English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 53 lectures (4h 12m) | 3.07 GB
Unlock the Potential of Your Data with Pinecone, Chroma, and Beyond
In the era of big data and AI, managing and extracting meaningful insights from vast amounts of unstructured data is more crucial than ever. “Mastering Vector Databases: From Foundations to Advanced Applications” is your comprehensive guide to understanding, building, and leveraging vector databases to transform your data management capabilities.
What You Will Learn:
- Foundations of Vector Databases: This course will help you gain a solid understanding of vector databases, why they are essential, and how they differ from traditional databases.
- Overview of Top Vector Database Solutions: Explore the top 5 vector database solutions, including Pinecone and Chroma, and understand their unique features and key differences.
- Building Vector Databases from Scratch: Learn how to construct your vector database from the ground up, focusing on metrics, data structures, and efficient data storage.
- Vectorization Techniques: Master converting unstructured data into meaningful vectors using abstraction frameworks and embedding techniques.
- Hands-On Projects: Apply your knowledge with practical projects that demonstrate real-world applications of vector databases, including AI-driven search, document clustering, and personalized content recommendations.
- Advanced Querying and Retrieval: Understand how to quickly perform efficient similarity searches and retrieve relevant data using advanced querying techniques.
Table of Contents
Introduction
1 Introduction – Course prerequisites and structure
Source Code and Resources
2 Code and resources
Vector Databases Deep Dive – Fundamentals
3 Introduction to Vector Databases – Full Overview
4 Why Vector Databases
5 Vector Databases – Benefits and Advantages
Traditional vs Vector Databases – Differences
6 Traditional vs Vector Databases – Limitations and Challenges
7 Embeddings vs Vectors – Differences
8 Vector Databases – How They Work and Advantages
9 Vector Databases Use Cases
10 Vector and Traditional Databases – Summary
Vector Databases Solutions – Top 5 Vector Databases
11 The Top 5 Vector Databases – Overview
12 Understanding LLM (Large Language Models)
Building Vector Databases – Hands-on – Chroma Vector Database
13 Development Environment Setup
14 Setup VS-Code, Python and OpenAI API Key
15 Chroma Database workflow
16 Creating a Chroma Vector Database & Adding Documents & Querying them
17 Looping Through the Results & Showing Similarity Search Results
18 Chroma Default Embedding Function
19 Chroma Vector Database – Persisting Data and Saving
20 Creating an OpenAI Embeddings – Raw without Chroma
21 Using OpenAIs Embedding API to Create Embedding in Chroma
22 Vector Databases Metrics and Data Structures
23 Section Summary
Common Measures of Vector Similarity
24 Vector Similarity Deep Dive – Cosine Similarity
25 Euclidean Distance – L2 Norm
26 Dot Product
27 Section Summary
Vector Databases and LLM – the Full Workflow
28 Vector Databases and LLM – Deep Dive
29 Loading all Documents
30 Generating Embeddings from Documents & Insert then into Chroma Database
31 Getting the Relevant Chunks when Given a Query
32 Using OpenAI LLM to Generate Response – Full Flow
33 Section Summary
Vector Databases & the Langchain Framework
34 The LangChain Framework – Quick Overview
35 Getting started with LangChain and the OpenAIChat Wrapper
36 Loading Documents with LangChain Document Loader
37 Splitting the Documents with LangChain
38 Creating a Chroma Vector Database with LangChain
39 Getting the Response from the Model – the Complete WorkFlow
Pinecone Vector Database
40 Pinecone – Deep Dive
41 Create Pinecone Account & Dashboard Overview
42 Creating our Pinecone Index in Code
43 Upserting and Querying our Pinecone Index
44 Querying Pinecone Manually in the Dashboard
45 Using LangChain Pinecone Wrapper – Create Index and Upsert & Similarity Search
46 Creating a Retriever and Chain Objects & a LLM to get a Response
47 Clean up – Delete Pinecone Index
48 Challenge – Explore other Vector Database
49 Section Summary
Choosing the Right Vector Database
50 Choosing the Right Vector Database – Comparison Tables
51 Which Database Should I Choose
52 Choosing the Right Database – Criterias
Wrap up & Next Steps
53 Congratulations and Next Steps
Resolve the captcha to access the links!