데이터·AI 스킬

Build and solve routing problems in Python with cuOpt, including delivery fleets, round trips, and pickup-delivery tasks. Define vehicle capacities, arrival windows, and visit order constraints, then inspect routes, total cost, and orders that cannot be served.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Calculate delivery routes with vehicle capacity limits
• Plan visits within specified arrival windows
• Define pickup-delivery pairs and visit order

Design protein backbones, the structural framework of proteins, with RFDiffusion through NVIDIA NIM. Generate new structures, build around existing structural motifs, or design binders, then save PDB files for subsequent amino acid sequence design.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generating a new protein backbone
• Building a backbone around an existing structural motif
• Designing a binder around specified target residues

Move pandas-style table processing to NVIDIA GPUs using cuDF. Choose minimal-change acceleration or explicit GPU code, handle joins and aggregations, compare results with pandas, and use dask-cuDF when data exceeds GPU memory.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Accelerate existing pandas processing with minimal changes
• Move joins and aggregations to GPU code
• Compare missing values and ordering with pandas

Fine-tune Parakeet TDT v2 on clinical vocabulary using NeMo, then compare key-term error rates before and after training. The results guide whether to keep the model, expand the dataset, or prepare it for deployment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reducing transcription errors in medication names
• Checking whether training improved clinical term recognition
• Deciding whether to expand the training dataset

Build English clinical speech-recognition benchmarks by selecting medical terms, checking pronunciations, and generating synthetic audio. Outputs include audio files and a NeMo manifest, a structured file listing recordings and metadata, ready for a separate scoring stage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a speech-recognition benchmark for a clinical specialty
• Checking synthesized pronunciations of drug and procedure names
• Generating evaluation audio across voices, noise, and contexts

Turn molecules listed in a SMILES CSV into numerical feature vectors using a KERMT model. The workflow checks the model and input, cleans molecular notation, and saves four sets of vectors with validity information.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extract molecular feature vectors from a SMILES CSV
• Reuse a local KERMT checkpoint
• Extract features with a released pretrained model

Model and solve optimization problems with cuOpt through Python, C/C++, or the command line. Choose linear, mixed-integer, or quadratic methods based on the decisions involved, configure stopping limits, and investigate infeasible or unbounded results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Modeling resource allocation problems
• Representing whole-number and yes/no decisions
• Minimizing squared error or variance

Predict biomolecular structures and estimate how strongly a ligand binds using Boltz2 NIM. Submit proteins, DNA, RNA, and ligand inputs through NVIDIA's hosted API or local Docker, then save structures and inspect confidence and affinity scores.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Predicting protein structures and DNA or RNA complexes
• Providing ligand inputs with SMILES or CCD identifiers
• Estimating binding affinity for one ligand

Create a Python configuration for generating synthetic datasets with the Data Designer library. Describe the data you need, then refine requirements interactively or let the agent choose assumptions and assemble the generation pipeline.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a synthetic dataset from a written description
• Generate person data such as names and addresses
• Produce data that follows a specific schema

Extend an existing grover_base model with a new decoder that reconstructs molecular structure strings, then continue pretraining on your corpus. The workflow validates inputs, rebuilds vocabulary components, and records the conversion and training outputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extend an existing grover_base model with cMIM
• Continue pretraining on a molecular corpus
• Trace checkpoint conversion and training records

Turn written planning problems into mathematical optimization models. Separate fixed inputs, constraints, decisions, and objectives, then choose linear, mixed-integer, or quadratic formulations for tasks such as production planning, inventory management, and material allocation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Formulate production plans with capacity and cost constraints
• Model inventory limits across purchasing and sales periods
• Define multiple goals in priority order

Fine-tune a pretrained KERMT model on a CSV of molecular structures and labeled targets. The workflow checks inputs, prepares features, launches training in a container, and saves trained models, logs, and test results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a molecular model on labeled CSV data
• Select specific prediction targets for training
• Reuse prepared data to compare training settings

