Upload 2 files

app/app.py

@@ -0,0 +1,387 @@
+"""
+FIN-SIGHT Streamlit Dashboard
+
+Place this file at the project root and the provided `agentic.py` inside `utils/agentic.py`.
+
+Features:
+- Sidebar to select tickers, interests, lookback days and indicators
+- Price + indicator charts, metrics and volume
+- Refresh / Live update capability (basic)
+- Bottom AI Insights panel that calls the `run_financial_crew` function from utils.agentic
+
+Notes:
+- Requires `yfinance`, `streamlit`, `plotly`, and your CrewAI dependencies (crewai, crewai_tools) for the agentic crew to run.
+- The agentic crew will block while generating insights (wrapped with spinner). Heavy/slow if LLM / Serper not configured.
+
+Run with:
+$ streamlit run fin_sight_streamlit_app.py
+
+"""
+
+import streamlit as st
+import pandas as pd
+import numpy as np
+import yfinance as yf
+import time
+from datetime import datetime, timedelta
+import plotly.express as px
+import plotly.graph_objects as go
+from typing import List
+# MODIFICATION: Removed unused PDF/IO libraries
+# import io
+# from reportlab.lib.pagesizes import letter
+# from reportlab.pdfgen import canvas as pdf_canvas
+
+# Import the agentic crew runner (must be provided in utils/agentic.py)
+try:
+    from utils.agentic import run_financial_crew
+    AGENTIC_AVAILABLE = True
+except Exception:
+    AGENTIC_AVAILABLE = False
+
+# -----------------------
+# Helper functions
+# -----------------------
+
+@st.cache_data(ttl=30)
+def fetch_market_data(ticker: str, days: int = 7) -> pd.DataFrame:
+    """Fetch historical market data for `ticker` using yfinance.
+    Uses a reasonable interval depending on lookback days to keep data size manageable.
+    Caches results for 30 seconds by default.
+    """
+    ticker = ticker.strip().upper()
+    if days <= 7:
+        interval = "5m"
+        period = f"{days}d"
+    elif days <= 60:
+        interval = "1h"
+        period = f"{days}d"
+    else:
+        interval = "1d"
+        period = f"{days}d"
+
+    t = yf.Ticker(ticker)
+    # try history; sometimes yfinance may return empty for small intervals for old days
+    df = t.history(period=period, interval=interval, actions=False)
+    if df.empty:
+        # fallback to 1d interval
+        df = t.history(period=f"{days}d", interval="1d", actions=False)
+    if df.empty:
+        raise ValueError(f"No market data found for {ticker} with lookback {days} days.")
+    df = df.reset_index()
+    df.rename(columns={"index": "Datetime"}, inplace=True)
+    return df
+
+
+def compute_indicators(df: pd.DataFrame, sma_windows: List[int] = [20, 50], ema_windows: List[int] = [12, 26]) -> pd.DataFrame:
+    df = df.copy()
+    for w in sma_windows:
+        df[f"SMA_{w}"] = df["Close"].rolling(window=w, min_periods=1).mean()
+    for w in ema_windows:
+        df[f"EMA_{w}"] = df["Close"].ewm(span=w, adjust=False).mean()
+    # RSI (14)
+    delta = df["Close"].diff()
+    up, down = delta.clip(lower=0), -1 * delta.clip(upper=0)
+    roll_up = up.ewm(com=13, adjust=False).mean()
+    roll_down = down.ewm(com=13, adjust=False).mean()
+    rs = roll_up / (roll_down + 1e-9)
+    df["RSI_14"] = 100 - (100 / (1 + rs))
+    return df
+
+
+def format_price(p: float) -> str:
+    return f"{p:,.2f}"
+
+
+# -----------------------
+# Streamlit app layout
+# -----------------------
+
+st.set_page_config(page_title="FIN-SIGHT — Real-time Financial Insights", layout="wide")
+
+st.sidebar.title("FIN-SIGHT Controls")
+with st.sidebar.form(key="controls_form"):
+    tickers_input = st.text_input("Tickers (comma-separated)", value="AAPL, MSFT, NVDA")
+    interests_input = st.text_input("Topics / Interests (comma-separated)", value="NVIDIA stock, US inflation rate")
+    lookback_days = st.slider("Lookback window (days)", min_value=1, max_value=365, value=30)
+    show_sma = st.checkbox("Show SMAs (20,50)", value=True)
+    show_ema = st.checkbox("Show EMAs (12,26)", value=True)
+    show_rsi = st.checkbox("Show RSI (14)", value=True)
+    show_volume = st.checkbox("Show Volume", value=True)
+    refresh_interval = st.number_input("Live refresh interval (seconds)", min_value=5, max_value=600, value=60)
+    start_live = st.form_submit_button("Apply")
+
+# Live toggle stored in session state
+if "live_mode" not in st.session_state:
+    st.session_state.live_mode = False
+
+col1, col2 = st.columns([1, 3])
+with col1:
+    st.markdown("### Selected Tickers")
+    tickers = [t.strip().upper() for t in tickers_input.split(",") if t.strip()]
+    if not tickers:
+        st.warning("Enter at least one ticker symbol in the sidebar.")
