Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ image: assets/images/posts/2023/10/mari-lezhava-q65bNe9fW-w-unsplash.jpg

Generative AI and large language models (LLMs) are becoming increasingly popular, and small and big tech companies are releasing new solutions like ChatGPT, Bard, and Llama on a weekly basis. Corporations are looking for ways to use this technology to create company-wide knowledge sources and AI assistants to improve employee productivity, efficiency and access to internal knowledge.

In order to meet this demand, we decided at Smile to experiment with a lot of different tools already (read about it [here](https://tech.smile.eu/your-private-gpt-to-chat-with-your-documents/) and here) but we wanted to give it a try to the freshly available [Amazon Bedrock](https://aws.amazon.com/bedrock/) service on AWS. We wanted to see whether it was easy to create generative AI based chatbots on AWS, and what could be the benefits of using it.
In order to meet this demand, we decided at Smile to experiment with a lot of different tools already (read about it [here](https://tech.smile.eu/your-private-gpt-to-chat-with-your-documents/)) but we wanted to give it a try to the freshly available [Amazon Bedrock](https://aws.amazon.com/bedrock/) service on AWS. We wanted to see whether it was easy to create generative AI based chatbots on AWS, and what could be the benefits of using it.

To experiment with this technology, we decided to create a Medical Assistant Chatbot, using [Anthropic](https://www.anthropic.com/)’s [Claude v2 model](https://www.anthropic.com/product) hosted on AWS Bedrock service. The Claude family of large language models is purpose built for conversations, summarization, Q&A, workflow automation and coding, supporting multiple languages (we tried in English and French).

Expand Down