Using LlamaIndex for building Generative AI apps

on YouTube ↗42m

" summary

LlamaIndex presents a concrete pipeline: 70+ data connectors to ingest files, APIs and databases, a vector store index (compatible with Pinecone, Chroma, etc.) and list/tree/index composition for heterogeneous corpora, plus a response synthesis (create-and-refine, tree-summarize/map-reduce) layer. Demos show semantic search, summarization, text-to-SQL and multi-step query decomposition working end-to-end; an evaluation module flags hallucinations by checking answers against retrieved sources. Notes on costs and trade-offs: large-context GPT‑4 queries cost significantly (example ~$2 per 32k tokens) and multi-step decomposition adds ~0.1–1s latency per extra LM call.

AI-written summary · about

" chapters (21)

1. 0:000:02:07 Intro
2. 2:070:03:17 Context setting
3. 3:170:05:38 Paradigms for inserting knowledge
4. 5:380:06:29 Challenges for in-context learning
5. 6:290:10:01 About LlamaIndex
6. 10:010:11:00 Data Connectors
7. 11:000:12:14 Data Indices + Query Interface
8. 12:140:14:23 Vector Store Index
9. 14:230:15:21 List Index
10. 15:210:17:08 Response Synthesis
11. 17:080:20:14 Composing a graph
12. 20:140:21:30 Use Case: Semantic Search
13. 21:300:22:28 Use Case: Summarization
14. 22:280:24:20 Use Case: Text-to-SQL
15. 24:200:26:51 Use Case: Synthesis over Heterogeneous Data
16. 26:510:28:12 Use Case: Compare/Contrast Queries
17. 28:120:31:35 Use Case: Multi-Step Queries
18. 31:350:35:33 Integration into downstream apps
19. 35:330:36:12 Resources
20. 36:120:38:57 Evaluation Model
21. 38:570:41:49 Q/A + Conclusion

" related talks

• 25mA Deep Dive Into Retrieval-Augmented Generation with LlamaIndexLaurie Voss · AI.dev: Open Source GenAI & ML Summit North America 2023
• 27mAI Demystified Unveiling the Intelligence Behind the MachineSathrukkan Kandasamy · Great International Developer Summit 2024
• 29mUsing LangChain and LlamaIndex to customize LLMs...Bassem Yacoube · Scale By the Bay 2023
• 36mBuilding & Deploying LLM AppsMax Pumperla · PyData Eindhoven 2023
• 35mAdvanced RAG Techniques with LlamaIndexPierre-Loic Doulcet · AI_dev: Open Source GenAI & ML Summit Europe 2024
• 55mBuild enterprise generative AI apps using Llama 3 at 1,000 tokens/s on the SambaNova AI platformVarun Badrinath Krishna, Petro Junior Milan · AI Engineer World's Fair 2024
• 01h 30mUsing LLMs to improve your Search EnginePattaniyil, Ravi, Zengin · PyData Global 2023
• 26mUsing LlamaIndex to Build an Open-Source NotebookLM AlternativeTuana Celik · Open Agent Summit 2025