数据与 AI技能

Build and operate AutoGPT agents that carry out multi-step workflows. Covers a visual editor for connecting processing blocks, scheduled and webhook triggers, deployment, execution monitoring, and benchmarks for evaluating agent performance.

中文简介正在准备中。当前显示英语简介。

• Build an AI workflow in a visual editor
• Run agents on a schedule or external event
• Add custom agent abilities with Forge

Build AI applications with LangChain, including chatbots with conversation history and systems that search documents before answering. The skill provides examples for connecting models, calling tools, retrieving information, and tracing application runs.

中文简介正在准备中。当前显示英语简介。

• Building a chatbot that uses conversation history
• Creating a question-answering system for documents
• Developing an agent that calls external tools

Adapt machine learning training to run across multiple GPUs or machines with Ray Train. Covers changes to existing code, comparing training settings with Ray Tune, and saving checkpoints so training can resume after failures.

中文简介正在准备中。当前显示英语简介。

• Adapting existing PyTorch code for multiple GPUs
• Training HuggingFace models across multiple machines
• Comparing learning rates and batch sizes with Ray Tune

Configure large language model training with NVIDIA Megatron-Core across multiple GPUs. This skill helps choose how to split computation, set training parameters, monitor GPU efficiency, and address memory limits or unstable training.

中文简介正在准备中。当前显示英语简介。

• Planning multi-GPU training for a LLaMA-style model
• Distributing MoE model experts across GPUs
• Tuning training throughput and GPU utilization

Design autonomous AI agents that break goals into tasks, use tools, and review their own work. Covers reasoning and action loops, separate planning and execution, and reliability measures such as cost limits, validation, and logging.

中文简介正在准备中。当前显示英语简介。

• Choosing how an agent plans and executes tasks
• Breaking goals into constrained steps
• Adding self-review and correction to an agent

Build data processing pipelines for machine learning, from preprocessing to batch predictions. Uses Ray Data to handle datasets larger than memory, distribute work across CPUs and GPUs, and feed data into training frameworks.

中文简介正在准备中。当前显示英语简介。

• Preprocessing datasets larger than memory
• Running batch predictions across multiple GPUs
• Preparing image and tabular data for training

Reduce LLM weight usage through pruning, which removes selected model parameters. Explore Wanda and SparseGPT for compression without retraining, choose hardware-friendly patterns for faster inference, and compare the compressed model's accuracy with the original.

中文简介正在准备中。当前显示英语简介。

• Compressing an LLM without retraining
• Comparing pruning methods
• Exploring faster inference on supported hardware

Build and train Mixture of Experts models, which activate selected specialist networks for each input. Use DeepSpeed or HuggingFace workflows to configure routing, balance workloads, distribute experts across GPUs, and optimize inference.

中文简介正在准备中。当前显示英语简介。

• Designing MoE models for a limited compute budget
• Implementing Mixtral-style expert routing
• Adjusting expert workloads and training stability

Design memory systems that help AI assistants retain conversation information and retrieve it when relevant. Explore short-term, long-term, and entity memory, along with memory consolidation, prompt integration, storage lifecycle management, and separation between users.

中文简介正在准备中。当前显示英语简介。

• Designing an assistant that remembers across conversations
• Storing and updating facts about people or other entities
• Adding relevant memories to prompts

Design AI agents that plan tasks, call tools, and retain useful information. Covers coordination between agents, evaluation, and debugging, with practical patterns for execution limits, error handling, and tracing what an agent does.

中文简介正在准备中。当前显示英语简介。

• Designing an agent that plans and executes tasks
• Organizing tool definitions and selection
• Deciding what an agent should remember

Combine capabilities from multiple fine-tuned LLMs without retraining using mergekit. Choose a merging method, configure how models are blended, and evaluate the resulting model on tasks such as math, code generation, and conversation.

中文简介正在准备中。当前显示英语简介。

• Combining math, coding, and conversation capabilities
• Blending two models at different ratios
• Comparing variants made with different merging methods

Organize PyTorch training code with LightningModule and Trainer. Follow examples for validation, logging, model saving, and distributed training across multiple GPUs, with callbacks that add monitoring or stop training when progress stalls.

