> This page is for version 3.0.0 (Latest) (default). > For other versions, use one of these documentation indexes: > - 3.0.0 (Latest) (default): https://docs.nvidia.com/nim/financial-fraud-training/3.0.0/llms.txt > - 2.0.0: https://docs.nvidia.com/nim/financial-fraud-training/2.0.0/llms.txt > - 1.0.0: https://docs.nvidia.com/nim/financial-fraud-training/1.0.0/llms.txt > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nim/financial-fraud-training/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/financial-fraud-training/_mcp/server. # Quick Start — End-to-End in 5 Steps This section walks through the full EP (Edge Prediction) pipeline from a cold start to a running inference server. Each step depends on the previous one completing successfully. Detailed documentation for every step is in the sections below. **Prerequisites:** Docker with `--gpus all` access, ≥ 2 NVIDIA GPUs, your graph data in the layout described in [Data Layout](/nim/financial-fraud-training/data/data-def). --- ## Step 1 — Pull the container from NGC ```bash docker pull nvcr.io/nvidia/cugraph/financial-fraud-training:3.0.0 ``` Requires an [NGC account and API key](https://ngc.nvidia.com). Log in first if not already authenticated: ```bash docker login nvcr.io # Username: $oauthtoken # Password: ``` --- ## Step 2 — Train the Edge Prediction (EP) model ```bash docker run --rm --gpus all --shm-size=10g \ --ulimit memlock=-1 --ulimit stack=67108864 \ -v /your/graph/data:/data:ro \ -v /your/ep/output:/workspace/output \ -v /your/config_ep.yaml:/workspace/config.yaml:ro \ nvcr.io/nvidia/cugraph/financial-fraud-training:3.0.0 ``` > **Data layout:** `/your/graph/data` must contain `nodes/` and `edges/` sub-directories following the conventions in [Data Layout](/nim/financial-fraud-training/data/data-def). Node and edge files can be CSV, Parquet, or ORC — the pipeline detects format by extension. Mask files (optional train/val/test splits) are always `.npy`. Watch for the final metrics block in the log (`AUC`, `AUCPR`, `F1`, threshold). Training takes 30–90 minutes depending on dataset size. See [Training](/nim/financial-fraud-training/training/training-guide) for config options. --- ## Step 3 — Serve the EP model Copy the full output directory before serving so the original is preserved: ```bash cp -r /your/ep/output /your/ep/output_serving ``` Start Triton (scoring only): ```bash NUM_GPUS= INSTANCES_PER_GPU= \ MODEL_REPO=/your/ep/output_serving/infer/triton/ \ bash /your/ep/output_serving/infer/serve.sh ``` **Optional — with LLM explanation:** Any OpenAI-compatible provider works (NVIDIA NIM, OpenAI, Azure OpenAI, etc.): ```bash NUM_GPUS= INSTANCES_PER_GPU= \ LLM_API_KEY="" \ LLM_BASE_URL="" \ LLM_MODEL="" \ MODEL_REPO=/your/ep/output_serving/infer/triton/ \ bash /your/ep/output_serving/infer/serve.sh ``` Example provider configurations (any OpenAI-compatible endpoint works — model names and URLs below are illustrative): | Provider | `LLM_BASE_URL` | Example `LLM_MODEL` | |----------|---------------|---------------------| | NVIDIA NIM (using `NVIDIA_API_KEY`) | *(not needed — auto-configured to `https://inference-api.nvidia.com`)* | `nvidia/meta/llama-3.2-1b-instruct` | | NVIDIA NIM (using `LLM_API_KEY`) | `https://inference-api.nvidia.com` | `nvidia/meta/llama-3.1-70b-instruct` | | OpenAI | `https://api.openai.com/v1` | `gpt-4o` | Poll until ready (usually < 2 minutes): ```bash until curl -sf http://localhost:8000/v2/health/ready >/dev/null 2>&1; do sleep 5; done echo "Triton ready" ``` --- ## Step 4 — Install client dependencies The inference clients (`client.py`, `client_np.py`, `client_saved_emb.py`, and `client_production.py`) run outside the container and communicate with Triton over gRPC. ```bash pip install "tritonclient[grpc]" pandas numpy torch # For client_production.py --serve mode (persistent HTTP service) also install: pip install fastapi uvicorn ``` `tritonclient[grpc]` must match the Triton server version. For Triton 26.04 use the version pinned to that release, or install the latest and verify the gRPC handshake succeeds. ## Step 5 — Run the EP inference client ```bash python /your/ep/output_serving/infer/client.py \ --data_path /your/graph/data/test_gnn \ --model_config /your/ep/output_serving/infer/triton/gnn_embedder/1/model_config.json \ --batch_size 512 \ --explain \ --explain_limit 10 ``` Stop the server when done: ```bash docker ps --filter "ancestor=nvcr.io/nvidia/tritonserver:26.04-py3" -q | xargs docker stop 2>/dev/null || true ``` --- ## Step 5b — (Optional) Train EP with saved node embeddings Set `save_node_embeddings: true` in your config before training to enable hybrid inference, where known nodes bypass the GNN entirely at inference time: ```yaml # In your config.yaml — models[0].hyperparameters.gnn: models: - kind: GNN_XGBoost hyperparameters: gnn: save_node_embeddings: true emb_dtype: float16 # halves disk footprint at negligible accuracy cost ``` Re-run the same docker training command. After training completes, Stage 9 runs automatically: it extracts GNN embeddings for all training nodes and saves them. The Triton export step merges rank shards into `output/node_embeddings/{type}/embeddings.mmap`. Run the hybrid inference client: ```bash python /infer/client_production.py \ --model_config /infer/triton/gnn_embedder/1/model_config.json \ --emb_dir /node_embeddings \ --data_path /data/test_gnn \ --batch_size 512 ``` Or start a persistent HTTP service: ```bash pip install fastapi uvicorn python /infer/client_production.py \ --model_config /infer/triton/gnn_embedder/1/model_config.json \ --emb_dir /node_embeddings \ --data_path /data/test_gnn \ --serve --port 8080 ``` --- ## What to check at each step | Step | Success indicator | |------|------------------| | 1 — Pull | `Status: Downloaded newer image` or `Status: Image is up to date` | | 2 — EP train | Final log line: `Training complete!` + metrics block with `AUC`, `AUCPR`, threshold | | 3 — EP serve | All 6 models show `"state":"READY"` in the startup log | | 4 — Client deps | `pip install` completes without error | | 5 — EP client | Per-batch latency printed; fraud detections listed with probabilities | If any step fails, stop and check [Troubleshooting](/nim/financial-fraud-training/supplemental/pipeline) before continuing.