Spaces:
Sleeping
Sleeping
| import os | |
| import sys | |
| import tempfile | |
| import time | |
| import itertools | |
| import streamlit as st | |
| import pandas as pd | |
| from io import BytesIO | |
| from xhtml2pdf import pisa | |
| # Add 'src' to Python path so we can import main.py | |
| sys.path.append(os.path.join(os.path.dirname(__file__), 'src')) | |
| from main import run_pipeline | |
| st.set_page_config(page_title="📰 AI News Analyzer", layout="wide") | |
| st.title("🧠 AI-Powered Investing News Analyzer") | |
| # === API Key Input === | |
| st.subheader("🔐 API Keys") | |
| openai_api_key = st.text_input("OpenAI API Key", type="password").strip() | |
| tavily_api_key = st.text_input("Tavily API Key", type="password").strip() | |
| # === Topic Input === | |
| st.subheader("📈 Topics of Interest") | |
| topics_data = [] | |
| with st.form("topics_form"): | |
| topic_count = st.number_input("How many topics?", min_value=1, max_value=10, value=1, step=1) | |
| for i in range(topic_count): | |
| col1, col2 = st.columns(2) | |
| with col1: | |
| topic = st.text_input(f"Topic {i+1}", key=f"topic_{i}") | |
| with col2: | |
| days = st.number_input(f"Timespan (days)", min_value=1, max_value=30, value=7, key=f"days_{i}") | |
| topics_data.append({"topic": topic, "timespan_days": days}) | |
| submitted = st.form_submit_button("Run Analysis") | |
| # === Tabs Setup === | |
| tab_report, tab_articles, tab_insights = st.tabs(["📝 Report", "📋 Articles", "📊 Insights"]) | |
| articles_df = pd.DataFrame() | |
| insights_df = pd.DataFrame() | |
| html_paths = [] | |
| def convert_html_to_pdf(source_html): | |
| output = BytesIO() | |
| pisa.CreatePDF(source_html, dest=output) | |
| return output.getvalue() | |
| # === Submission logic === | |
| if submitted: | |
| if not openai_api_key or not tavily_api_key or not all([td['topic'] for td in topics_data]): | |
| st.warning("Please fill in all fields.") | |
| else: | |
| os.environ["OPENAI_API_KEY"] = openai_api_key | |
| os.environ["TAVILY_API_KEY"] = tavily_api_key | |
| df = pd.DataFrame(topics_data) | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmp_csv: | |
| df.to_csv(tmp_csv.name, index=False) | |
| csv_path = tmp_csv.name | |
| spinner_box = st.empty() | |
| log_box = st.empty() | |
| logs = [] | |
| def log(msg): | |
| logs.append(msg) | |
| log_box.code("\n".join(logs)) | |
| try: | |
| spinner_box.markdown("⏳ Running analysis pipeline...") | |
| # Run the full pipeline | |
| html_paths, articles_df, insights_df = run_pipeline(csv_path, tavily_api_key, progress_callback=log) | |
| spinner_box.success("✅ Analysis complete!") | |
| # --- Report Tab --- | |
| with tab_report: | |
| if html_paths: | |
| for path in html_paths: | |
| with open(path, 'r', encoding='utf-8') as f: | |
| html_content = f.read() | |
| st.components.v1.html(html_content, height=600, scrolling=True) | |
| pdf_data = convert_html_to_pdf(html_content) | |
| st.download_button( | |
| label="⬇️ Download Report as PDF", | |
| data=pdf_data, | |
| file_name=os.path.basename(path).replace(".html", ".pdf"), | |
| mime="application/pdf" | |
| ) | |
| else: | |
| st.error("❌ No reports were generated.") | |
| # --- Articles Tab --- | |
| with tab_articles: | |
| if not articles_df.empty: | |
| st.dataframe(articles_df, use_container_width=True) | |
| else: | |
| st.info("No articles available.") | |
| # --- Insights Tab --- | |
| with tab_insights: | |
| if not insights_df.empty: | |
| st.dataframe(insights_df, use_container_width=True) | |
| else: | |
| st.info("No insights available.") | |
| except Exception as e: | |
| spinner_box.error("❌ Failed.") | |
| log_box.error(f"❌ Error: {e}") | |
| # import os | |
| # import sys | |
| # import tempfile | |
| # import time | |
| # import itertools | |
| # import streamlit as st | |
| # import pandas as pd | |
| # from threading import Thread | |
| # from io import StringIO | |
| # # Add 'src' to Python path so we can import main.py | |