中文简介正在准备中。当前显示英语简介。

• Converting an existing PyTorch training loop
• Adding validation, logs, and model checkpoints
• Configuring training across multiple GPUs

Extend the amount of text a language model can process at once. Compares RoPE, YaRN, ALiBi, and position interpolation, with implementation examples, additional training guidance, and memory optimization approaches for long document processing.

中文简介正在准备中。当前显示英语简介。

• Extend an existing model to handle longer inputs
• Compare methods for representing token positions
• Plan additional training with long documents

Build collaborating AI teams with CrewAI by defining roles, tasks, and shared context. Configure ordered execution or manager-led delegation, add memory and tools, and create workflows that branch based on events or results.

中文简介正在准备中。当前显示英语简介。

• Build a research-to-writing agent workflow
• Coordinate specialists through a manager agent
• Create workflows with conditional branches

Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.

中文简介正在准备中。当前显示英语简介。

• Clean web data for model training
• Remove exact and near duplicates from large text collections
• Redact personal information from training text

Design memory systems that help AI agents retrieve relevant past information. Choose short-term and long-term memory structures, compare vector storage options, and review document splitting and retrieval strategies for different kinds of knowledge and experience.

中文简介正在准备中。当前显示英语简介。

• Design memory for information used across conversations
• Choose storage for experiences, facts, and procedures
• Review retrieval when an agent misses saved information

Build LlamaIndex applications that retrieve relevant material before generating answers, a method called RAG. Connect documents, websites, and databases to support document questions, conversational search, structured summaries, and checks of answer relevance and source consistency.

中文简介正在准备中。当前显示英语简介。

• Building question answering over internal documents
• Creating a chatbot that remembers the conversation
• Searching information across files, websites, and databases

Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.

中文简介正在准备中。当前显示英语简介。

• Reducing chatbot response latency
• Comparing methods for faster code generation
• Selecting a small draft model for a larger LLM

Design collaborative AI teams with CrewAI by defining each agent’s role, goals, tasks, and expected results. Covers passing work between agents, manager-led coordination, memory settings, and execution planning for workflows such as research and writing.

中文简介正在准备中。当前显示英语简介。

• Build a team that researches and writes articles
• Coordinate specialists through a manager agent
• Define agent roles and expected task outputs

Connect a company SQL database, support ticket exports, and documents in cognee, linking shared people, teams, and projects so questions about ownership, decisions, and ongoing work can draw on several sources together.

中文简介正在准备中。当前显示英语简介。

• Finding owners across company databases, tickets, and documents
• Tracing decisions across multiple company sources
• Checking who is handling a support issue

Connect cognee to model providers, databases, storage services, and development tools. Guides configuration of language models and embeddings, the numerical representations used for search, including the separate settings each requires.

中文简介正在准备中。当前显示英语简介。

• Switching model providers or using Ollama locally
• Connecting cognee to Postgres or Neo4j
• Storing cognee data in S3

Import text, files, URLs, repositories, and database content into cognee memory. This skill explains input handling, storage organization, extraction options, and cost estimates, while helping diagnose unsupported arguments and document update errors.

中文简介正在准备中。当前显示英语简介。

• Importing documents, URLs, or database content
• Organizing stored information by project or topic
• Estimating tokens and cost before importing

Query documents and conversations stored in cognee to retrieve answers, supporting passages, or context for an AI model. This skill guides search method selection, source filtering, result interpretation, and troubleshooting empty or unexpected results.

中文简介正在准备中。当前显示英语简介。

• Searching selected datasets or conversation sessions
• Retrieving supporting passages or model context
• Choosing a search method for a question

Tune cognee ingestion speed, query response time, and LLM costs by adjusting concurrency, text chunk sizes, request limits, and model choices. Estimate ingestion costs before processing and assess options for background work and deployment scaling.

中文简介正在准备中。当前显示英语简介。

• Estimating costs before importing documents
• Adjusting ingestion speed and request limits
• Reducing query response time