233 skills · sorted by relevance
Build document search with Chroma, a database that stores text as numerical representations of meaning. Save and update documents, filter by metadata, and connect retrieval to AI applications using LangChain or LlamaIndex.
Train and evaluate RuView models using Wi-Fi measurements for pose estimation, retrieval, and adaptation to different environments. Follow laptop or GCloud GPU workflows, then package and publish trained models to Hugging Face.
Represent dependency trees, taxonomies, and other hierarchies inside a Poincare ball, a geometric model for hierarchical distances. Use tree depth for radius and text embeddings for direction, then measure distances to examine the encoded structure.
Convert chat messages into template strings for local model runtimes such as Ollama or llama.cpp. Optionally route queries among a few registered intents using embeddings, numerical representations of meaning, without calling a model.
Convert text, code, or documents into 384-dimensional vectors, numerical representations used for meaning-based search, similarity comparison, and clustering. Save vectors to files, check their dimensions and magnitude, and optionally record metadata in AgentDB.
Reduce data with many features into fewer dimensions using UMAP. Create 2D or 3D views, prepare inputs for clustering, compare parameter settings, and project new samples while checking whether the results remain stable and meaningful.
Turn small-molecule structures into numerical features for similarity searches and models that predict activity or properties. Using Molfeat, the skill covers representation choices, invalid inputs, alignment with experimental labels, and saving feature-generation settings for reuse.
Use Biohub’s Python SDK to complete protein sequences with ESM3, extract numerical sequence representations with ESMC, and predict all-atom structures with ESMFold2. The skill guides local or hosted inference, input validation, and output checks.
Query public single-cell and spatial gene expression data by tissue, disease, or cell type. Retrieve selected expression values, cell metadata, and summary counts for analysis and comparisons across datasets without first downloading entire collections.
Help implement Azure OpenAI features in C# and .NET applications using SDK examples. Cover authentication, chat, document-backed answers, image generation, and audio processing, including transcription and speech generation.
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Includes PyTorch and TensorFlow logging examples for examining weight distributions, predictions, and performance bottlenecks during machine learning training.
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.
Extract references between imported documents and classify how they relate, such as relying on, extending, or refuting another work. Store these relationships as typed links so explicit graph queries can trace connections through the collection.
Generate a client in your chosen language for live, two-way communication with Gemini Enterprise LiveAPI. Includes token renewal, session recovery, tests, and a demo interface for trying text, audio, video, and transcription.
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
Design and implement RAG systems, which retrieve documents to inform AI answers. Get document preparation strategies, vector database comparisons, combined keyword and meaning-based search, result reranking, and an evaluation plan for retrieval quality.
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
Add AI chat, text generation, and agents to applications using AI SDK. The skill checks documentation and source code to guide streaming replies, external tool calls, structured results, React integration, and fixes for outdated API usage.
Use scGPT to convert single-cell gene expression data into numerical representations of cells and genes. These representations support clustering, data integration, cell-type annotation, and analyses of gene perturbations or regulatory relationships.
Convert protein sequences into numerical features with Meta AI's ESM-2 for machine learning. Extract features for individual amino acids or whole sequences, score mutations, and predict which positions in a protein may contact each other.
Predict structures of protein, nucleic acid, and small-molecule complexes with ESMFold2, using single sequences or aligned related sequences. The skill also covers ESMC models for numerical sequence representations, mutation scoring, and predictions of contacts between residues.
Find and run over 2,000 AI models and API tools through one MCP connection, a shared interface for agents. Inspect inputs and pricing before generating media, searching the web, or retrieving structured and social data.
Prepare research papers for RAG, a method that supplies retrieved documents to AI. Download PDFs, extract and split text, and build a local searchable database, with parallel processing for document batches.
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.
The English summary is being prepared. Showing the original description.