+    st.write(tickers)
+
+    # Live mode controls
+    if st.session_state.live_mode:
+        if st.button("Stop Live Updates"):
+            st.session_state.live_mode = False
+    else:
+        if st.button("Start Live Updates"):
+            st.session_state.live_mode = True
+
+    if st.button("Refresh Now"):
+        # Force refresh by clearing cache for fetch_market_data
+        fetch_market_data.clear()
+        st.rerun()
+
+with col2:
+    st.title("FIN-SIGHT — Real-time Analytics & AI Insights")
+    st.markdown(
+        "A compact dashboard that displays price charts, indicators and LLM-augmented news insights."
+    )
+
+# -----------------------
+# Fetch, display market panels, and additional visuals (grid, pie charts, bars)
+# -----------------------
+
+if tickers:
+    panels = st.container()
+    with panels:
+        for ticker in tickers:
+            try:
+                df = fetch_market_data(ticker, lookback_days)
+            except Exception as e:
+                st.error(f"Error fetching {ticker}: {e}")
+                continue
+
+            df = compute_indicators(df)
+
+            # Top metrics (latest price, change)
+            latest = df.iloc[-1]
+            prev = df.iloc[-2] if len(df) > 1 else latest
+            change = latest["Close"] - prev["Close"]
+            pct_change = (change / prev["Close"]) * 100 if prev["Close"] != 0 else 0
+
+            st.markdown(f"---\n## {ticker}  —  {format_price(latest['Close'])}  ( {change:+.2f}, {pct_change:+.2f}% )")
+
+            # Price + indicators chart
+            fig = go.Figure()
+            fig.add_trace(go.Scatter(x=df["Datetime"], y=df["Close"], name="Close", mode="lines"))
+            if show_sma:
+                for w in [20, 50]:
+                    colname = f"SMA_{w}"
+                    if colname in df.columns:
+                        fig.add_trace(go.Scatter(x=df["Datetime"], y=df[colname], name=colname, mode="lines"))
+            if show_ema:
+                for w in [12, 26]:
+                    colname = f"EMA_{w}"
+                    if colname in df.columns:
+                        fig.add_trace(go.Scatter(x=df["Datetime"], y=df[colname], name=colname, mode="lines"))
+
+            fig.update_layout(height=320, margin=dict(l=20, r=20, t=30, b=20), legend=dict(orientation="h"))
+            st.plotly_chart(fig, use_container_width=True)
+
+            # Volume & RSI row
+            cols = st.columns([3, 1])
+            with cols[0]:
+                if show_volume and "Volume" in df.columns:
+                    vol_fig = px.bar(df, x="Datetime", y="Volume", labels={"Volume": "Volume"})
+                    vol_fig.update_layout(height=180, margin=dict(l=20, r=20, t=10, b=10))
+                    st.plotly_chart(vol_fig, use_container_width=True)
+            with cols[1]:
+                if show_rsi and "RSI_14" in df.columns:
+                    st.metric("RSI (last)", f"{df['RSI_14'].iloc[-1]:.1f}")
+
+            st.markdown("\n")
+            # Additional Bar Chart: Daily % Change for this stock
+            df['Daily_Return'] = df['Close'].pct_change() * 100
+            ret_fig = px.bar(df.tail(30), x='Datetime', y='Daily_Return', title=f'{ticker} - Daily % Change')
+            ret_fig.update_layout(height=200, margin=dict(l=20, r=20, t=30, b=20))
+            st.plotly_chart(ret_fig, use_container_width=True)
+
+# -----------------------
+# AI Insights area
+
+# Market Overview Dashboard (combined analytics)
+st.markdown('---')
+st.subheader('Market Overview — Comparative Visuals')
+# Build combined dataframe dict
+combined_close = {}
+market_caps = {}
+for ticker in tickers:
+    try:
+        tdf = fetch_market_data(ticker, lookback_days)
+        combined_close[ticker] = tdf[['Datetime','Close']].set_index('Datetime')['Close']
+        # fetch market cap
+        try:
+            info = yf.Ticker(ticker).info
+            market_caps[ticker] = info.get('marketCap') or 0
+        except Exception:
+            market_caps[ticker] = 0
+    except Exception:
+        market_caps[ticker] = 0
+
