Choose this when
You need document search, support answers, internal knowledge tools, research assistants, or grounded chat.
All learning paths
AI learning path
RAG and knowledge systems
Build AI systems that answer from your knowledge base instead of improvising from memory.
- Best for
- Developers building AI apps
- Level
- Intermediate
- Time
- 10-18 hours
You should be able to
You can design ingestion, chunking, retrieval, reranking, citation, and answer-quality checks.
Checkpoint
Move on when you know whether failure came from ingestion, retrieval, context, or generation.
Do
Learning sequence
This is the route through the topic. Watch and open the material inside the step where it is used.
Step 1
Model the knowledge
Decide what the system knows, where it comes from, and how freshness matters.
- Sources
- Metadata
- Freshness
Watch here
RAG and LlamaIndex
LlamaIndex
Start here for documents, retrieval, and grounded app structure.
Open here
OpenAI Retrieval guide
Guide · OpenAI · Intermediate
You need the official path for file search, retrieval, and grounded answers before designing a RAG stack.
Open resourceStep 2
Retrieve the right context
Experiment with chunks, embeddings, filters, rerankers, and query rewriting.
- Chunking
- Embeddings
- Reranking
Watch here
Pinecone semantic search
Pinecone
Use this when working through embeddings and retrieval behavior.
Vector search and Weaviate
Weaviate
A second retrieval perspective for vector search and hybrid search.
Open here
Cohere LLM University
Free course · Cohere · Beginner to intermediate
You want a structured, practical course path for LLM and RAG concepts from Cohere.
Open resourceStep 3
Ground the answer
Make citations, refusal behavior, and eval questions part of the product.
- Citations
- Abstention
- Evals
Open here
LlamaIndex Docs
Docs and examples · LlamaIndex · Intermediate
You need to connect LLMs to documents, data, and retrieval.
Open resourcePinecone Learn: Retrieval-Augmented Generation
Guide · Pinecone · Beginner to intermediate
You need to understand the moving parts of RAG.
Open resourcePractice task
Build a tiny Q&A system over 10-20 documents and collect five questions it gets wrong.
Reference
All resources in this path
Step 1
OpenAI Retrieval guide
Guide · OpenAI · Intermediate
You need the official path for file search, retrieval, and grounded answers before designing a RAG stack.
Step 2
Cohere LLM University
Free course · Cohere · Beginner to intermediate
You want a structured, practical course path for LLM and RAG concepts from Cohere.
Step 3
LlamaIndex Docs
Docs and examples · LlamaIndex · Intermediate
You need to connect LLMs to documents, data, and retrieval.
Step 3
Pinecone Learn: Retrieval-Augmented Generation
Guide · Pinecone · Beginner to intermediate
You need to understand the moving parts of RAG.
Educators to follow
Jason Liu
Intermediate
Try the Instructor examples for extraction and validation.
View educator
Jerry Liu
Intermediate
Read the LlamaIndex introduction, then build a small document Q&A app.
View educator
Hamel Husain
Intermediate to advanced
Read the evals guide and build a small test set for your own app.
View educator
Eugene Yan
Intermediate to advanced
Read the applied ML and LLM systems posts.
View educator
Brian Casel
Beginner to intermediate
Look for workflow breakdowns and implementation examples.
View educator
Ethan Mollick
Beginner to advanced
Read recent essays on using AI as a collaborator and on organizational adoption.
View educator