llamaindex - Build RAG applications with LlamaIndex
Build LLM applications that ingest documents, create indexes, retrieve knowledge, answer questions, and use agents or multimodal data.
Tags
Updated: 2026-09-28Typical Inputs
Typical Outputs
What this skill does
- Ingest documents
- Create vector indexes
- Query indexed data
- Retrieve relevant chunks
- Build tool agents
- Run conversational chats
- Filter by metadata
- Generate structured outputs
- Connect vector stores
Inputs
- Documents
- Web URLs
- Database queries
- API endpoints
- User questions
- Metadata filters
- Agent tools
- LLM provider credentials
Outputs
- Query responses
- Chat responses
- Retrieved document chunks
- Persisted indexes
- Structured data
- Vector store records
Requirements
- Python environment
- llama-index package
- OpenAI or Anthropic integration packages
- Access to an LLM provider