Release v5.2.0 into Main

Author: estohlmann

.github/workflows/code.end-to-end-test.nightly.yml

@@ -36,8 +36,6 @@ jobs:
           cache: 'npm'
       - name: Install base dependencies
         run: npm ci
-      - name: Install Cypress deps
-        run: npm ci --prefix cypress
       - name: Run Cypress E2E Suite
         env:
           TEST_ACCOUNT_PASSWORD: ${{ secrets.TEST_ACCOUNT_PASSWORD }}

.gitignore

@@ -29,6 +29,8 @@ lib/rag/ingestion/ingestion-image/build
 .DS_Store
 *.iml
 *.code-workspace
+.cursor
+memory-bank/
 
 # Coverage Statistic Folders
 coverage

.pre-commit-config.yaml

@@ -12,22 +12,22 @@ repos:
       files: config.yaml
 
 - repo: https://github.com/PyCQA/bandit
-  rev: '1.7.5'
+  rev: '1.7.10'
   hooks:
     - id: bandit
       args: [--recursive, -c=pyproject.toml]
-      additional_dependencies: ['bandit[toml]']
+      additional_dependencies: ['bandit[toml]', 'pbr']
 
 - repo: https://github.com/Yelp/detect-secrets
-  rev: v1.4.0
+  rev: v1.5.0
   hooks:
     - id: detect-secrets
       exclude: (?x)^(
         .*.ipynb|config.yaml|.*.md|.*test.*.py
         )$
 
 - repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.5.0
+  rev: v5.0.0
   hooks:
     - id: check-json
     - id: check-yaml
@@ -41,15 +41,15 @@ repos:
     - id: trailing-whitespace
 
 - repo: https://github.com/codespell-project/codespell
-  rev: v2.2.6
+  rev: v2.3.0
   hooks:
     - id: codespell
       entry: codespell
       args: ['--skip=*.git*,*cdk.out*,*venv*,*mypy_cache*,*package-lock*,*node_modules*,*dist/*,*poetry.lock*,*coverage*,*models/*,*htmlcov*,*TIKTOKEN_CACHE/*', "-L=xdescribe"]
       pass_filenames: false
 
 - repo: https://github.com/pycqa/isort
-  rev: 5.12.0
+  rev: 5.13.2
   hooks:
     - id: isort
       name: isort (python)
@@ -59,13 +59,14 @@ repos:
   hooks:
     - id: black
 
-- repo: https://github.com/charliermarsh/ruff-pre-commit
-  rev: 'v0.1.3'
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  rev: 'v0.8.4'
   hooks:
     - id: ruff
       args:
         - --exit-non-zero-on-fix
         - --per-file-ignores=test/**/*.py:E402
+      exclude: \.ipynb$
 
 - repo: https://github.com/pycqa/flake8
   rev: '7.1.1'
@@ -85,7 +86,7 @@ repos:
 
 
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: 'v1.6.1'
+  rev: 'v1.13.0'
   hooks:
     - id: mypy
       verbose: true

CHANGELOG.md

@@ -1,3 +1,46 @@
+# v5.2.0
+## Key Features
+### Model Context Protocol (MCP)  Enhancements
+- **Connection Validation**: Real-time connection testing with detailed feedback on server connectivity during connection creation/edit
+- **Enhanced Debugging**: Improved error handling and connection status reporting for MCP servers
+
+### Session Management Improvements
+- **Time-Based Session Grouping**: Sessions are now automatically organized into time-based groups based on updated date (Last Day, Last 7 Days, Last Month, Last 3 Months, Older)
+- **Session ID Removal**: Removed session ID from prompt input for cleaner user interface
+
+### RAG (Retrieval-Augmented Generation) Improvements
+#### Document Processing
+- **Document Chunk Processing Fixes**: Resolved issues with document chunk processing and ingestion
+- **Document Library Pagination**: Added pagination support for the Document Library to handle large numbers of documents efficiently
+
+#### Vector Store Configuration
+- **Default Embedding Model Support**: Added ability to define a default embedding model when creating or updating vector stores
+- **IAM Permissions Optimization**: Trimmed vector store IAM permissions to follow the principle of least privilege
+- **Container Configuration**: Added container override configuration for batch ingestion processes
+
+#### Batch Ingestion
+- **Container Configuration**: Added support for container override configuration in batch ingestion jobs
+- **Max Batch Jobs Setting**: Implemented dynamic maximum batch jobs limit
+- **Ingestion Rules Updates**: Automatic updates to ingestion rules when Lambda functions are updated
+
+### Model Management Improvements
+- **Base Container Configuration**: Added support for using prebuilt model containers, instead of building during model deployment
+
+### UI/UX Enhancements
+- **General UI Improvements**: Various user interface enhancements to improve usability
+- **Updated Default System Prompt**: Updated LISAs default system prompt to take advantage of new rendering capabilities. Pairing this prompt with new UI components supports the display of:
+  - Inline-Code
+  - Mathematic equations using LaTex syntax
+  - Mermaid Diagrams. These diagrams can also be copied and downloaded as images
+
+## Acknowledgements
+* @bedanley
+* @estohlmann
+* @dustins
+* @jmharold
+
+**Full Changelog**: https://github.com/awslabs/LISA/compare/v5.1.0...v5.2.0
+
 # v5.1.0
 ## Key Features
 ### Model Management Enhancements

