skills.rest
Jensen-Yao
Jensen-YaoCOMMUNITY
Explore all skills by this author →
GitHub

llamaindex

Build RAG pipelines with document ingestion, vector indices, and query engines.

2|Updated Aug 15, 2026
Search Tags:#knowledge retrieval#llm#rag#document ingestion#vector index#llamaindex#query engine
One-click install
npx skills add https://github.com/Jensen-Yao/agents-skills --skill llamaindex-jensen-yao
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llamaindex
Source: https://github.com/Jensen-Yao/agents-skills/tree/main/skills/llamaindex
Command: npx skills add https://github.com/Jensen-Yao/agents-skills --skill llamaindex-jensen-yao

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires llama-index, openai, anthropic, and includes references (resource) components.

What problem does it solve? Connecting LLMs to private data for question-answering requires building ingestion, indexing, and retrieval infrastructure from scratch, which is time-consuming and error-prone. ## Core Features & Use Cases - Document Ingestion: Load data from 300+ connectors including files, web pages, GitHub, databases, and APIs. - Indexing & Querying: Create vector, list, and tree indices, then query them with configurable response modes, streaming, and metadata filtering. - Agents & Chat Engines: Build agents that combine RAG tools with custom functions, or conversational chat engines with memory. - Use Case: Build a chatbot that answers questions over your company's internal documentation by loading a folder of PDFs and Markdown files into a vector index and querying it with natural language. ## Quick Start Use the llamaindex skill to build a RAG pipeline that answers questions over the documents in my ./data folder.

Frequently Asked Questions about llamaindex

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a RAG application with LlamaIndex?▼

Load documents with SimpleDirectoryReader, create a VectorStoreIndex from them, and call index.as_query_engine() to query with natural language. The whole pipeline takes about five lines of Python code.

LlamaIndex vs LangChain for document Q&A?▼

LlamaIndex is purpose-built for RAG with 300+ data connectors and a simpler document Q&A API. LangChain is more general-purpose and better suited for complex multi-step agents and workflows.

Does LlamaIndex support vector databases like Pinecone and Chroma?▼

Yes, LlamaIndex integrates with Chroma, Pinecone, FAISS, and other vector stores through StorageContext. Pass the vector store when creating the index to persist embeddings externally.

How do I add memory to a LlamaIndex chatbot?▼

Use index.as_chat_engine() with chat_mode set to condense_plus_context, which condenses chat history and retrieves relevant context for each turn. Call chat_engine.reset() to clear the conversation.

Why is my LlamaIndex query returning irrelevant answers?▼

Low-quality retrieval usually comes from poor chunking or too few retrieved nodes. Increase similarity_top_k, add a reranker postprocessor like SentenceTransformerRerank, or apply metadata filters to narrow results.

Related Skills

Explore More Software Engineering Skills→
qodex-aiqodex-ai
39

workspace-documentation

Capture and structure conversation knowledge into Notion wikis, databases, and knowledge graphs.

Official
Intermediate
a-church-aia-church-ai
19

ask-church

Query aChurch.ai's knowledge base to generate source-cited answers via the /api/ask endpoint.

Official
Intermediate
adriancodesadriancodes

ecc-rag-pipeline-reviewer

Reviews RAG retrieval pipelines for context relevance, citations, tenant isolation, and evaluation gaps.

Community
Intermediate
qcmuuqcmuu

haystack

Build RAG search pipelines with retrievers, rerankers, and generators.

Community
Intermediate