skills.rest
Orchestra-Research
Orchestra-ResearchOFFICIAL
Explore all skills by this author →
GitHub

llamaindex

Build RAG pipelines for document ingestion, indexing, and querying.

11.5k|842|Updated Nov 3, 2025
Search Tags:#knowledge retrieval#rag#vector database#data ingestion#llamaindex#llm applications
One-click install
npx skills add https://github.com/Orchestra-Research/AI-Research-SKILLs --skill llamaindex-orchestra-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llamaindex
Source: https://github.com/Orchestra-Research/AI-Research-SKILLs/tree/main/14-agents/llamaindex
Command: npx skills add https://github.com/Orchestra-Research/AI-Research-SKILLs --skill llamaindex-orchestra-research

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill bridges the gap between Large Language Models (LLMs) and your private data, enabling them to understand and act upon information not present in their training sets.

Core Features & Use Cases

  • RAG Pipelines: Build Retrieval-Augmented Generation systems to answer questions based on your documents.
  • Document Ingestion: Load data from over 300+ sources using built-in and community connectors.
  • Vector Indexing: Structure your data for efficient semantic search and retrieval.
  • Agent Framework: Create agents that can use tools and interact with your data.
  • Use Case: You have a large internal knowledge base in Notion. Use this Skill to build a chatbot that can answer employee questions by searching and synthesizing information directly from Notion.

Quick Start

Use the llamaindex skill to load documents from the 'data' directory and create a query engine to answer questions about them.

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 pipeline to answer questions from my private documents?▼

To build a RAG pipeline, you load documents from your private sources, index them into a vector database, and use a query engine to retrieve and synthesize answers from your data.

Can I load and ingest data into my LLM application from external sources like Notion?▼

Yes, you can ingest data from external sources like Notion using over 300 built-in and community connectors, allowing your LLM application to access and act upon private information.

What is the best way to connect an LLM to my internal knowledge base for semantic search?▼

The best way to connect an LLM to an internal knowledge base is using a data framework that structures your data into vector indices, enabling efficient semantic search and retrieval.

Does this framework support building agents that can interact with my ingested data?▼

Yes, the framework includes an agent framework that allows you to create agents capable of using tools and interacting directly with your ingested data.

How do I handle multimodal input when building data-centric LLM applications?▼

You can handle multimodal input by using the framework's data ingestion and indexing capabilities, which support multimodal input to build comprehensive data-centric LLM applications.

Related Skills

Explore More Software Engineering Skills→
angryracoonangryracoon

data360-prepare

Prepare Salesforce Data Cloud ingestion assets for raw source data.

Community
Advanced
ovachieverovachiever
52

llamaindex

Ingest documents from 300+ connectors into vector indices for retrieval-augmented generation.

Community
Advanced
maruakshaymaruakshay
4

embedding-attack-security

Enforce validation and access controls to protect vector databases from embedding attacks.

Community
Advanced
christian-bromannchristian-bromann
3

langchain-document-loading

Load and structure documents from PDFs, websites, and text files for RAG.

Community
Intermediate