# aws-samples/aws-genai-llm-chatbot

A modular and comprehensive solution to deploy a Multi-LLM and Multi-RAG powered chatbot (Amazon Bedrock, Anthropic, HuggingFace, OpenAI, Meta, AI21, Cohere, Mistral) using AWS CDK on AWS

Repository: https://github.com/aws-samples/aws-genai-llm-chatbot
Canonical: https://ross.abutalabs.com/products/aws-genai-llm-chatbot
Homepage: https://aws-samples.github.io/aws-genai-llm-chatbot/
Language: TypeScript
License: MIT-0
License Family: permissive
Topics: cdk, chatbot, genai, huggingface, llm, sagemaker, semantic-search, vectordb, aurora, pgvector, bedrock, kendra, opensearch, aws, amazon-bedrock, langchain, opensearch-serverless, idefics, claude
Last push: 2026-06-30T15:46:28+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 90, release rhythm 8, longevity 83
- inputs: {"age_days": 1174, "days_push": 64, "days_rel": 587, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1400, forks 436 (observed 2026-08-28T04:04:37.176273+00:00)

## What it is
A modular, production-ready AWS solution for deploying a multi-LLM, multi-RAG powered chatbot using AWS CDK. It supports Amazon Bedrock, SageMaker, and external providers (Anthropic, OpenAI, HuggingFace, Meta, AI21, Cohere, Mistral) with a React web UI, workspaces for document indexing, and multiple vector database backends.

## Use cases
- deploy a chatbot with RAG on AWS
- compare responses from multiple LLMs side by side
- index company documents for semantic search and retrieval
- experiment with Amazon Bedrock models in my own account
- build domain-specific chatbots with role-based access control
- run multimodal LLMs that answer questions about images
- set up a self-hosted ChatGPT alternative on AWS

## When to choose
- you want a full-stack, production-ready RAG chatbot deployed on AWS with IaC
- you need to evaluate or serve multiple LLM providers (Bedrock, SageMaker, OpenAI, HuggingFace) behind one interface
- you require enterprise features like user roles, audit logging, and multiple vector store options (OpenSearch, Aurora pgvector, Kendra)
- you want a ready-made React UI plus API for chatbot interactions

## When to avoid
- you need a simple local chatbot without cloud infrastructure or AWS costs
- your stack is not AWS-based (GCP, Azure, on-prem)
- you want a lightweight library to embed in an existing app rather than a deployable solution
- you cannot grant the AWS permissions required for CDK deployment of Bedrock, SageMaker, and vector stores

## Facets
- artifact type: application
- maturity: active
- function: chatbot, rag, llm-inference, search-engine, vector-database, web-framework, infrastructure-as-code, auth, self-hosted
- domain: artificial-intelligence, large-language-models, chatbots, cloud-computing, web-development, self-hosted
- platform: cloud, browser, python
- tags: aws-cdk, amazon-bedrock, sagemaker, opensearch, pgvector, aurora, kendra, langchain, multi-llm, react-ui, enterprise, semantic-search, huggingface, claude, retrieval-augmented-generation, web-server, typescript, docker

## Member repositories
- aws-samples/aws-genai-llm-chatbot (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:37.176273+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:05.819105+00:00, confidence not recorded.
  - readme: https://github.com/aws-samples/aws-genai-llm-chatbot (fetched 2026-08-28T04:04:37.176273+00:00, sha 79d57075b66e)
  - homepage: https://aws-samples.github.io/aws-genai-llm-chatbot/ (fetched 2026-08-29T11:53:20.232281+00:00, sha 600419c0f079)
- Data as of 2026-08-30T08:39:29.467469+00:00.