VERSION

@@ -1 +1 @@
-5.1.0
+5.2.0

lambda/mcp_server/lambda_functions.py

@@ -21,7 +21,8 @@
 
 import boto3
 from boto3.dynamodb.conditions import Attr, Key
-from utilities.common_functions import api_wrapper, get_item, get_username, is_admin, retry_config
+from utilities.auth import get_username, is_admin
+from utilities.common_functions import api_wrapper, get_item, retry_config
 
 from .models import McpServerModel, McpServerStatus
 

lambda/models/domain_objects.py

@@ -432,7 +432,9 @@ class RagDocument(BaseModel):
     def __init__(self, **data: Any) -> None:
         super().__init__(**data)
         self.pk = self.createPartitionKey(self.repository_id, self.collection_id)
-        self.chunks = len(self.subdocs)
+        # Only calculate chunks if not explicitly provided in data (for new documents)
+        if "chunks" not in data:
+            self.chunks = len(self.subdocs)
 
     @staticmethod
     def createPartitionKey(repository_id: str, collection_id: str) -> str:

lambda/models/lambda_functions.py

@@ -24,7 +24,8 @@
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse
 from mangum import Mangum
-from utilities.common_functions import get_groups, is_admin, retry_config
+from utilities.auth import is_admin
+from utilities.common_functions import get_groups, retry_config
 from utilities.fastapi_middleware.aws_api_gateway_middleware import AWSAPIGatewayMiddleware
 
 from .domain_objects import (

lambda/models/state_machine/create_model.py

@@ -117,6 +117,49 @@ def handle_start_copy_docker_image(event: Dict[str, Any], context: Any) -> Dict[
     image_path = get_container_path(request.inferenceContainer)
     output_dict["containerConfig"]["image"]["path"] = image_path
 
+    # Check if image type is ECR - skip building docker image if it already exists
+    if request.containerConfig and request.containerConfig.image.type == "ecr":
+        logger.info(f"ECR image detected for model {event.get('modelId')}, verifying image accessibility")
+        # Verify the ECR image is accessible
+        try:
+            # Extract repository name and tag from the base image
+            base_image = request.containerConfig.image.baseImage
+            if ":" in base_image:
+                repository_name, image_tag = base_image.rsplit(":", 1)
+            else:
+                repository_name = base_image
+                image_tag = "latest"
+
+            # Remove registry URL if present to get just the repository name
+            if "/" in repository_name:
+                repository_name = repository_name.split("/")[-1]
+
+            # Verify image exists in ECR
+            ecrClient.describe_images(repositoryName=repository_name, imageIds=[{"imageTag": image_tag}])
+
+            logger.info(f"ECR image {base_image} verified successfully")
+            output_dict["image_info"] = {
+                "image_tag": image_tag,
+                "image_uri": repository_name,
+                "image_type": "ecr",
+                "remaining_polls": 0,
+                "image_status": "prebuilt",
+            }
+            return output_dict
+
+        except ecrClient.exceptions.ImageNotFoundException:
+            error_msg = f"ECR image {base_image} not found. Please ensure the image exists and is accessible."
+            logger.error(error_msg)
+            raise Exception(error_msg)
+        except ecrClient.exceptions.RepositoryNotFoundException:
+            error_msg = (
+                f"ECR repository {repository_name} not found. Please ensure the repository exists and is accessible."
+            )
+            logger.error(error_msg)
+            raise Exception(error_msg)
+
+    # For non-ECR images, proceed with the normal docker image building process
+    logger.info(f"Invoking image build for model {event.get('modelId')}")
     response = lambdaClient.invoke(
         FunctionName=os.environ["DOCKER_IMAGE_BUILDER_FN_ARN"],
         Payload=json.dumps(
@@ -130,6 +173,7 @@ def handle_start_copy_docker_image(event: Dict[str, Any], context: Any) -> Dict[
     payload = response["Payload"].read()
     output_dict["image_info"] = json.loads(payload)
     output_dict["image_info"]["remaining_polls"] = 30
+    output_dict["image_info"]["image_status"] = "building"
     return output_dict
 
