Generative AI and Similarity Search with Vertex AI Matching Engine Kamolphan Liwprasert She/Her GDE Cloud / WTM Ambassador

Generative AI is a type of artificial intelligence (AI) that can create new content, such as text, images, or music. Generative AI Generative AI Vertex AI

LLM: Large Language Models LLM Example: ChatGPT, Bard (PaLM 2)

When all these begin? Language Model

PaLM 2 (Pathway Language Model) is a Google’s LLM. It comes with different model sizes and parameters for different tasks. cloud.google.com/vertex-ai/docs/generative-ai/learn/models PaLM API PaLM API Available models: ● Text-bison ● Textembedding-gecko ● Chat-bison ● Code-bison ● Codechat-bison ● Code-gecko

Getting started with Generative AI! Generative AI developers.generativeai.google/

MakerSuite MakerSuite developers.generativeai.google/

Vertex AI capabilities Vertex AI

Demo time!

Demo Scenario PDF files PaLM API embeddings Vector Store 🦜🔗

Embedding Google Developers Embedding Layer in a Deep Network An embedding is a relatively low-dimensional space into which you can translate high-dimensional vectors. Embeddings make it easier to do machine learning on large inputs like sparse vectors representing words

Similarity Search Flikr Similarity Search “Nearest Neighbor Search” : Compare embedding distance

Show me the code! Code

Code github.com/GoogleCloudPlatform/generative-ai/blob/main /language/use-cases/document-qa/question_answering_d ocuments_langchain_matching_engine.ipynb

Vector Store Vertex AI Matching Engine is a high-scale low latency vector database. These vector databases are commonly referred to as vector similarity-matching or an approximate nearest neighbor (ANN) service. Matching Engine provides the ability to search for semantically similar or semantically related items from its embeddings. Vertex AI Matching Engine Real world use cases such as: ● Recommendation engines ● Search engines ● Ad targeting systems ● Image classification or image search ● Text classification ● Question answering ● Chatbots

Langchain LangChain is a framework (Python / JS library) for developing applications powered by large language models (LLMs). The main values of LangChain are: ● Components: abstractions for working with language models, along with a collection of implementations for each abstraction. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not ● Off-the-shelf chains: a structured assembly of components for accomplishing specific higher-level tasks langchain.com

Code github.com/GoogleCloudPlatform/generative-ai/blob/main /language/examples/document-qa/question_answering_do cuments_langchain_matching_engine.ipynb

Architecture Image:github.com/GoogleCloudPlatform/generative-ai/blob/main/language/examples/document-qa/question_answering_document s_langchain_matching_engine.ipynb Store embeddings in Vertex AI Matching Engine (vector search)

Architecture Image:github.com/GoogleCloudPlatform/generative-ai/blob/main/language/examples/document-qa/question_answering_document s_langchain_matching_engine.ipynb RAG = Retrieval Augmented Generation

Vector Store Create Index * Take up to 1 hours Create Index Endpoint (deploy index) Add documents as embeddings Read PDF files chunks → embeddings Vertex AI Matching Engine

developers.generativeai.google Resource

github.com/GoogleCloudPlatform /generative-ai Resource

Generative AI Learning Path cloudskillsboost.google/journeys/118 Resource

Generative AI Learning Path cloudskillsboost.google/journeys/118 Resource

cloud.withgoogle.com/next Event Aug. 29-31, 2023

Q & A Kamolphan Liwprasert She/Her GDE Cloud / WTM Ambassador

Thank You Kamolphan Liwprasert She/Her GDE Cloud / WTM Ambassador