update

.dockerignore

@@ -0,0 +1,15 @@
+.streamlit/
+
+.git
+.gitignore
+README.md
+DEV.md
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.pytest_cache
+.coverage
+.env
+.venv
+*.log

.gitignore

@@ -0,0 +1,12 @@
+.streamlit/
+.env
+docker.env
+local.env
+
+__pycache__/
+*.py[cod]
+.venv/
+*.log
+.python-version
+chromadb
+chromadb/

Dockerfile

@@ -1,20 +1,31 @@
-FROM python:3.13.5-slim
+# Use Python 3.13 slim image
+FROM python:3.13-slim
 
+# Set working directory
 WORKDIR /app
 
+# Install system dependencies
 RUN apt-get update && apt-get install -y \
     build-essential \
     curl \
     git \
     && rm -rf /var/lib/apt/lists/*
 
-COPY requirements.txt ./
+# Install uv
+COPY --from=ghcr.io/astral-sh/uv:latest /uv /bin/uv
+
+# Copy project files
+COPY pyproject.toml uv.lock ./
 COPY src/ ./src/
 
-RUN pip3 install -r requirements.txt
+# Install dependencies
+RUN uv sync --frozen
 
+# Expose port (default 8501, can be overridden)
 EXPOSE 8501
 
+# Health check
 HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# Run the application
+CMD ["sh", "-c", "uv run streamlit run src/legisqa_local/app.py --server.port=${PORT:-8501} --server.address=0.0.0.0"]

README.md

@@ -1,20 +1,64 @@
 ---
-title: Legisqa Local
-emoji: 🚀
-colorFrom: red
+title: LegisQA Local
+emoji: 🏛️
+colorFrom: blue
 colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
+sdk: streamlit
+sdk_version: 1.49.1
+app_file: src/app.py
 pinned: false
-short_description: Streamlit template space
 license: mit
 ---
 
-# Welcome to Streamlit!
+# LegisQA Local
 
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+Query Congressional Bills with AI using local ChromaDB vector search.
 
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+## Features
+
+- 🏛️ Query US Congressional legislation from sessions 113-119
+- 🔍 Semantic search powered by ChromaDB and google/embeddinggemma-300m embeddings
+- 🤖 Multiple AI providers: OpenAI, Anthropic, Together AI, Google
+- 📊 Side-by-side comparison of different models
+- 🏠 Runs completely locally - no external vector database needed
+
+## Setup
+
+The app will automatically download and set up the vector database on first run. This includes:
+
+1. Downloading the HuggingFace dataset `hyperdemocracy/usc-vecs-s8192-o512-google-embeddinggemma-300m`
+2. Loading Congress 119 data (first 200 documents) into local ChromaDB
+3. Setting up the vector search index
+
+For local development, you can also run:
+
+```bash
+# Install dependencies
+uv sync
+
+# Load test data
+uv run python load_chromadb.py
+
+# Run the app
+uv run streamlit run src/app.py
+```
+
+## Dataset
+
+Uses the HuggingFace dataset containing US Congressional legislation with pre-computed embeddings:
+- **Source**: `hyperdemocracy/usc-vecs-s8192-o512-google-embeddinggemma-300m`
+- **Embeddings**: google/embeddinggemma-300m (768 dimensions)
+- **Coverage**: Congress sessions 113-119 (2013-2025)
+- **Documents**: ~233K total (test mode uses 200 from Congress 119)
+
+## Architecture
+
+- **Frontend**: Streamlit
+- **Vector Store**: ChromaDB (local)
+- **Embeddings**: HuggingFace Transformers (google/embeddinggemma-300m)
+- **LLMs**: Multiple providers via LangChain
+- **Data**: HuggingFace Datasets
+
+## Migration from Pinecone
+
+This app was migrated from using Pinecone to local ChromaDB. See `MIGRATION.md` for details.

env.example

@@ -0,0 +1,21 @@
+# Example environment variables for Docker deployment
+# Copy this to .env and fill in your actual values
+
+# LangChain configuration
+LANGCHAIN_API_KEY=your_langchain_api_key_here
+LANGCHAIN_PROJECT=legisqa-local
+
+# LLM Provider API Keys
+OPENAI_API_KEY=your_openai_api_key_here
+ANTHROPIC_API_KEY=your_anthropic_api_key_here
+TOGETHER_API_KEY=your_together_api_key_here
+GOOGLE_API_KEY=your_google_api_key_here
+
+# Port configuration (optional, defaults to 8501 for local, 8505 for Docker)
+PORT=8505
+
+# ChromaDB configuration
+# For local development: use ./chromadb (relative to project root)
+# For Docker: use /app/chroma_data (container path, will be mounted as volume)
+CHROMA_PERSIST_DIRECTORY=./chromadb
+CHROMA_COLLECTION_NAME=usc