Build DeepStream commands for image and video inference, object detection, tracking, and streaming. The skill asks about missing requirements, assembles a GStreamer processing pipeline, and checks its syntax, components, properties, and connections where supported.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a pipeline for inference on local images or video
• Detect and track objects across multiple RTSP streams
• Save processed output to an MP4 file

Generate small-molecule candidates from a starting structure, optimize supported molecular properties, and save results for validation. Local deployment also supports embeddings, numerical representations of molecules, and workflows that convert between molecular structures and learned internal representations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate molecular candidates around a seed structure
• Optimize candidates for QED or plogP
• Obtain molecular embeddings with a local deployment

Predict structures of proteins, DNA, RNA, and complexes with small molecules using OpenFold3. Guides hosted API requests or local Docker setup, saves structure files, and helps interpret confidence scores supplied with the predictions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Predicting protein structures through the hosted API
• Predicting complexes with DNA, RNA, or small molecules
• Setting up local inference with Docker

Generate molecular predictions from a CSV of SMILES strings, a text notation for molecular structures, using a finetuned KERMT model. Validate inputs, clean data, compute molecular features, and return predictions with execution logs and a replay command.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Predict targets for molecules listed in a SMILES CSV
• Check whether a saved model is suitable for inference
• Reuse prepared data for another prediction run

Explore competing goals such as cost and service quality through repeated cuOpt solves. Organize efficient alternatives into a Pareto frontier, a set of tradeoff choices, and explain what each improvement costs in another objective.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare cost and service quality
• Explore return and risk tradeoffs
• Compare delivery distance and vehicle count

Pretrain a new KERMT chemistry model from a molecular corpus, starting with random weights. The skill validates the data, builds fresh vocabularies, estimates runtime, and launches containerized training with logs and records for reproducing the run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a new model on a specialized chemistry corpus
• Run pretraining without an existing checkpoint
• Choose a training objective and batch size

Continue training a KERMT molecular model on a custom SMILES corpus, where text strings describe molecular structures. The skill validates data and checkpoints, prepares training inputs, and launches containerized training with saved logs and checkpoints.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continue molecular model pretraining on a custom SMILES corpus
• Start additional training with a new learning-rate schedule
• Resume an interrupted training run from a saved checkpoint

Monitor KERMT jobs running in the background by reading run records, Docker container status, and logs. Summarize training progress and validation metrics, stream logs, or report final test metrics when a finetune run completes successfully.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check progress on a background pretraining run
• Watch training logs and validation metrics live
• Review test metrics after finetuning completes

Generate DNA sequences with NVIDIA Evo 2, check their length and alphabet, and save sequence files alongside probabilities and timing metrics. A local deployment also supports extracting numerical outputs from selected internal model layers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate DNA from a starting sequence
• Save generated sequences and metrics
• Extract internal layer outputs from a local model

Write and debug nvMolKit Python code for processing large molecule batches on GPUs. Covers molecular fingerprints, compact representations of molecular features, plus similarity calculations, 3D conformer generation, optimization, clustering, and molecular searches using RDKit objects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Calculate fingerprints and similarities for large molecule libraries
• Generate and optimize batches of molecular conformers
• Cluster conformers by differences in their 3D structures

Integrate a supported object detection model from HuggingFace or NVIDIA NGC into NVIDIA DeepStream. Automates model acquisition and conversion, TensorRT engine building, detection output parsing, multi-stream performance benchmarks, and reports with charts in Markdown, HTML, and PDF.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Run the default RT-DETR model in DeepStream
• Integrate a supported HuggingFace or NVIDIA NGC detection model
• Compare performance across multiple video streams

Calibrate live cameras by recording their RTSP video streams through VIOS and processing the clips with AutoMagicCalib. The workflow imports settings and alignment files, checks readiness, tracks calibration progress, and retrieves results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Calibrate cameras from live RTSP streams
• Import settings and alignment files for a camera scene
• Retrieve evaluation statistics using ground truth data