docs: Update readme and cleanup

Author: Linked-Liszt

README.md

@@ -4,26 +4,31 @@ OpenAlphaDiffract is an open-source implementation of the AlphaDiffract research
 - Create a dataset from the Materials Project
 - Simulate powder diffraction patterns from those structures
 - Train and evaluate models on the generated dataset
+- Run an inference web app to try out the model
 
-For ease of use, a HF endpoint exists [TODO]. 
-
-## Inference Quickstart
-[TODO]: (probably hosting on HF)
-[TODO]: Minimal local install with the trainer container
 
 ## Dataset Pipeline Overview
 
-1. Acquire CIFs (Downloader Container)
+1. Acquire CIFs (downloader.Dockerfile)
     - Uses the Materials Project API to fetch crystal structures as CIF files
     - Configurable via `configs/download.yaml`
     - Filters structures by checking conventional cell consistency across multiple angle tolerances. This filters ~4.4% of MP structures as of 10/22/2025. 
 
-2. GSAS-II XRD Simulation (Simulator Container)
+2. GSAS-II XRD Simulation (simulator.Dockerfile)
     - Generates synthetic powder diffraction patterns from CIFs
     - Configurable via `configs/simulator.yaml` (e.g., instrument file, noise ranges, job parallelism)
     - Creates .npy files with simulated pattern and metadata ready to be consumed by the training system
 
-3. TODO: Training
+3. Open Alpha Diffract Training (trainer.Dockerfile)
+   - Trains the multi-task AlphaDiffract model on the generated dataset
+   - Configurable via `configs/trainer.docker.yaml` or `configs/trainer.local.yaml`
+   - Logs checkpoints and metrics (CSV and optional MLflow)
+
+4. XRD Inference Web App (ui.Dockerfile)
+   - FastAPI service for model inference with a React frontend
+   - Accepts processed XRD patterns and returns predictions via `/api/predict`
+   - Serves the built frontend from the same container
+
 
 ## Training from Scratch Quickstart
 
@@ -45,14 +50,22 @@ Setup:
    - Optionally set `UID` and `GID` so the containers write files as your user. 
 
 2. Download CIFs:
-   - `scripts/download.sh`
+   - `scripts/download.sh` (or docker compose run --rm trainer)
    - CIFs will be written to `./data/raw_cif`
 
 3. Simulate diffraction patterns:
-   - `scripts/simulate.sh`
+   - `scripts/simulate.sh` (or docker compose run --rm simulator)
    - Patterns will be written to `./data/dataset`
    - Errors (if any) go to `./data/error_logs`
 
+4. Train the model:
+   - `docker compose run --rm trainer`
+   - Checkpoints and logs will be written to `./outputs`
+
+5. Run the inference UI:
+   - Move a model checkpoint to `./src/ui/models/xrd_model.ckpt`
+   - `docker compose up ui`
+
 Notes:
 - You can pass extra CLI args to the simulator via `scripts/simulate.sh`, e.g. `--sims_per_file 1 --parallel_jobs 4`
 - The default container commands and mounts are defined in `compose.yaml`
@@ -66,12 +79,12 @@ OpenAlphaDiffract/
 ├── scripts/ - User-facing scripts
 ├── src/ - Source code for pipeline components
 │   ├── downloader/
-│   └── simulator/
-
+│   ├── simulator/
+│   ├── trainer/
+│   └── ui/
 ```
 
 
-
 ## Citation
 
-We hope this code was helpful to your work! If you use our code or extend our work, please consider citing our paper:
+We hope this code was helpful to your work! If you use our code or extend our work, please consider citing our paper. (Will be added once released!)

configs/download.yaml

@@ -14,23 +14,16 @@ skip_existing: true
 
 # Lattice reduction tolerances (Niggli reduction of conventional standard structure)
 representation:
-  # Symmetry tolerance parameters used by SpacegroupAnalyzer (paper defaults)
-  symprec: 0.01            # Distance tolerance (Angstroms)
-  angle_tolerance: 5.0     # Angle tolerance (degrees)
+  symprec: 0.01            
+  angle_tolerance: 5.0   
 
 # Initial structural filters (applied to standardized structure)
 filters:
-  # Maximum allowed atoms per unit cell (paper default)
   max_atoms: 500
 
-  # Unit cell volume bounds (Angstrom^3). Set None to disable a bound.
   min_volume:
   max_volume: 100000
 
-  # - require_spacegroup_stability: verify space group is stable across a grid of tolerances
-  # - symprecs / angle_tolerances: tolerance grid to test (defaults match staging/tools)
-  # - check_reduced_cell_consistency: verify Niggli-reduced cell matches crystal-system symmetry
-  # - rtol: absolute tolerance for length/angle equalities in reduced cell checks
   require_spacegroup_stability: true
   symprecs: [0.01, 0.05, 0.1]
   angle_tolerances: [0.1, 1.0, 2.5, 5.0]

configs/simulator.yaml

@@ -14,17 +14,16 @@ worker_base_dir: "/data/workers"
 # --- Execution Control ---
 parallel_jobs: 256
 sims_per_file: 100
-master_seed: 42           # Reproducible parameter sampling
+master_seed: 42          
 cleanup_worker_dirs: true
 progress_step_pct: 0.1   # Progress logging interval in percent
-log_to_console: false     # Useful in HPC settings
+log_to_console: false     
 
 # If true, read SG from "# _original_symmetry_space_group_name_H-M" comment in CIF
 # If using custom CIFs without this comment, set to false to use standard tags
 parse_from_comment: true  
 
 # --- Simulation Parameter Ranges ---
-# The format is ALWAYS (smaller_number, larger_number)
 strain_range: [500, 10000]
 size_range: [0.1, 1.0]
 U_range: [0.0, 3.0]
@@ -37,7 +36,5 @@ scaler_range: [1.0, 1.0]
 wl_range: [0.6199, 0.6199]
 
 # --- Noise Parameter Ranges ---
-# Proportional noise is (intensity * random_factor)
 proportional_noise_range: [0.002, 0.02]
-# Constant noise is (intensity + random_count)
 constant_noise_range: [2, 5]

scripts/ui_dev_setup.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+# Development startup script for XRD Analysis Tool
+
+set -e
+
+echo "=== XRD Analysis Tool - Development Setup ==="
+
+cd src/ui
+
+# Install frontend dependencies
+echo ""
+echo "Installing frontend dependencies..."
+cd src/ui/frontend
+if [ ! -d "node_modules" ]; then
+    npm install
+else
+    echo "Frontend dependencies already installed"
+fi
+
+# Install Python dependencies
+echo ""
+echo "Installing Python dependencies..."
+cd ../..
+
+# Check if uv is installed
+if ! command -v uv &> /dev/null; then
+    echo "⚠️  uv not found. Installing uv..."
+    curl -LsSf https://astral.sh/uv/install.sh | sh
+    export PATH="$HOME/.cargo/bin:$PATH"
+fi
+
+echo "Installing Python dependencies with uv..."
+uv env
+uv pip install -r requirements.txt
+
+echo ""
+echo "Setup complete!"
+echo ""
+echo "To start development:"
+echo "  1. Backend in src/ui:  uv run uvicorn app.main:app --reload --host 0.0.0.0 --port 8000"
+echo "  2. Frontend in src/ui/frontend: npm run dev"