pyproject.toml

@@ -0,0 +1,30 @@
+[project]
+name = "legisqa-local"
+version = "0.1.0"
+description = "Congressional Legislation Query and Analysis Tool"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+    "chromadb>=1.1.0",
+    "datasets>=3.0.0",
+    "langchain>=0.3.27",
+    "langchain-anthropic>=0.3.19",
+    "langchain-chroma>=0.1.4",
+    "langchain-community>=0.3.29",
+    "langchain-core>=0.3.75",
+    "langchain-google-genai>=2.1.10",
+    "langchain-huggingface>=0.3.1",
+    "langchain-openai>=0.3.32",
+    "langchain-together>=0.3.1",
+    "sentence-transformers>=5.1.0",
+    "streamlit>=1.49.1",
+    "tqdm>=4.66.0",
+]
+
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["legisqa_local*"]

requirements.txt

@@ -1,3 +0,0 @@
-altair
-pandas
-streamlit

run-docker.sh

@@ -0,0 +1,42 @@
+#!/bin/bash
+
+# Script to run LegisQA with Docker, mounting the ChromaDB volume
+
+# Port configuration (default to 8505 to avoid conflicts)
+PORT=${PORT:-8505}
+
+# ChromaDB host path (local chromadb directory)
+CHROMA_HOST_PATH="$(pwd)/chromadb"
+
+# Container path where ChromaDB will be mounted
+CHROMA_CONTAINER_PATH="/app/chroma_data"
+
+echo "Starting LegisQA Docker container..."
+echo "Port: $PORT"
+echo "ChromaDB Host Path: $CHROMA_HOST_PATH"
+echo "ChromaDB Container Path: $CHROMA_CONTAINER_PATH"
+echo "Environment File: docker.env"
+echo ""
+
+# Check if ChromaDB path exists
+if [ ! -d "$CHROMA_HOST_PATH" ]; then
+    echo "ERROR: ChromaDB path does not exist: $CHROMA_HOST_PATH"
+    exit 1
+fi
+
+# Check if env file exists
+if [ ! -f "docker.env" ]; then
+    echo "ERROR: Environment file does not exist: docker.env"
+    exit 1
+fi
+
+# Run Docker container
+docker run -p $PORT:$PORT \
+  --env-file docker.env \
+  -e PORT=$PORT \
+  -v "$CHROMA_HOST_PATH:$CHROMA_CONTAINER_PATH" \
+  --name legisqa-container \
+  --rm \
+  legisqa-local
+
+echo "Docker container stopped."

src/legisqa_local/__init__.py

@@ -0,0 +1,5 @@
+"""
+LegisQA: Congressional Legislation Query and Analysis Tool
+"""
+
+__version__ = "0.1.0"

src/legisqa_local/app.py

@@ -0,0 +1,51 @@
+"""Main Streamlit application for LegisQA"""
+
+import streamlit as st
+from legisqa_local.config.settings import STREAMLIT_CONFIG, setup_environment
+from legisqa_local.components.sidebar import render_sidebar
+from legisqa_local.tabs.rag_tab import RAGTab
+from legisqa_local.tabs.rag_sbs_tab import RAGSideBySideTab
+from legisqa_local.tabs.guide_tab import GuideTab
+
+
+def main():
+    """Main application function"""
+    # Configure Streamlit
+    st.set_page_config(**STREAMLIT_CONFIG)
+    
+    # Setup environment
+    setup_environment()
+    
+    # Main content
+    st.title(":classical_building: LegisQA :classical_building:")
+    st.header("Query Congressional Bills")
+
+    # Sidebar
+    with st.sidebar:
+        render_sidebar()
+
+    # Create tab instances
+    rag_tab = RAGTab()
+    rag_sbs_tab = RAGSideBySideTab()
+    guide_tab = GuideTab()
+
+    # Create tabs
+    query_rag_tab, query_rag_sbs_tab, guide_tab_ui = st.tabs([
+        rag_tab.name,
+        rag_sbs_tab.name,
+        guide_tab.name,
+    ])
+
+    # Render tab content
+    with query_rag_tab:
+        rag_tab.render()
+
+    with query_rag_sbs_tab:
+        rag_sbs_tab.render()
+
+    with guide_tab_ui:
+        guide_tab.render()
+
+
+if __name__ == "__main__":
+    main()

src/streamlit_app.py

@@ -1,40 +0,0 @@
-import altair as alt
-import numpy as np
-import pandas as pd
-import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))