| # sys.path.append(os.path.join(os.path.dirname(__file__), 'src')) | |
| # from main import run_pipeline | |
| # st.set_page_config(page_title="📰 AI News Analyzer", layout="wide") | |
| # st.title("🧠 AI-Powered Investing News Analyzer") | |
| # # === API Key Input === | |
| # st.subheader("🔐 API Keys") | |
| # openai_api_key = st.text_input("OpenAI API Key", type="password").strip() | |
| # tavily_api_key = st.text_input("Tavily API Key", type="password").strip() | |
| # # === Topic Input === | |
| # st.subheader("📈 Topics of Interest") | |
| # topics_data = [] | |
| # with st.form("topics_form"): | |
| # topic_count = st.number_input("How many topics?", min_value=1, max_value=10, value=1, step=1) | |
| # for i in range(topic_count): | |
| # col1, col2 = st.columns(2) | |
| # with col1: | |
| # topic = st.text_input(f"Topic {i+1}", key=f"topic_{i}") | |
| # with col2: | |
| # days = st.number_input(f"Timespan (days)", min_value=1, max_value=30, value=7, key=f"days_{i}") | |
| # topics_data.append({"topic": topic, "timespan_days": days}) | |
| # submitted = st.form_submit_button("Run Analysis") | |
| # # === Submission logic === | |
| # if submitted: | |
| # if not openai_api_key or not tavily_api_key or not all([td['topic'] for td in topics_data]): | |
| # st.warning("Please fill in all fields.") | |
| # else: | |
| # os.environ["OPENAI_API_KEY"] = openai_api_key | |
| # os.environ["TAVILY_API_KEY"] = tavily_api_key | |
| # df = pd.DataFrame(topics_data) | |
| # with tempfile.NamedTemporaryFile(delete=False, suffix=".csv") as tmp_csv: | |
| # df.to_csv(tmp_csv.name, index=False) | |
| # csv_path = tmp_csv.name | |
| # # === UI Elements === | |
| # spinner_box = st.empty() # For rotating messages | |
| # log_box = st.empty() # For logs | |
| # logs = [] | |
| # rotating = True | |
| # def log(msg): | |
| # logs.append(msg) | |
| # log_box.code("\n".join(logs)) | |
| # # === Rotating UI Messages === | |
| # def rotating_messages(): | |
| # messages = itertools.cycle([ | |
| # "🔍 Searching financial news...", | |
| # "🧠 Running language models...", | |
| # "📊 Analyzing investor sentiment...", | |
| # "📝 Summarizing key takeaways...", | |
| # "💹 Building markdown reports..." | |
| # ]) | |
| # while rotating: | |
| # spinner_box.markdown(f"⏳ {next(messages)}") | |
| # time.sleep(1.5) | |
| # rotator_thread = Thread(target=rotating_messages) | |
| # rotator_thread.start() | |
| # try: | |
| # # Check API Keys | |
| # import openai | |
| # openai.OpenAI(api_key=openai_api_key).models.list() | |
| # log("✅ OpenAI API key is valid.") | |
| # import requests | |
| # tavily_test = requests.post( | |
| # "https://api.tavily.com/search", | |
| # headers={"Authorization": f"Bearer {tavily_api_key}"}, | |
| # json={"query": "test", "days": 1, "max_results": 1} | |
| # ) | |
| # if tavily_test.status_code == 200: | |
| # log("✅ Tavily API key is valid.") | |
| # else: | |
| # raise ValueError(f"Tavily error: {tavily_test.status_code} - {tavily_test.text}") | |
| # # Run the full pipeline | |
| # log("🚀 Running analysis pipeline...") | |
| # output_path = run_pipeline(csv_path, tavily_api_key, progress_callback=log) | |
| # rotating = False | |
| # rotator_thread.join() | |
| # spinner_box.success("✅ Analysis complete!") | |
| # if output_path and isinstance(output_path, list): | |
| # for path in output_path: | |
| # if os.path.exists(path): | |
| # with open(path, 'r', encoding='utf-8') as file: | |
| # html_content = file.read() | |
| # filename = os.path.basename(path) | |
| # st.download_button( | |
| # label=f"📥 Download {filename}", | |
| # data=html_content, | |
| # file_name=filename, | |
| # mime="text/html" | |
| # ) | |
| # st.components.v1.html(html_content, height=600, scrolling=True) | |
| # else: | |
| # st.error("❌ No reports were generated.") | |
| # except Exception as e: | |
| # rotating = False | |
| # rotator_thread.join() | |
| # spinner_box.error("❌ Failed.") | |
| # log_box.error(f"❌ Error: {e}") | |