Amazon Bedrock RAG Workshop

1. Introduction
2. Lab 1: Introduction [5 mins]
- 2.1. Prerequisites
- 2.2. Setup
3. Lab 2: Semantic Similarity Search [30 mins]
- 3.1. Implementation
4. Lab 3: Semantic Similarity Search with Metadata Filtering [30 mins]
- 4.1. Implementation
5. Lab 4: Semantic Similarity Search with Document Summaries [30 mins]
- 5.1. Implementation
6. Lab 5: Semantic Similarity Search with Re-Ranking [30 mins]
- 6.1. Implementation
7. Conclusion
8. References

1. Introduction

The Amazon Bedrock Retrieval-Augmented Generation (RAG) Workshop is designed to provide hands-on experience with foundation models (FMs) and retrieval-augmented generation using Amazon Bedrock. This workshop is intended for developers and solution builders.

1.1. Workshop Overview

This workshop explores two primary types of knowledge for LLMs:

Parametric knowledge: Everything the LLM learned during training
Source (external) knowledge: Information fed into the LLM via the input prompt

We focus on retrieval-augmented generation (RAG) to ingest domain-specific information through source knowledge and augment the prompt passed to the LLM.

1.2. Key Abstractions

LLM: Anthropic Claude V2 (Amazon Bedrock)
Embeddings Model: Amazon Titan Embeddings (Amazon Bedrock)
Document Loader: PDF Loader and TextLoader (LangChain)
Vector Store: FAISS, LlamaIndex, ChromaDB (LangChain)
Chunking: Data splits
Index: VectorIndex
Wrapper: Abstracts logic from the user
Retrieval and Search: Retrieval QA, Semantic Similarity Search
Orchestrator: LangChain, LlamaIndex

1.3. RAG Workflow

2. Lab 1: Introduction [5 mins]

2.1. Prerequisites

AWS account
Familiarity with Python
Basic understanding of machine learning concepts

2.2. Setup

aws sts get-caller-identity | jq -r .Arn

pip3 install --user --no-build-isolation --force-reinstall \
    "boto3>=1.28.57" \
    "awscli>=1.29.57" \
    "botocore>=1.31.57"
pip3 install langchain==0.0.305 --user --force-reinstall

3. Lab 2: Semantic Similarity Search [30 mins]

Semantic search uses vector embedding representations of documents to perform searches in higher-dimensional vector spaces.

3.1. Implementation

# Python code for semantic similarity search will go here
print("Implementing semantic similarity search...")

4. Lab 3: Semantic Similarity Search with Metadata Filtering [30 mins]

This lab demonstrates how to use metadata to filter queries and improve result relevancy.

4.1. Implementation

# Python code for semantic search with metadata filtering will go here
print("Implementing semantic search with metadata filtering...")

5. Lab 4: Semantic Similarity Search with Document Summaries [30 mins]

Learn how to use document summaries to improve retrieval results and reduce latency.

5.1. Implementation

# Python code for semantic search with document summaries will go here
print("Implementing semantic search with document summaries...")

6. Lab 5: Semantic Similarity Search with Re-Ranking [30 mins]

Explore how re-ranking can improve result relevancy and introduce diversity in results.

6.1. Implementation

# Python code for semantic search with re-ranking will go here
print("Implementing semantic search with re-ranking...")

7. Conclusion

Summarize the key takeaways from the workshop and suggest next steps for further learning.