fetcher",
     func=fetch_stock_data,
     description="Fetch recent stock data for a valid stock ticker symbol (e.g., AAPL for Apple)."
 )
 
-
 stock_news_tool = Tool(
     name="Stock News Fetcher",
     func=lambda ticker: fetch_stock_news(ticker, NEWSAPI_KEY),
@@ -102,7 +96,9 @@ moving_average_tool = Tool(
     description="Calculate the moving average of a stock over a 5-day window."
 )
 
+# Initialize agent
 tools = [stock_data_tool, stock_news_tool, moving_average_tool]
+llm = HuggingFacePipeline(pipeline=pipe)
 
 agent = initialize_agent(
     tools=tools,
@@ -113,29 +109,19 @@ agent = initialize_agent(
     handle_parsing_errors=True
 )
 
-
-print(fetch_stock_data("AAPL"))
-print(fetch_stock_news("AAPL", NEWSAPI_KEY))
-print(calculate_moving_average("AAPL"))
-
-
+# Streamlit interface
 st.title("Trading Helper Agent")
 
 query = st.text_input("Enter your query:")
 
 if st.button("Submit"):
     if query:
-        st.write("Debug: User Query ->", query)
         with st.spinner("Processing..."):
             try:
                 response = agent.run(query)
-                st.write("Debug: Agent Response ->", response)
                 st.success("Response:")
                 st.write(response)
             except Exception as e:
                 st.error(f"An error occurred: {e}")
-                # Log the full LLM output for debugging
-                if hasattr(e, "output"):
-                    st.write("Raw Output:", e.output)
     else:
         st.warning("Please enter a query.")