AWSListed
AWS Training
AWS Generative AI Learning Plan
For: Engineers at AWS-stack companies
Intermediate · ~20-40 hours (modular) · Free
AWS Generative AI Learning PlanvsVector Databases: from Embeddings to Applications
Side-by-side comparison on level, duration, pricing, instructor, tier. Editor verdict on which course wins for which buyer.
AWS
AWS Training
AWS Generative AI Learning Plan
AWS's free learning path for engineers building on Bedrock. Covers the AWS-specific patterns (Bedrock, SageMaker, Knowledge Bases for RAG, Bedrock Agents) plus general LLM/RAG concepts. Free, vendor-locked, useful only if your stack is AWS. The AI Practitioner cert ($100) and ML Engineer Associate ($150) build on this learning plan; pair with our /learn/certifications page for the cert side.
DL.AI
DeepLearning.AI
Vector Databases: from Embeddings to Applications
If you're going to use a vector DB (and in 2026 most AI engineers will), this is the right 90 minutes to spend. Covers embeddings, ANN algorithms, sparse vs dense, hybrid search, and a head-to-head of Pinecone, Weaviate, Chroma and pgvector. Free, vendor-agnostic enough despite the Weaviate teaching credit. Take before you commit to a vector DB.
Side-by-side
| Dimension | AWS Generative AI Learning Plan | Vector Databases: from Embeddings to Applications |
|---|---|---|
| Provider | AWS Training | DeepLearning.AI |
| Editorial tier | Listed | Hands-on reviewed |
| Level | Intermediate | Intermediate |
| Format | self paced | self paced |
| Duration | ~20-40 hours (modular) | ~1.5 hours (5 lessons) |
| Pricing | Free | Free |
| Instructor | AWS Training & Certification — AWS | Sebastian Witalec — Head of Developer Relations, Weaviate |
| Rating | No public rating | No public rating |
| Topics | llm fundamentals, fine tuning, rag systems | rag systems, llm fundamentals |
| Last verified | 2026-05-24 | 2026-05-24 |
Pros & cons
AWS Generative AI Learning Plan
Pros
- +Free, comprehensive AWS-stack curriculum
- +Direct prep for AWS AI Practitioner + ML Engineer Associate certs
- +AWS Bedrock content is the deepest available for that platform
Cons
- −AWS-locked — patterns don't transfer to GCP / Azure
- −Some labs require small AWS spend ($5-20)
- −Tier 3 because we list rather than personally vet every module
Vector Databases: from Embeddings to Applications
Pros
- +Vendor-agnostic — covers Pinecone, Weaviate, Chroma, pgvector
- +First-principles approach — you understand WHY, not just HOW
- +Free, 90 minutes
Cons
- −Light on production-ops (sharding, backups, hybrid filtering)
Which course is for whom?
AWS Generative AI Learning Plan
Best for
- · Engineers at AWS-stack companies
- · Anyone preparing for AWS AI certs
Not ideal for
- · Non-AWS teams — wrong vendor focus
Vector Databases: from Embeddings to Applications
Best for
- · Engineers about to commit to a vector DB choice
- · PMs scoping a RAG project who need to understand the storage layer
Not ideal for
- · People wanting a single-vendor deep-dive — see Pinecone Learn or Weaviate Academy
Editor's short verdict
These cover different primary topics — AWS Generative AI Learning Plan focuses on llm fundamentals while Vector Databases: from Embeddings to Applications focuses on rag systems. Take the one matching your current goal first; the other can come later if your interests expand.
DL.AIHands-on reviewed
DeepLearning.AI
Vector Databases: from Embeddings to Applications
For: Engineers about to commit to a vector DB choice
Intermediate · ~1.5 hours (5 lessons) · Free
Other comparisons
Similar courses you might also be considering.
- Compare AWS Generative AI Learning Plan vs Practical Deep Learning for Coders (fast.ai) →
- Compare AWS Generative AI Learning Plan vs Hugging Face LLM Course →
- Compare AWS Generative AI Learning Plan vs Google Cloud Generative AI Learning Path →
- Compare Vector Databases: from Embeddings to Applications vs Weaviate Academy (open-source RAG) →
- Compare Vector Databases: from Embeddings to Applications vs Pinecone Learn (vector DB + RAG) →
- Compare Vector Databases: from Embeddings to Applications vs Building Agentic RAG with LlamaIndex →