+if combined_close:
+    combined_df = pd.concat(combined_close, axis=1)
+    combined_df = combined_df.sort_index()
+    # Normalize for comparison
+    norm_df = combined_df.ffill().dropna()
+    if not norm_df.empty:
+        norm_df = norm_df / norm_df.iloc[0]
+        norm_df_reset = norm_df.reset_index()
+        # Line chart comparison
+        fig_all = px.line(norm_df_reset, x='Datetime', y=norm_df_reset.columns[1:], labels={'value':'Normalized Price'})
+        fig_all.update_layout(height=400, title='Normalized Price Comparison')
+        st.plotly_chart(fig_all, use_container_width=True)
+
+    # MODIFICATION: Added st.columns to create a grid layout
+    # for heatmap and pie chart
+    
+    # --- Start of Grid Layout ---
+    col_m1, col_m2 = st.columns(2)
+    returns = combined_df.pct_change().dropna()
+
+    with col_m1:
+        # Correlation heatmap
+        if not returns.empty:
+            corr = returns.corr()
+            heatmap = go.Figure(data=go.Heatmap(z=corr.values, x=corr.columns, y=corr.index, colorscale='RdBu'))
+            heatmap.update_layout(height=350, title='Returns Correlation Heatmap')
+            st.plotly_chart(heatmap, use_container_width=True)
+        else:
+            st.info("Not enough data for correlation heatmap.")
+
+    with col_m2:
+        # Market Cap pie chart
+        mc_df = pd.DataFrame({'Ticker': list(market_caps.keys()), 'MarketCap': list(market_caps.values())})
+        mc_df = mc_df[mc_df['MarketCap'] > 0]
+        if not mc_df.empty:
+            pie = px.pie(mc_df, names='Ticker', values='MarketCap', title='Market Cap Distribution')
+            pie.update_layout(height=350)
+            st.plotly_chart(pie, use_container_width=True)
+        else:
+            st.info("No market cap data available for pie chart.")
+    
+    # --- End of Grid Layout ---
+
+    # Cumulative returns bar chart (full width below the grid)
+    if not returns.empty:
+        cum_returns = (1 + returns).cumprod().iloc[-1] - 1
+        cum_df = cum_returns.reset_index()
+        cum_df.columns = ['Ticker','CumulativeReturn']
+        bar_cum = px.bar(cum_df, x='Ticker', y='CumulativeReturn', title='Cumulative Return')
+        bar_cum.update_layout(height=300)
+        st.plotly_chart(bar_cum, use_container_width=True)
+        
+else:
+    st.info('No combined market data available for overview visuals.')
+
+st.markdown('---')
+st.header('AI Insights & Research')
+
+if not AGENTIC_AVAILABLE:
+    st.warning(
+        'Agentic crew (utils.agentic) not available or failed to import. Place agentic.py at utils/agentic.py and ensure crewai dependencies are installed.'
+    )
+
+# Collect interests
+interests = [t.strip() for t in interests_input.split(',') if t.strip()]
+
+insights_placeholder = st.empty()
+insights_collapsed = st.checkbox('Keep insights panel collapsed by default', value=False)
+
+with insights_placeholder.container():
+    if st.button('Generate AI Insights'):
+        if not AGENTIC_AVAILABLE:
+            st.error('Agentic crew not available. Cannot generate insights.')
+        else:
+            with st.spinner('Running financial crew — gathering research & analysis (this may take some time)...'):
+                try:
+                    result = run_financial_crew(interests)
+                    # store last report for export
+                    st.session_state['last_ai_report'] = result
+                except Exception as e:
+                    st.error(f'Error while running financial crew: {e}')
+                    result = None
+
+            if result:
+                st.subheader('Investor Insight Report (LLM)')
+                st.markdown(result)
+            else:
+                st.info('No output returned from the financial crew.')
+
+# Live update loop
+if st.session_state.live_mode:
+    try:
+        time.sleep(max(1, int(refresh_interval)))
+        st.rerun()
+    except Exception:
+        pass
+
+# Live update loop
+if st.session_state.live_mode:
+    # Simple live update implementation: sleep -> rerun. This will re-run the whole script.
