Learn to build an intelligent AutoRAG system from scratch using PhiData in this comprehensive tutorial video. Discover how to enhance AI's decision-making capabilities for using memory, searching vector databases, or utilizing web search tools for relevant responses. Explore the basics of AutoRAG, set up an assistant with a large language model, add documents to a knowledge base, query the AI effectively, and create a user interface. Gain insights into memory storage with Postgres and PG Vector, utilize tools like DuckDuckGo Search, and integrate Groq LLM and Llama Hermes 2 Pro. Follow along with step-by-step instructions to develop a functional autonomous AI application, complete with a Streamlit-based user interface for improved interaction.
Creating an Autonomous AI App with AutoRAG and PhiData
Overview
Syllabus
- Introduction to AutoRAG using PhiData
- Memory Storage with Postgres and PG Vector
- Utilising Tools like DuckDuckGo Search
- Adding Documents to the Knowledge Base
- Running Queries and Generating Responses
- Creating a User Interface with Streamlit
- Integrating Groq LLM and Llama Hermes 2 Pro
Taught by
Mervin Praison
Related Courses
-
Comprehensive Guide to Generative AI Development and Implementation
-
Knowledge Graphs for RAG
-
Creating an AI Operating System from Scratch with GPT-4
-
Llama Index 101 with Vector DBs and GPT 3.5
-
Creating an AI Research Assistant Using Ollama RAG - Cost-Free Implementation
-
Understanding Generative AI: RAG, Semantic Search, Embeddings, and Vectors
