A solution guidance for Generative BI using Amazon Bedrock, Amazon OpenSearch with RAG

Demonstration of Natural Language Query (NLQ) of an Amazon RDS for PostgreSQL database, using SageMaker JumpStart, Amazon Bedrock, LangChain, Streamlit, and Chroma.

Parser for end-user search-like queries and rule-based named entity recognition (NER) in context of tabular dataset schema.

GenoQuery is an innovative tool designed to streamline the process of querying genomic and biological data through a user-friendly chatbot interface.

VS Code extension for AI-generated SQL from Natural Language Queries

Query OpenSearch indices with natural language.

Application component that provides Natural Language Querying (NLQ) services, making knowledge stored in a graph database accessible for e.g. a ChatBot UI.

We'll use NQ (Natural Questions) dataset from the Google. We'll find weak negatives, and hard negatives first. Then we'll calculate word embeddings using OpenAI's text-embedding-ada-002 word embedding model to compare the accuracy and performance with customized word embeddings.