A Hands-on Practical Guide to LlamaIndex

Prerequisites:

Familiarity with Python programming language
Set up a Google Colab account if you don’t have one already
Set up an OpenAI API key if you don’t have one already

Course Outline:

Each section will be accompanied by a set of slides and a Colab notebook walk-through corresponding to each subsection. There will be a total of 10 Colab notebooks, two for each section. We will select one notebook for each section to dive into the details during the class, and leave the other notebook in the same section to the homework so students can take their time to practice in their Colab notebooks.

Check out the slides used during this course.

Query Engines

SubQuestionQueryEngine
RouterQueryEngine

Data Agents

ReAct Agent
OpenAI Agent

Evaluation (Evaluation-Driven Development)

Evaluation for LLMs
Evaluation for retrieval strategies

Fine-tuning

Fine-tune GPT-3.5
Fine-tune open source embedding model

LlamaPacks

Neo4j query engine pack
Llama Guard moderator pack

Sample RAG pipeline deployment

References

To learn more about LlamaIndex, refer to the official LlamaIndex documentation:

You are also welcome to check out my list of Medium blog posts on LlamaIndex and LLM application development.

wenqiglantz/hands-on-llamaindex