LlamaIndex
技能 已验证 活跃Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal support. Use for document Q&A, chatbots, knowledge retrieval, or building RAG pipelines. Best for data-centric LLM applications.
To enable users to build robust LLM applications that leverage their own data through Retrieval-Augmented Generation, offering specialized tools for document ingestion, indexing, and querying.
功能
- Document ingestion from 300+ connectors
- Data indexing and querying capabilities
- Support for vector indices
- Integration with query engines and agents
- Multi-modal RAG support
使用场景
- Building RAG applications
- Document question-answering over private data
- Creating knowledge bases for LLMs
- Building chatbots with enterprise data
非目标
- Serving as a general-purpose agent framework without a RAG focus
- Replacing a vector database directly (integrates with them)
- Providing a UI for end-users (focuses on developer framework)
实践
- RAG implementation
- Data ingestion
- Vector indexing
- LLM application development
先决条件
- Python 3.8+
- pip package manager
- API keys for LLMs (e.g., OpenAI, Anthropic) if used
安装
请先添加 Marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skills质量评分
已验证类似扩展
LangChain
99Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
Embedding Strategies
100Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
Dspy
99Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming
Langchain Framework
99LangChain LLM application framework with chains, agents, RAG, and memory for building AI-powered applications
Hybrid Search Implementation
98Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
Init
100创建或优化存储库的 AGENTS.md 文件，提供最少、高信号的说明，涵盖代理无法从代码库推断的不可发现的编码约定、工具怪癖、工作流偏好和项目特定规则。在为新存储库设置代理说明或 Claude 配置时，当现有的 AGENTS.md 文件过长、通用或过时，当代理反复犯可避免的错误，或当存储库工作流发生变化且需要修剪代理配置时使用。应用可发现性过滤器—省略 Claude 可从 README、代码、配置或目录结构中学到的任何内容—并应用质量门，以验证每行是否仍然准确且具有操作意义。