Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Couchbase Vector Search RAG
Learn to build a production‑grade RAG pipeline using Couchbase vector search and Amazon Bedrock, covering embedding creation, retrieval, and LLM integration with LangChain or LlamaIndex.
This demo showcases how to build a Retrieval-Augmented Generation (RAG) application using a vector database and Amazon Bedrock. The process begins with creating a vector index in the vector database to store, index, and retrieve embeddings efficiently. Amazon Bedrock is then integrated to access foundation models like Anthropic Claude for embeddings and large language model (LLM) responses. The demo also highlights the development of a production-grade RAG pipeline using orchestration frameworks such as LangChain or LlamaIndex. By combining vector search capabilities with foundation models, this approach enables highly granular and contextually accurate applications across industries, supporting use cases like content creation, question answering, summarization, and report generation.
Jupyter Notebook demonstrates RAG utilizing Amazon Bedrock and Couchbase vector search.
- CouchbaseCouchbase is a distributed, multi-model NoSQL database: it delivers sub-millisecond, memory-first performance and horizontal scaling for mission-critical applications.Couchbase is the high-performance, distributed NoSQL document database built for scale and flexibility. It stores data as JSON documents, supporting a multi-model architecture that includes key-value, full-text search, and analytics services. The memory-first design ensures ultra-low latency, often in the sub-millisecond range, critical for use cases like e-commerce and financial transactions. Developers leverage SQL++ (N1QL) to query JSON data, combining NoSQL flexibility with familiar SQL syntax. With Couchbase Lite, the platform extends to the mobile and edge, providing robust offline-first synchronization capabilities.
- Amazon BedrockAmazon Bedrock is the fully managed, serverless service for building and scaling generative AI applications with a choice of high-performing foundation models via a single API.Bedrock is the AWS fully managed service for enterprise-grade generative AI: it delivers a single, consistent API to access a wide selection of top Foundation Models (FMs). This includes models like Anthropic's Claude 3, Meta's Llama 2, and Amazon's Titan family . Developers can privately customize these FMs using their own data via techniques like fine-tuning and Retrieval Augmented Generation (RAG) . Bedrock also provides essential builder tools, including Agents for complex task orchestration and Guardrails for implementing application-specific safety policies . The serverless experience removes infrastructure management, letting teams focus entirely on application logic and deployment .
- LangChainThe open-source framework for building and deploying reliable, data-aware Large Language Model (LLM) applications.LangChain is the essential framework for engineering LLM-powered applications: it simplifies connecting models (like GPT-4 or Claude) to external data, computation, and APIs. The platform provides a modular set of components—Chains, Agents, Tools, and Memory—allowing developers to quickly build complex workflows like Retrieval-Augmented Generation (RAG) pipelines and sophisticated conversational agents. Its Python and JavaScript libraries, combined with LangChain Expression Language (LCEL), offer a standardized interface for rapid prototyping and moving applications to production with confidence.
Related projects
Agents using Advanced RAG Capabilities
Dubai
Demonstrates a proof‑of‑concept using modern retrieval methods—late interaction, OCR‑free pipelines, reasoning retrievers, and hypothetical embeddings—to improve agentic systems…
RAGistotle - a multi modal RAG
Dubai
This talk demonstrates a multi-modal RAG system handling text, audio, video, images, data files, and YouTube links, integrating…
AI SQL Agent
Dubai
This talk demonstrates an AI-driven system that converts simple English questions into optimized SQL queries using AWS Athena,…
From Crawl to Chat: Building AI Assistants with Web Crawlers, RAG, and LLMs
Dubai
Learn to build domain-specific AI assistants using web crawling, pgvector storage, and RAG with OpenAI, covering deployment and…
Semantic Recipe Search Using Couchbase and Embeddings
Dubai
Demonstrating a recipe recommendation system that transforms ingredient lists into embeddings, stores them in Couchbase, and uses vector…
Open source data ingestion for RAGs
Berlin
This talk demonstrates using dlt to ingest data from REST APIs and load it into LanceDB, enabling efficient,…