Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
From Crawl to Chat: Building AI Assistants with Web Crawlers, RAG, and LLMs
Learn to build domain-specific AI assistants using web crawling, pgvector storage, and RAG with OpenAI, covering deployment and future multi-agent integrations.
This talk explores how to build domain-specific AI assistants using web crawling, vector databases (pgvector), and Retrieval-Augmented Generation powered by OpenAI. It walks through an end-to-end system—data ingestion, vector storage, real-time response generation—and includes lessons learned in optimizing latency, retraining pipelines, and orchestrating services with RabbitMQ.
The talk also looks ahead: exploring how this system could integrate with recent developments like OpenAI’s ChatGPT Agents and Google’s A2A protocol, transforming the chatbot into a multi-agent AI system.
Ideal for ML engineers and developers, the session offers not just code, but vision—bridging today’s RAG pipelines with tomorrow’s autonomous AI workflows.
Express backend uses PostgreSQL, RabbitMQ (amqplib), JWT, and bcrypt for authentication.
RAG model using GPT-4o-mini, RabbitMQ messaging, and PostgreSQL/pgvector vector storage.
Compose Email
Loading recent emails...