Change the repository type filter
All
Repositories list
99 repositories
bedrock-agent-txt2sql
Public- Use natural language to run inference on various LLMs via Bedrock agents
- This repo provides guidance on setting up a bedrock agent to webscrape and internet search via action groups
bedrock-agents-streamlit
Publicagentic-workshop
PublicLearn how to build Agentic Workflows on AWSllm-rag-vectordb-python
PublicExplore sample applications and tutorials demonstrating the prowess of Amazon Bedrock with Python. Learn to integrate Bedrock with databases, use RAG techniques, and showcase experiments with langchain and streamlit.- This repository sets up an end-to-end CI/CD container pipeline with Hashicorp Terraform based on native AWS services for hosting and testing application code, building a container image from the code, pushing and storing the container image to ECR, and deploying this container on EKS as a deployment.
- Authorization is one of the foundational needs when building your applications and services. Learn how, with the help of Cedar and Amazon Verified Permissions, to to add non-trivial authorization rules to your web application.
- Command-Query Responsibility Segregation (CQRS) is often presented as a pattern focused on scaling by separating reads and writes. However, this is an architecture-level pattern that has nothing to do with infrastructure. At AWS re:Invent 2023 session (BOA211) we explored the right way of combining AWS Lambda and CQRS together.
langchain-embeddings
Publicgen-ai-workshop
PublicLearn how to build generative AI applications on AWS using PartyRock, Amazon Bedrock, and Amazon Q- Example gaming leaderboard application covering streaming ingestion, CDC enrichment, processing and visualisation including demo of advance real-time analytics concepts like late data arrival, exactly-once, dynamic config, archival and on-demand replay
- Deploying TRURL 2 on Amazon SageMaker. TRURL 2 is a Large Language Model (LLM), which is a fine-tuned version of LLaMA 2 with support for Polish language developed by VoiceLab and published at the company profile on Hugging Face (https://huggingface.co/Voicelab).
- With this WhatsApp app, you can chat in any language with a Large language models (LLM) on Amazon Bedrock. Send voice notes and receive transcriptions. By making a minor change in the code, you can also send the transcription to the model.
- Sample code for features of Agents for Amazon Bedrock
- Welcome to this repo where we'll continue adding hands-on examples demonstrating the use of the Java SDK for Amazon Bedrock.
- This repository contains sample app code to build an object and text detection web app. An individual can upload images that contains real world objects or text, and get the labels for all the detected objects and texts in the image.
- This project contains the sample code for a small utility to pull and store the priority dates from the monthly USCIS Visa Bulletins. It is based on series of articles on [Community.aws](https://community.aws).
- This application is built in four stages using infrastructure as code with CDK with Python to deploy. In the first stage, an Amazon Aurora PostgreSQL vector database is set up. In the second stage, the Knowledge Base for Amazon Bedrock is created using the established database. The third stage involves creating an Amazon
- Get ready to embark on an exciting journey as we combine the power of Amazon Bedrock, ReactJS and the AWS JavaScript SDK to create a generative AI application with minimal integration code.
- This repo contains code for a demo of Amazon Bedrock Agents.
- Sample code that shows the important aspects of developing custom connectors for Kafka Connect. It provides the resources for building, deploying, and running the code on-premises using Docker, as well as running the code in the cloud.
- I'll guide you through setting up the resources, defining the agent's action groups, associating AWS Lambda functions to execute DynamoDB operations, and integrating the knowledge base for enhanced conversational experiences to provide more personalized and context-aware responses to user queries. All this with a 'CDK deploy' command using the AWS
- In the fast-paced world of data-driven decision making, real-time insights are crucial for staying ahead of the competition. Amazon OpenSearch Service and Amazon DynamoDB offer a powerful combination that enables organizations to visualize and analyze data in near real-time, without the need for complex Extract, Transform, Load (ETL) processes