I recommend you look deeper at LangChain if you are not already familiar with it. You can also look at the aws-samples Github page; they have some great examples to get you started. For example, you could add Amazon Kendra to the mix. Connect it with one of its many sources, like Atlassian Confluence, and set up Langchain to utilize the Kendra retriever. And now you have a chatbot that can answer questions based... - Source: dev.to / 8 months ago

If you're doing this on AWS they already have a really contained solution for this. I'm sure Azure has a similar solution. I'll assume AWS - if so, AWS Kendra is a good place to start. This will give you performant natural language understanding and enterprise search support. Then you just need to map the rest of your desired functions to core AWS solutions. Source: about 1 year ago

> > One of the most important capabilities of Bedrock is how easy it is to customize a model. Customers simply point Bedrock at a few labeled examples in Amazon S3, and the service can fine-tune the model for a particular task without having to annotate large volumes of data (as few as 20 examples is enough) I can't even. Does anyone remember Amazon Kendra [1]? They promised the same there. "Here's an ML powered... - Source: Hacker News / about 1 year ago

Amazon Kendra is now FedRAMP High Compliant. Amazon Kendra is now authorized as FedRAMP High in AWS GovCloud (US-West) Region. Amazon Kendra is a highly accurate intelligent search service powered by machine learning. Kendra reimagines enterprise search for your websites and applications so your employees and customers can easily find the content they are looking for, even when it's scattered across multiple... - Source: dev.to / over 1 year ago

It supports using Lambdas for fulfilling specific duties, such as placing orders, as well as integrating into Kendra which is a ML powered search service. You can effectively have a conversation asking for information and it can intelligently look through your business domain and respond with answers in a naturally conversational way. - Source: dev.to / over 1 year ago

I run a large scale production application that does something along these lines. If the data needs to be close to real-time, I'd say use `searchkick` + Elasticsearch, and use `searchkick`'s async feature to "stream" the data from your table to the ES index. Your dashboard will then just query from the ES index via searchkick. Source: over 1 year ago

You're right, that's actually what we implemented, application-level hooks, but they needed development and maintenance effort that come for free with the adapter we're using for OpenSearch integration, which also comes with welcome features: synonyms, partial matches, and many others. Spoiler, the adapter is Searchkick: https://github.com/ankane/searchkick. - Source: Hacker News / over 1 year ago

Normally for Rails applications you would use a gem like searchkick since it greatly reduces the initial Elasticsearch complexity. Source: almost 2 years ago

We lean heavily on Elasticsearch at CompanyCam. One of it's primary use cases is serving our highly filterable project feed. It is incredibly fast, even when you apply multiple filters to your query and are searching a largish data set. Our primary interface for interacting with Elasticsearch is using the Searchkick gem. Searchkick is a powerhouse and provides so many features out of the box. One place where we... - Source: dev.to / almost 2 years ago

Convinced? Ok read on and I’ll show you what switching from Elasticsearch to Meilisearch looked like for a real production app — ScribeHub. We also moved from Ankane’s excellent Searchkick gem to the first party meilisearch-rails gem and I’ll show you the changes there as well. - Source: dev.to / almost 2 years ago