Update app.py

app.py

@@ -40,10 +40,10 @@ llm = ChatGoogleGenerativeAI(model="gemini-2.5-pro",google_api_key = GOOGLE_API_
 #llm_vis = ChatGoogleGenerativeAI(model="gemini-pro-vision",google_api_key = GOOGLE_API_KEY)
 
 
-activities = st.sidebar.selectbox("Select",["Symbol Analysis","News Sentiment"])
+activities = st.sidebar.selectbox("Select", ["Symbol Analysis", "News Sentiment"])
 
 
-if activities=="Symbol Analysis":
+if activities == "Symbol Analysis":
     ticker_user = st.text_input("Enter Ticker for NSE Stocks","")
     def get_tradingview_analysis(symbol, exchange, screener, interval):
         try:
@@ -367,65 +367,65 @@ if activities=="Symbol Analysis":
             st.error(f"JSON decode error: {e}")
             st.write("Raw text was:")
             st.text(res["output_text"])
-    elif activities=="News Sentiment":
-        st.subheader("News Action : ")
-        url1 = f"https://in.tradingview.com/news-flow/?market=stock&market_country=in"
-        # url2 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/"
-        # url3 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/news/"
-        # url4 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/minds/"
+elif activities=="News Sentiment":
+    st.subheader("News Action : ")
+    url1 = f"https://in.tradingview.com/news-flow/?market=stock&market_country=in"
+    # url2 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/"
+    # url3 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/news/"
+    # url4 = f"https://in.tradingview.com/symbols/NSE-{ticker_user}/minds/"
+
+    loader = WebBaseLoader([url1])
+    docs = loader.load()
     
-        loader = WebBaseLoader([url1])
-        docs = loader.load()
-        
-        st.divider()
+    st.divider()
 
-        llm_prompt_template = """You are an expert Stock Market Trader specializing in stock market insights derived from fundamental analysis, analytical trends, profit-based evaluations, news indicators from different sites and detailed company financials. You will receive one or more news articles from TradingView’s India stock news feed. For each article, perform the following tasks:
+    llm_prompt_template = """You are an expert Stock Market Trader specializing in stock market insights derived from fundamental analysis, analytical trends, profit-based evaluations, news indicators from different sites and detailed company financials. You will receive one or more news articles from TradingView’s India stock news feed. For each article, perform the following tasks:
 
-        Context:
-        {input_documents}
+    Context:
+    {input_documents}
 
-        
-        1. **Identify the stock(s)** mentioned (by ticker and company name).
-        2. **Sentiment analysis**: classify as Bullish, Bearish, or Neutral.
-        3. **Extract critical news**: What is the main event or update? (e.g., earnings beat, regulatory approval, management change, major contract or macro impact).
-        4. **Summarize impact**: Briefly explain how this news might affect stock price and investor behavior (e.g., “could boost investor confidence”, “sign indicates profit pressure”, etc.).
-        5. **Actionable signal**: Based on the sentiment and news, suggest whether this is a “Buy”, “Sell”, “Hold”, or “Watch” recommendation, and the rationale.
-        6. **Overall top picks**: After analyzing all provided articles, rank the top 3–5 stocks to look at this week, including tickers, current sentiment, and why they made the list.
-        
-        ***Format your output as JSON*** with the following structure:
-        
-        ```json
+    
+    1. **Identify the stock(s)** mentioned (by ticker and company name).
+    2. **Sentiment analysis**: classify as Bullish, Bearish, or Neutral.
+    3. **Extract critical news**: What is the main event or update? (e.g., earnings beat, regulatory approval, management change, major contract or macro impact).
+    4. **Summarize impact**: Briefly explain how this news might affect stock price and investor behavior (e.g., “could boost investor confidence”, “sign indicates profit pressure”, etc.).
+    5. **Actionable signal**: Based on the sentiment and news, suggest whether this is a “Buy”, “Sell”, “Hold”, or “Watch” recommendation, and the rationale.
+    6. **Overall top picks**: After analyzing all provided articles, rank the top 3–5 stocks to look at this week, including tickers, current sentiment, and why they made the list.
+    
+    ***Format your output as JSON*** with the following structure:
+    
+    ```json
+    {{
+      "articles": [
         {{
-          "articles": [
-            {{
-              "ticker": "TICKER",
-              "company": "Company Name",
-              "sentiment": "Bullish|Bearish|Neutral",
-              "critical_news": "Brief summary of the key event",
-              "impact_summary": "How this may affect the stock",
-              "action": "Buy|Sell|Hold|Watch"
-            }},
-            ...
-          ],
-          "top_picks": [
-            {{
-              "ticker": "TICKER",
-              "company": "Company Name",
-              "sentiment": "Bullish|Bearish|Neutral",
-              "reason": "Why this stock ranks among top picks"
-            }},
-            ...
-          ]
-        }}
+          "ticker": "TICKER",
+          "company": "Company Name",
+          "sentiment": "Bullish|Bearish|Neutral",
+          "critical_news": "Brief summary of the key event",
+          "impact_summary": "How this may affect the stock",
+          "action": "Buy|Sell|Hold|Watch"
+        }},
+        ...
+      ],
+      "top_picks": [
+        {{
+          "ticker": "TICKER",
+          "company": "Company Name",
+          "sentiment": "Bullish|Bearish|Neutral",
+          "reason": "Why this stock ranks among top picks"
+        }},
+        ...
+      ]
+    }}
 
-        """
-        llm_prompt = PromptTemplate.from_template(llm_prompt_template)
+    """
+    llm_prompt = PromptTemplate.from_template(llm_prompt_template)
+
+    llm_chain = LLMChain(llm=llm,prompt=llm_prompt)
+    stuff_chain = StuffDocumentsChain(llm_chain=llm_chain,document_variable_name="input_documents")
     
-        llm_chain = LLMChain(llm=llm,prompt=llm_prompt)
-        stuff_chain = StuffDocumentsChain(llm_chain=llm_chain,document_variable_name="input_documents")
-        
-        # res = stuff_chain.invoke(docs)
-        res = stuff_chain.invoke({"input_documents": docs})
-        st.write(res["output_text"])
-    else:
-        pass
+    # res = stuff_chain.invoke(docs)
+    res = stuff_chain.invoke({"input_documents": docs})
+    st.write(res["output_text"])
+else:
+    pass