+    try:
+        time.sleep(max(1, int(refresh_interval)))
+        st.rerun()
+    except Exception:
+        # If the script cannot rerun, just ignore
+        pass
+
+# -----------------------
+# Dataframe display & Export options
+
+# Display combined data if user wants
+if st.checkbox('Show raw data and download CSV'):
+    for ticker in tickers:
+        try:
+            df = fetch_market_data(ticker, lookback_days)
+            st.subheader(f'Raw Data - {ticker}')
+            st.dataframe(df)
+            csv = df.to_csv(index=False).encode('utf-8')
+            st.download_button(
+                label=f'Download {ticker} data as CSV',
+                data=csv,
+                file_name=f'{ticker}_data.csv',
+                mime='text/csv'
+            )
+        except Exception:
+            pass
+
+# MODIFICATION: Replaced PDF export with Markdown (.md) export
+# This removes the need for 'reportlab' and 'io' libraries
+last_report = st.session_state.get('last_ai_report')
+if st.button('Export AI Report to Markdown (.md)'):
+    if not last_report:
+        st.error('No AI report available. Generate insights first.')
+    else:
+        try:
+            # Prepare the markdown content
+            md_content = f"# FIN-SIGHT - Investor Insight Report\n\n"
+            md_content += f"**Date:** {datetime.utcnow().strftime('%Y-%m-%d %H:%M UTC')}\n\n"
+            md_content += "---\n\n"
+            md_content += str(last_report) # Add the raw report from the AI
+            
+            # Encode for download
+            md_bytes = md_content.encode('utf-8')
+            
+            st.success('Markdown file prepared!')
+            # Show the download button
+            st.download_button(
+                label='Download AI Report (.md)', 
+                data=md_bytes, 
+                file_name='ai_report.md', 
+                mime='text/markdown'
+            )
+        except Exception as e:
+            st.error(f"Failed to prepare markdown file: {e}")
+
+
+# Footer / tips
+st.markdown("---")
+st.caption("Tip: Configure your LLM credentials, Serper/SerperDev keys and CrewAI environment before generating AI insights. If you plan to run this on a server, consider running the agentic crew asynchronously (e.g., background worker) and store results in a DB to avoid blocking the UI.")
+
+
+# End of file

app/utils/agentic.py

@@ -0,0 +1,184 @@
+"""
+FinancialInsights.py
+A single-file, modular-style agentic workflow for financial news insights.
+This file can be imported by a main application (e.g., a FastAPI server)
+to run the crew.
+"""
+
+import os
+from crewai import Agent, Task, Crew, Process, LLM
+from crewai_tools import SerperDevTool
+
+# --- 1. Configuration ---
+
+# Using a placeholder for the model name as per your original script.
+# Replace with a valid model identifier if needed.
+LLM_MODEL = "gemini/gemini-2.5-flash-lite"
+LLM_TEMPERATURE = 0.7
+
+SERPER_SEARCH_URL = "https://google.serper.dev/search"
+SERPER_N_RESULTS = 5 # Increased results for better financial context
+
+# --- 2. LLM & Tool Initialization ---
+
+# Initialize the LLM instance
+llm = LLM(
+    model=LLM_MODEL,
+    temperature=LLM_TEMPERATURE,
+)
+
+# Initialize the search tool
+search_tool = SerperDevTool(
+    search_url=SERPER_SEARCH_URL,
+    n_results=SERPER_N_RESULTS,
+)
+
+
+# --- 3. Agent Definitions ---
+
+def create_financial_researcher():
+    """Creates the Financial Researcher agent."""
+    return Agent(
+        role="Financial Researcher",
+        goal="Gather the latest news, market sentiment, and key developments "
+             "for the given list of financial topics, companies, and cryptocurrencies. "
+             "Use the Serper tool to find relevant articles, reports, and discussions.",
+        backstory=(
+            "You are an expert financial researcher, skilled at digging through "
+            "market news, press releases, and financial forums to find the most "
+            "relevant and timely information for an investor."
+        ),
+        tools=[search_tool],
+        verbose=True,
+        memory=True,
+        llm=llm,
+    )
+
+def create_financial_analyst():
+    """Creates the Financial Analyst agent."""
