Index is not created inside the Amazon OpenSearch cluster

Question

I am following the turorial "Build a Full Stack Large Language Model Powered Chatbot: Extract Insights from Unstructured Documents" at https://community.aws/tutorials/fullstack-llm-langchain-chatbot-on-aws. I have completed all steps up to step 5 but there I face the following problem:
There is a Lambda function which is invoked by an S3 bucket event. The Lambda function initiates a Fargate task, which in turn runs a Docker container containing a python script, responsible for generating embeddings in Amazon OpenSearch under a new OpenSearch index. The problem is that the index is not created in the Amazon OpenSearch cluster as it should.
Do you think it is a policy issue in the fargate task? I don't see any errors in CloudWatch from the Lambda Function. Could you please help me?
Thank you for your time.

Accepted Answer

The logs that will tell you the root cause of your problem are likely to be found in the Fargate Task Cloudwatch Logs.

If you want to check out an end-to-end solution, you can look at https://github.com/aws-samples/aws-genai-llm-chatbot which uses AWS Batch + Fargate and not Fargate directly.

Index is not created inside the Amazon OpenSearch cluster

Relevant content