datasets:
  - from: s3://spiceai-demo-datasets/taxi_trips/2024/
    name: taxi_trips
    params:
      file_format: parquet
      s3_region: us-east-1
      s3_auth: iam_role  # Uses IAM credentials from environment

datasets:
  - from: s3://spiceai-demo-datasets/taxi_trips/2024/
    name: taxi_trips
    params:
      file_format: parquet
      s3_region: us-east-1
      s3_auth: iam_role  # Uses IAM credentials from environment

datasets:
  - from: dynamodb:users
    name: users
    params:
      dynamodb_aws_region: us-west-2

datasets:
  - from: dynamodb:users
    name: users
    params:
      dynamodb_aws_region: us-west-2

datasets:
  - from: glue:my_namespace.orders
    name: orders
    params:
      glue_catalog_id: 123635965758:s3tablescatalog/my-table-bucket
      glue_region: us-east-2

datasets:
  - from: glue:my_namespace.orders
    name: orders
    params:
      glue_catalog_id: 123635965758:s3tablescatalog/my-table-bucket
      glue_region: us-east-2

catalogs:
  - from: glue
    name: my_data_lake
    include:
      - '*.*'  # Include all tables from all databases
    params:
      glue_region: us-east-1

catalogs:
  - from: glue
    name: my_data_lake
    include:
      - '*.*'  # Include all tables from all databases
    params:
      glue_region: us-east-1

models:
  - from: bedrock:us.amazon.nova-lite-v1:0
    name: nova
    params:
      aws_region: us-east-1

models:
  - from: bedrock:us.amazon.nova-lite-v1:0
    name: nova
    params:
      aws_region: us-east-1

models:
  - from: bedrock:amazon.nova-pro-v1:0
    name: nova-guarded
    params:
      aws_region: us-east-1
      bedrock_guardrail_identifier: arn:aws:bedrock:us-east-1:123456789012:guardrail/abc123
      bedrock_guardrail_version: '1'

models:
  - from: bedrock:amazon.nova-pro-v1:0
    name: nova-guarded
    params:
      aws_region: us-east-1
      bedrock_guardrail_identifier: arn:aws:bedrock:us-east-1:123456789012:guardrail/abc123
      bedrock_guardrail_version: '1'

embeddings:
  - from: bedrock:amazon.titan-embed-text-v2:0
    name: titan
    params:
      aws_region: us-east-1
      dimensions: '256'

embeddings:
  - from: bedrock:amazon.titan-embed-text-v2:0
    name: titan
    params:
      aws_region: us-east-1
      dimensions: '256'

embeddings:
  - from: bedrock:amazon.nova-2-multimodal-embeddings-v1:0
    name: nova_embed
    params:
      dimensions: '1024'
      truncation_mode: START
      embedding_purpose: GENERIC_RETRIEVAL
      aws_region: us-east-1

embeddings:
  - from: bedrock:amazon.nova-2-multimodal-embeddings-v1:0
    name: nova_embed
    params:
      dimensions: '1024'
      truncation_mode: START
      embedding_purpose: GENERIC_RETRIEVAL
      aws_region: us-east-1

datasets:
  - from: oracle:"CUSTOMER_REVIEWS"
    name: reviews
    vectors:
      enabled: true
      engine: s3_vectors
      params:
        s3_vectors_bucket: my-s3-vector-bucket
        s3_vectors_aws_region: us-east-1
    columns:
      - name: body
        embeddings:
          from: bedrock_titan

embeddings:
  - from: bedrock:amazon.titan-embed-text-v2:0
    name: bedrock_titan
    params:
      aws_region: us-east-1
      dimensions: '256'

datasets:
  - from: oracle:"CUSTOMER_REVIEWS"
    name: reviews
    vectors:
      enabled: true
      engine: s3_vectors
      params:
        s3_vectors_bucket: my-s3-vector-bucket
        s3_vectors_aws_region: us-east-1
    columns:
      - name: body
        embeddings:
          from: bedrock_titan

embeddings:
  - from: bedrock:amazon.titan-embed-text-v2:0
    name: bedrock_titan
    params:
      aws_region: us-east-1
      dimensions: '256'

datasets:
  - from: s3://source-bucket/events/
    name: analytics_events
    acceleration:
      engine: cayenne
      enabled: true
      mode: file
      params:
        # Store accelerated data in S3 Express One Zone bucket
        cayenne_file_path: s3://my-bucket--usw2-az1--x-s3/cayenne/
        cayenne_s3_region: us-west-2

datasets:
  - from: s3://source-bucket/events/
    name: analytics_events
    acceleration:
      engine: cayenne
      enabled: true
      mode: file
      params:
        # Store accelerated data in S3 Express One Zone bucket
        cayenne_file_path: s3://my-bucket--usw2-az1--x-s3/cayenne/
        cayenne_s3_region: us-west-2

datasets:
  - from: postgresql://db/events
    name: fast_events
    acceleration:
      engine: cayenne
      enabled: true
      mode: file
      params:
        # Auto-generates bucket: spice-{spicepod-name}-fast_events--usw2-az1--x-s3
        cayenne_s3_zone_ids: usw2-az1

datasets:
  - from: postgresql://db/events
    name: fast_events
    acceleration:
      engine: cayenne
      enabled: true
      mode: file
      params:
        # Auto-generates bucket: spice-{spicepod-name}-fast_events--usw2-az1--x-s3
        cayenne_s3_zone_ids: usw2-az1

secrets:
  - from: aws_secrets_manager:my_database_creds
    name: db

datasets:
  - from: postgres:public.users
    name: users
    params:
      pg_host: ${db:host}
      pg_user: ${db:username}
      pg_pass: ${db:password}

secrets:
  - from: aws_secrets_manager:my_database_creds
    name: db

datasets:
  - from: postgres:public.users
    name: users
    params:
      pg_host: ${db:host}
      pg_user: ${db:username}
      pg_pass: ${db:password}

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "s3:GetObject",
        "s3:ListBucket",
        "dynamodb:Scan",
        "dynamodb:DescribeTable",
        "glue:GetTable",
        "glue:GetTables",
        "glue:GetDatabase",
        "glue:GetDatabases",
        "bedrock:InvokeModel",
        "secretsmanager:GetSecretValue"
      ],
      "Resource": "*"
    }
  ]
}

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "s3:GetObject",
        "s3:ListBucket",
        "dynamodb:Scan",
        "dynamodb:DescribeTable",
        "glue:GetTable",
        "glue:GetTables",
        "glue:GetDatabase",
        "glue:GetDatabases",
        "bedrock:InvokeModel",
        "secretsmanager:GetSecretValue"
      ],
      "Resource": "*"
    }
  ]
}

curl https://install.spiceai.org | /bin/bash

curl https://install.spiceai.org | /bin/bash

aws configure

aws configure

# spicepod.yaml
version: v1
kind: Spicepod
name: aws_quickstart

datasets:
  - from: s3://spiceai-demo-datasets/taxi_trips/2024/
    name: taxi_trips
    params:
      file_format: parquet
      s3_auth: iam_role

# spicepod.yaml
version: v1
kind: Spicepod
name: aws_quickstart

datasets:
  - from: s3://spiceai-demo-datasets/taxi_trips/2024/
    name: taxi_trips
    params:
      file_format: parquet
      s3_auth: iam_role

spice run

spice run

spice sql
> SELECT COUNT(*) FROM taxi_trips;

spice sql
> SELECT COUNT(*) FROM taxi_trips;