Browse skills

Generates OpenAI embeddings from text data using grepai's infrastructure for efficient vector representation and similarity search.

Fine Tuning Serving Openpi — provides AI agent assistance for software development workflows.

This skill integrates Upstash with Vector DBs for efficient similarity search and retrieval of vector embeddings, boosting AI applications.

Provides LLMs guidance and assistance for software development workflows.

Automatically expands limited training data with synthetic examples generated from web searches, boosting model accuracy.

This skill leverages vector databases to efficiently store and search semantic similarity between data points, enabling powerful retrieval-based AI applications.

Helps with AI, search, optimization as part of agent workflows workflows.

Serves LLMs like VLLM efficiently for experimentation and deployment, streamlining development workflows and scaling AI applications.

Provides LLMs guidance and assistance for building AI and machine learning applications.

Davila7's perplexity-search analyzes text to identify confusing or unclear passages needing clarification or rephrasing.

Prompt Guard filters potentially harmful or irrelevant prompts, ensuring safer and more focused AI interactions for improved results.

This skill automatically converts documents into vector datasets, streamlining data preparation for semantic search and AI applications.

This skill optimizes large language model performance by reducing model precision (bitsandbytes) for faster inference and lower memory usage.

This skill trains large language models like Megatron using orchestra-research techniques for enhanced performance and customization.

Automates vector database creation and configuration, streamlining data storage and similarity search workflows.

This skill generates Google Gemini embeddings for your text data, enabling semantic search and powerful AI applications like similarity analysis.

Analyzes Gemini web search results to identify potential risks, threats, and vulnerabilities related to specified topics.

LlamaCpp enables running Meta’s LLaMA language model locally using C++, offering efficient inference and privacy without internet dependency.

This skill assesses LLM harnesses for performance and efficiency, helping users optimize their AI workflows and select the best models.

This skill streamlines LLM integration (like ChatGPT) into your workflows, boosting automation and content generation capabilities.

Generates high-quality embeddings using GrepAI and Ollama for semantic search, similarity analysis, and knowledge graph construction.

Provides search guidance and assistance for software development workflows.

Quickly retrieves relevant data from a vector database using semantic search queries for enhanced insights.

Generates vector representations (embeddings) of text, enabling semantic similarity searches and powerful AI applications like clustering & recommendation.