From e3d1beda1a6ae2d916076826cfc6aca3af5d4eaf Mon Sep 17 00:00:00 2001 From: nadeempat <107585931+nadeempat@users.noreply.github.com> Date: Wed, 20 Mar 2024 18:03:45 -0500 Subject: [PATCH 1/2] Update README.md --- packages/blueprints/subscribe-blueprint/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/blueprints/subscribe-blueprint/README.md b/packages/blueprints/subscribe-blueprint/README.md index 168cd5134..a05ce2511 100644 --- a/packages/blueprints/subscribe-blueprint/README.md +++ b/packages/blueprints/subscribe-blueprint/README.md @@ -1,4 +1,4 @@ -# Subscribe to External Blueprint +# Subscribe to external blueprint This blueprint allows you to subscribe to community blueprint packages on NPM. The generated workflows periodically pull NPM packages and publishes them as custom blueprints in your CodeCatalyst space. A workflow is created for each package you want imported, so the target blueprint that you want published in your space must be made available through NPM. If you publish your own blueprints to NPM, you can use this blueprint to ensure that multiple spaces have the same NPM packages available as custom blueprints. Custom blueprints aren’t available for all tiers. Make sure that your space is subscribed at a tier that supports custom blueprints before using this blueprint. @@ -15,4 +15,4 @@ This blueprint creates a workflow for each imported package and works with priva * [Working with custom blueprints in CodeCatalyst](https://docs.aws.amazon.com/codecatalyst/latest/userguide/custom-blueprints.html) * [Working with packages](https://docs.aws.amazon.com/codecatalyst/latest/userguide/workflows-packages.html) * [About packages and modules](https://docs.npmjs.com/about-packages-and-modules) -* [Open-source GitHub repository](https://github.com/aws/codecatalyst-blueprints) \ No newline at end of file +* [Open-source GitHub repository](https://github.com/aws/codecatalyst-blueprints) From 139d6a1f5755f62504a7755acde58d53856c1a09 Mon Sep 17 00:00:00 2001 From: nadeempat <107585931+nadeempat@users.noreply.github.com> Date: Thu, 28 Mar 2024 13:47:41 -0500 Subject: [PATCH 2/2] Update README.md new version introduces claude 3 models and what that means is that any existing customer using the current version of the blueprint will have their conversation history deleted if they upgrade to this (this new blueprint version is not backwards compatible with the old version). --- packages/blueprints/gen-ai-chatbot/README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/packages/blueprints/gen-ai-chatbot/README.md b/packages/blueprints/gen-ai-chatbot/README.md index e2473a7ac..13dbf82e9 100644 --- a/packages/blueprints/gen-ai-chatbot/README.md +++ b/packages/blueprints/gen-ai-chatbot/README.md @@ -1,5 +1,7 @@ # Bedrock GenAI chatbot -This blueprint allows you to build, customize, and manage a chatbot using Anthropic’s LLM [Claude](https://www.anthropic.com/index/claude-2), a model provided by [Amazon Bedrock](https://aws.amazon.com/bedrock/) for generative AI. The chatbot supports multiple languages, content formats, conversation capabilities, and ability to monitor usage. You can set necessary permissions with IAM roles for a secure and login-protected LLM playground that can be customized to your data. +This blueprint allows you to build, customize, and manage a chatbot using Anthropic’s LLM [Claude](https://www.anthropic.com/index/claude-2), a model provided by [Amazon Bedrock](https://aws.amazon.com/bedrock/) for generative AI. The chatbot supports multiple languages, content formats, conversation capabilities, and ability to monitor usage. You can set necessary permissions with IAM roles for a secure and login-protected LLM playground that can be customized to your data. + +**Important**: Changing to a blueprint version with a different Claude model deletes the conversation history. A new blueprint version is not backwards compatible with an older version. ## Bot conversation and bot personalization You can personalize your chatbot through custom instructions and external knowledge that can be provided through URLs or files (for example, [retrieval-augmented generation (RAG)](https://github.com/aws-samples/bedrock-claude-chat/blob/main/docs/RAG.md)). When a chatbot is created or updated, it pulls and breaks down data into text, and uses Cohere Multilingual to find and match the text to provide responses to user questions. The customized bot can be shared among application users.