Catalogue
/
Databases
/
Weaviate for Vector Search, RAG, and Scalable AI Applications

Weaviate for Vector Search, RAG, and Scalable AI Applications

A practical two day technical course for participants who are new to Weaviate and want to build semantic search, retrieval, and generative AI applications. The agenda progresses from Weaviate architecture, deployment, collections, and data modeling through vectorization, similarity search, hybrid retrieval, filtering, Python integration, RAG, multi-tenancy, performance optimization, scaling, and security. The course focuses on building useful retrieval applications while developing the operational knowledge needed to move them toward production.

What will you learn?

You will learn how Weaviate stores structured objects together with vector embeddings and how its indexing architecture supports semantic, keyword, filtered, and hybrid retrieval. You will work with collections, vectorizers, the Python client, generative integrations, and RAG workflows. You will also learn how to design multi-tenant applications and make informed decisions about indexing, performance, scaling, and security.

  • Create and manage Weaviate collections, objects, vectors, properties, and indexes
  • Implement vector, filtered, keyword, and hybrid search workflows
  • Integrate Weaviate with Python, embedding models, generative models, and RAG applications
  • Configure multi-tenancy, performance optimization, scaling, and secure access

Requirements:

  • Basic Python programming experience, including API integration
  • Familiarity with JSON data structures, databases, data modeling, and querying
  • Basic understanding of vector embeddings, semantic search, and LLM applications
  • Familiarity with Docker and containerized applications

Course Outline*:

*We customize the course outline and content to your specific needs and relevant use cases.

Module 1: Weaviate architecture and deployment

  • Understanding Weaviate as a vector database for semantic and AI-powered applications
  • Reviewing collections, objects, properties, vectors, vector indexes, and inverted indexes
  • Running Weaviate locally with containers or connecting to a managed deployment
  • Understanding the relationship between application clients, Weaviate, model integrations, and storage

Module 2: Collections, data modeling, and vectorization

  • Creating collections and defining properties and data types
  • Configuring vectorizers and understanding automatic versus externally generated embeddings
  • Importing, updating, retrieving, and deleting objects with the Python client
  • Designing collection schemas and metadata for search and downstream application use

Module 3: Vector search, filtering, and indexing

  • Performing semantic similarity searches using vector or natural-language queries
  • Applying structured filters to combine semantic relevance with application constraints
  • Understanding HNSW, flat, and dynamic vector index approaches
  • Selecting index and distance settings based on collection size, recall, latency, and resource requirements

Module 4: Keyword and hybrid search

  • Using keyword search for exact terms and lexical relevance
  • Combining vector and BM25F results with hybrid search
  • Adjusting the balance between semantic and keyword retrieval
  • Designing retrieval strategies for queries that require both meaning and exact terminology

Module 5: Python applications and semantic retrieval

  • Building reusable ingestion and search workflows with the Weaviate Python client
  • Converting application queries into semantic retrieval requests
  • Returning relevant objects, metadata, distances, and search scores
  • Structuring search services for integration into larger Python applications

Module 6: RAG integration and generative search

  • Positioning Weaviate within ingestion, retrieval, context construction, and generation workflows
  • Configuring generative model integrations for retrieved content
  • Designing chunking, metadata, filtering, and retrieval strategies for RAG
  • Investigating poor retrieval and incomplete context before tuning generation

Module 7: Multi-tenancy, performance, and optimization

  • Understanding tenant isolation and when multi-tenancy is preferable to separate collections
  • Designing collections and tenant structures for SaaS and segmented datasets
  • Tuning vector indexes and using compression or quantization to reduce resource requirements
  • Balancing recall, query latency, memory consumption, indexing cost, and workload scale

Module 8: Scaling, security, and production readiness

  • Understanding sharding, replication, and multi-node deployment concepts
  • Planning capacity and scaling for growing collections and query workloads
  • Configuring authentication, authorization, and protected application access
  • Building a practical production readiness checklist covering indexing, multi-tenancy, security, backups, monitoring, scaling, and recovery

Hands-on learning with expert instructors at your location for organizations.

3,072€*
Graph Icon - Education X Webflow Template
Level:
intermediate
Clock Icon - Education X Webflow Template
Duration:
14
Hours (days:
2
)
Camera Icon - Education X Webflow Template
Training customized to your needs
Star Icon - Education X Webflow Template
Immersive hands-on experience in a dedicated setting
*Price can range depending on number of participants, change of outline, location etc.

Master new skills guided by experienced instructors from anywhere.

2,037€*
Graph Icon - Education X Webflow Template
Level:
intermediate
Clock Icon - Education X Webflow Template
Duration:
14
Hours (days:
2
)
Camera Icon - Education X Webflow Template
Training customized to your needs
Star Icon - Education X Webflow Template
Reduced training costs
*Price can range depending on number of participants, change of outline, location etc.

Upcoming Sessions

5-6 Jan 2027
Madrid
19-20 Jan 2027
Amsterdam
25-26 Mar 2027
Munich
6-7 Apr 2027
Brussels
29-30 Jun 2027
Berlin
7-8 Jul 2027
Zurich

Can't find a suitable date? Get in touch and we'll arrange one that works for you.

We use cookies to improve site navigation, analyse how the site is used, and support our marketing. You can accept all cookies, reject non-essential ones, or choose individual categories. Read our Cookie Notice