Плагин llm-application-dev

Что внутри llm-application-dev

14 частей прочитано из файлов самого плагина.

Навыки в llm-application-dev

1. 
   embedding-strategieswshobson/agents

   Select and optimize embedding models, chunking strategies, and pipelines for semantic search and RAG applications.

   2 файла
   42,4 тыс.звёзд
2. 
   langchain-architecturewshobson/agents

   Design and implement LLM applications using LangChain 1.x and LangGraph for agent orchestration, state management, and tool integration.

   2 файла
   42,4 тыс.звёзд
3. 
   llm-evaluationwshobson/agents

   Implement evaluation strategies for LLM applications using automated metrics, human feedback, and LLM-as-a-judge techniques.

   2 файла
   42,4 тыс.звёзд
4. 
   prompt-engineering-patternswshobson/agents

   Apply advanced prompt engineering patterns to optimize LLM performance, reliability, and controllability through structured reasoning and few-shot learning.

   10 файлов
   42,4 тыс.звёзд
5. 
   hybrid-search-implementationwshobson/agents

   Combines vector similarity and keyword-based search to improve retrieval accuracy in RAG systems and search engines.

   2 файла
   42,4 тыс.звёзд