Example Usage

The workflow below demonstrates Bedrock connector's Create Embeddings and AI Generation operations.

It shows a query coming in through a Webhook and being sent to AWS Bedrock to create an embedding vector. The resulting vector is then passed to a vector database to perform a similarity search.

The AI Generation operation uses the similarity search result to Create a model response for the received query.

To generate the embeddings the Create Embeddings operation requires a model name to use and the query received through the Werbhook trigger

The AI Generation operation requires information for the following mandatory parameters:

• Messages: A list of messages comprising the conversation so far. Every message

  • Role: The role of the messages author. For example, system, user, assistant, etc.

• Model: ID of the model to use. You can choose from the available options.

Key Configurations

System Message:

• The system message sets the tone and context for the AI's responses. In this case, the AI is instructed to act as a helpful assistant who creates technical documentations.

• The system message includes specific rules and guidelines to ensure that responses are accurate, relevant, and in the desired format. It also included top 10 relevant searches from a Vector database.

User Message:

• This is where the user’s query is passed to the AI. In this example the query is dynamically fetched from the Webhook trigger