Add Streamlit app files

app.py

@@ -0,0 +1,141 @@
+import os
+import sys
+import tempfile
+import streamlit as st
+import pandas as pd
+from io import StringIO
+import contextlib
+
+# 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
+
+        # Live log capture
+        log_output = st.empty()
+        string_buffer = StringIO()
+
+        with contextlib.redirect_stdout(string_buffer), st.spinner("🔍 Running analysis..."):
+            output_path = run_pipeline(csv_path, tavily_api_key)
+
+        logs = string_buffer.getvalue()
+        log_output.code(logs)
+
+        if output_path and isinstance(output_path, list):
+            st.success("✅ Analysis complete!")
+
+            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.")
+
+
+
+# import os
+# import sys
+# import tempfile
+# import streamlit as st
+# import pandas as pd
+
+# # 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.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 do you want to analyze?", min_value=1, max_value=10, step=1, value=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:
+#             timespan = st.number_input(f"Timespan (days) for Topic {i+1}", min_value=1, max_value=30, value=7, key=f"days_{i}")
+#         topics_data.append({"topic": topic, "timespan_days": timespan})
+
+#     submitted = st.form_submit_button("Analyze Topics")
+
+# # === Run pipeline on submit ===
+# 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:
+#         # Set environment variables so downstream modules can use them
+#         os.environ["OPENAI_API_KEY"] = openai_api_key
+#         os.environ["TAVILY_API_KEY"] = tavily_api_key
+
+#         # Save user topics to temp CSV
+#         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
+
+#         with st.spinner("Running analysis..."):
+#             output_path = run_pipeline(csv_path, tavily_api_key)
+
+#         if os.path.exists(output_path):
+#             st.success("✅ Analysis complete!")
+#             with open(output_path, 'r', encoding='utf-8') as file:
+#                 html_content = file.read()
+#                 st.download_button("📥 Download HTML Report", html_content, file_name="news_report.html", mime="text/html")
+#                 st.components.v1.html(html_content, height=600, scrolling=True)
+#         else:
+#             st.error("❌ Something went wrong during the analysis.")

requirements.txt

@@ -0,0 +1,88 @@
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.9.0
+async-timeout==4.0.3
+attrs==25.3.0
+blinker==1.9.0
+cachetools==6.1.0
+certifi==2025.6.15
+charset-normalizer==3.4.2
+click==8.1.8
+distro==1.9.0
+exceptiongroup==1.3.0
+filelock==3.18.0
+fsspec==2025.5.1
+gitdb==4.0.12
+GitPython==3.1.44
+greenlet==3.2.3
+h11==0.16.0
+hf-xet==1.1.5
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.33.1
+idna==3.10
+importlib_metadata==8.7.0
+Jinja2==3.1.6
+jiter==0.10.0
+jsonpatch==1.33
+jsonpointer==3.0.0
+jsonschema==4.24.0
+jsonschema-specifications==2025.4.1
+langchain==0.3.26
+langchain-core==0.3.66
+langchain-openai==0.3.27
+langchain-text-splitters==0.3.8
+langsmith==0.4.4
+Markdown==3.8.2
+MarkupSafe==3.0.2
+mpmath==1.3.0
+narwhals==1.45.0
+networkx==3.2.1
+numpy==1.26.4
+openai==1.93.0
+orjson==3.10.18
+packaging==24.2
+pandas==2.3.0
+pillow==11.0.0
+protobuf==6.31.1
+pyarrow==20.0.0
+pydantic==2.11.7
+pydantic_core==2.33.2
+pydeck==0.9.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.1
+pytz==2025.2
+PyYAML==6.0.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.4
+requests-toolbelt==1.0.0
+rpds-py==0.26.0
+safetensors==0.5.3
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+SQLAlchemy==2.0.41
+streamlit==1.46.1
+sympy==1.13.1
+tenacity==9.1.2
+tiktoken==0.9.0
+tokenizers==0.21.2
+toml==0.10.2
+torch==2.2.2
+torchvision==0.17.2
+# OR if 0.17.2 still breaks, try:
+# torchvision==0.16.1
+sympy==1.13.1
+#sympy==1.14.0
+#torch>=2.2.0,<2.6.0
+#torchaudio==2.2.2
+tornado==6.5.1
+tqdm==4.67.1
+transformers==4.53.0
+typing-inspection==0.4.1
+typing_extensions==4.14.0
+tzdata==2025.2
+urllib3==2.5.0
+zipp==3.23.0
+zstandard==0.23.0