Ingest documents from 300+ connectors into vector indices for retrieval-augmented generation.
npx skills add https://github.com/ovachiever/droid-tings --skill llamaindex
Please help me install this Agent Skill. Skill: llamaindex Source: https://github.com/ovachiever/droid-tings/tree/main/skills/llamaindex Command: npx skills add https://github.com/ovachiever/droid-tings --skill llamaindex
This Skill provides a complete data framework for building LLM-powered apps with retrieval augmented generation, document ingestion, indices, and agents.
Create a VectorStoreIndex from documents, then query with a simple engine for robust Q&A over private data.
High-intent search queries and answers about installing and using this skill.
Retrieval-augmented generation (RAG) combines document ingestion with LLM queries to answer questions over private data. LlamaIndex provides 300+ connectors to ingest documents, vector indices to store embeddings, and query engines to retrieve context and generate answers without retraining your model.
Yes. LlamaIndex supports 300+ data connectors for multi-source ingestion—databases, APIs, cloud storage, and file formats. Documents are loaded, indexed into vector or other index types, then queried through a single unified interface for consistent retrieval across all sources.
Vector indices use embeddings for semantic similarity search; list indices scan documents sequentially with LLM refinement; tree indices build hierarchical summaries for recursive retrieval. Choose based on query complexity, latency requirements, and whether you need dense or sparse matching across your ingested documents.
Agents in LlamaIndex integrate tools and query engines to automate multi-step workflows. Define tools, attach them to an agent, and let the agent decide which tools to call based on user queries. Combined with vector indices, agents enable intelligent Q&A, routing, and decision-making over your private documents.
Yes. LlamaIndex includes multimodal tools and data flows to ingest and index both text and images. Multimodal indices and query engines retrieve context from mixed-format documents, enabling applications like visual Q&A and document understanding across diverse data types.
Yes. LlamaIndex is designed for document-based chatbots and knowledge retrieval systems. Ingest your documents with multi-source connectors, index them with vector or other indices, then build a query engine or agent to power conversational Q&A with retrieved context and private data governance.
nrakowSelect and configure data ingestion strategies for Fivetran, Airbyte, or custom pipelines.
KaranKathur06Create coordinated analytics dashboards with KPI cards, charts, tables, and shared filters.
Sumeet138Integrate retrieval-augmented generation workflows with vector databases and embeddings.
smith-hornPerform vector-based semantic search over document collections with AgentDB.