+    return Agent(
+        role="Financial Analyst",
+        goal="Analyze the raw research findings and synthesize them into a "
+             "consolidated, easy-to-read investor insight report. "
+             "Identify key trends, potential risks, and opportunities. "
+             "The final output must be a professional report for an investor.",
+        backstory=(
+            "You are a seasoned financial analyst with a talent for "
+            "cutting through the noise. You can take a pile of raw data and "
+            "news snippets and distill them into actionable insights and "
+            "concise summaries for busy investors."
+        ),
+        tools=[],  # No external tools needed; analyzes data from the researcher
+        verbose=True,
+        memory=True,
+        allow_delegation=False,
+        llm=llm,
+    )
+
+
+# --- 4. Task Definitions ---
+
+def create_research_task(agent):
+    """Creates the research task for the given agent."""
+    return Task(
+        description=(
+            "For each topic in the provided list {interests}, search for the "
+            "latest news, market analysis, and significant events from the past 48 hours. "
+            "Gather key snippets, sources, and general sentiment."
+        ),
+        expected_output=(
+            "A structured report with sections for each topic, each containing:\n"
+            "Topic: <topic name>\n"
+            "Key News Snippets:\n- [Source]: <snippet>...\n"
+            "Market Sentiment:\n- <Summary of general sentiment (e.g., bullish, bearish, neutral)>\n"
+            "Recent Developments:\n- <Bulleted list of key events or changes>"
+        ),
+        agent=agent,
+        tools=[search_tool],
+    )
+
+def create_analysis_task(agent):
+    """Creates the analysis and reporting task for the given agent."""
+    return Task(
+        description=(
+            "Take the researcher's raw findings for all {interests}. "
+            "Analyze and synthesize this information into a consolidated 'Investor Insight' report. "
+            "Start with a high-level executive summary, then provide a detailed "
+            "breakdown for each topic. Focus on what this information *means* "
+            "for an investor, highlighting key insights, risks, and potential opportunities."
+        ),
+        expected_output=(
+            "A comprehensive investor report in markdown format.\n\n"
+            "## Executive Summary\n"
+            "<Brief overview of all topics and major market movements.>\n\n"
+            "## Detailed Insights\n\n"
+            "### [Topic 1 Name]\n"
+            "- **Key Insight:** <What is the most important takeaway?>\n"
+            "- **Recent News:** <Summary of the most impactful news.>\n"
+            "- **Potential Risk:** <Identify a potential risk.>\n"
+            "- **Potential Opportunity:** <Identify a potential opportunity.>\n\n"
+            "### [Topic 2 Name]\n"
+            "- **Key Insight:** <...>\n"
+            "- **Recent News:** <...>\n"
+            "- **Potential Risk:** <...>\n"
+            "- **Potential Opportunity:** <...>\n"
+            "(...and so on for all topics)"
+        ),
+        agent=agent,
+    )
+
+
+# --- 5. Crew Definition & Workflow Function ---
+
+def run_financial_crew(interest_list):
+    """
+    Initializes and kicks off the financial insights crew with a given list of interests.
+    This is the main function to be imported and called by an external app.
+    
+    Args:
+        interest_list (list): A list of financial topics (strings) to research.
+        
+    Returns:
+        str: The final result from the crew's execution (the investor report).
+    """
+    # 1. Create Agents
+    financial_researcher = create_financial_researcher()
+    financial_analyst = create_financial_analyst()
+    
+    # 2. Create Tasks
+    research_task = create_research_task(financial_researcher)
+    analysis_task = create_analysis_task(financial_analyst)
+    
+    # 3. Create Crew
+    financial_crew = Crew(
+        agents=[financial_researcher, financial_analyst],
+        tasks=[research_task, analysis_task],
+        process=Process.sequential, # Sequential: Researcher -> Analyst
+    )
+    
+    # 4. Prepare Inputs
+    inputs = {"interests": interest_list}
+    
+    # 5. Run Crew
+    print(f"Starting crew for financial interests: {interest_list}...")
+    result = financial_crew.kickoff(inputs=inputs)
+    return result
+
+
+# --- 6. Independent Run (for testing) ---
+
+if __name__ == "__main__":
+    """
+    This block allows the script to be run directly for testing purposes.
+    It will not execute when the file is imported as a module.
+    """
+    
+    # Define the list of financial interests to research
+    interests = ["NVIDIA stock", "US inflation rate"]
+    
+    # Run the crew workflow
+    result = run_financial_crew(interests)
+    
+    # Print the final output
+    print("\n=== Final Investor Insight Report ===\n")
+    print(result)