Decoding

Greedy Decoding

Non-Deterministic Decoding

Temperature

Hallucination

Groundedness and Attributability

Retrieval Augmented Generation

Code Models

OCI Generative AI Service

How does OCI Generative AI service work

Pretrained Foundational Models

Fine-tuning

Dedicated AI Clusters

Tokens

Pretrained Chat Models

Chat Model Parameters

Preamble Override

Temperature

Chat Model Parameters

Top k

Top p

Frequency and Presence Penalties

Embeddings

Word Embeddings

Prompt & Prompt Engineering

LLMs as next word predictors

Aligning LLMs to follow instructions

In-context Learning and Few-shot Prompting

Prompt Formats

Advanced Prompting Strategies

Training LLMs from scratch with my data

In-context Learning / Few-shot Prompting

Fine-tuning a pretrained model

Fine-tuning Benefits

Retrieval Augmented Generation (RAG)

Customize LLMs with your data

Fine-tuning and Inference

Fine-tuning workflow in OCI Generative AI

Inference workflow in OCI Generative AI

Dedicated AI Clusters

T-Few Fine-tuning

Dedicated AI Cluster Units

Dedicated AI Cluster Units Sizing

Dedicated AI Clusters Sizing

Example Pricing

Fine-tuning Configuration

Fine-tuning Parameters (T-Few)

Understanding Fine-tuning Results

Dedicated GPU and RDMA Network

Model Endpoints

Customer Data and Model Isolation

Generative AI leverages OCI Security Services

Retrieval Augmented Generation

RAG Framework

RAG Techniques

RAG Pipeline

Chatbot Introduction

Demo Chatbot

Chatbot Architecture

OCI Generative AI and LangChain Integration

LangChain Components

LangChain Prompt, Model and Chain Interaction

LangChain Prompt Templates

String Prompt Template and PromptValue

Chat Prompt Template and PromptValue

LangChain Models

LangChain Models OCI Chat Models

LangChain Models OCI Embedding Models

LangChain Chains

LangChain Chains

LangChain Memory

Memory

Memory Chat Messages

LangChain Memory Per User

Demo Memory

Demo Streamlitand Memory

RAG with LangChain

Retrieval Augmented Generation (RAG) with LangChain

Read and Split Documents

Embed documents and store in the vector database

Retrieve documents and send as a context to the LLM

Demo RAG - Indexing

Demo RAG - Retrieval and Generation

RAG Plus Memory

Adding chat history as context

Print of Response

Demo RAG Plus Memory and Tracing with LangSmith

Demo Evaluate Model using LangSmith

Chatbot Technical Architecture

Deploy Chatbot to OCI Compute Instance (Virtual Machine)

Demo Deploy Chatbot to VM

Deploy LangChain Application to Data Science as Model