 
@@ -138,14 +182,22 @@ def handle_poll_docker_image_available(event: Dict[str, Any], context: Any) -> D
     output_dict = deepcopy(event)
 
     try:
+        # Use the appropriate repository name based on image type
+        repository_name = (
+            event["image_info"]["image_uri"]
+            if event["image_info"].get("image_type") == "ecr"
+            else os.environ["ECR_REPOSITORY_NAME"]
+        )
         ecrClient.describe_images(
-            repositoryName=os.environ["ECR_REPOSITORY_NAME"], imageIds=[{"imageTag": event["image_info"]["image_tag"]}]
+            repositoryName=repository_name, imageIds=[{"imageTag": event["image_info"]["image_tag"]}]
         )
     except ecrClient.exceptions.ImageNotFoundException:
         output_dict["continue_polling_docker"] = True
         output_dict["image_info"]["remaining_polls"] -= 1
         if output_dict["image_info"]["remaining_polls"] <= 0:
-            ec2Client.terminate_instances(InstanceIds=[event["image_info"]["instance_id"]])
+            # Only terminate EC2 instance if one exists (not for pre-existing ECR images)
+            if "instance_id" in event["image_info"]:
+                ec2Client.terminate_instances(InstanceIds=[event["image_info"]["instance_id"]])
             raise MaxPollsExceededException(
                 json.dumps(
                     {
@@ -157,7 +209,9 @@ def handle_poll_docker_image_available(event: Dict[str, Any], context: Any) -> D
         return output_dict
 
     output_dict["continue_polling_docker"] = False
-    ec2Client.terminate_instances(InstanceIds=[event["image_info"]["instance_id"]])
+    # Only terminate EC2 instance if one exists (not for pre-existing ECR images)
+    if "instance_id" in event["image_info"]:
+        ec2Client.terminate_instances(InstanceIds=[event["image_info"]["instance_id"]])
     return output_dict
 
 
@@ -178,11 +232,32 @@ def camelize_object(o):  # type: ignore[no-untyped-def]
 
     prepared_event = camelize_object(event)
     prepared_event["containerConfig"]["environment"] = event["containerConfig"]["environment"]
-    prepared_event["containerConfig"]["image"] = {
-        "repositoryArn": os.environ["ECR_REPOSITORY_ARN"],
-        "tag": event["image_info"]["image_tag"],
-        "type": "ecr",
-    }
+
+    # Handle ECR images differently - use the existing ECR image instead of the built one
+    if event["image_info"].get("image_type") == "ecr":
+        # For pre-existing ECR images, construct the ARN using the image repository
+        account_id = os.environ.get("AWS_ACCOUNT_ID", "")
+        if not account_id:
+            # Try to get account ID from the existing ECR repository ARN
+            ecr_repo_arn = os.environ.get("ECR_REPOSITORY_ARN", "")
+            if ecr_repo_arn:
+                account_id = ecr_repo_arn.split(":")[4]
+
+        repository_arn = (
+            f"arn:aws:ecr:{os.environ['AWS_REGION']}:{account_id}:repository/{event['image_info']['image_uri']}"
+        )
+        prepared_event["containerConfig"]["image"] = {
+            "repositoryArn": repository_arn,
+            "tag": event["image_info"]["image_tag"],
+            "type": "ecr",
+        }
+    else:
+        # For built images, use the default ECR repository
+        prepared_event["containerConfig"]["image"] = {
+            "repositoryArn": os.environ["ECR_REPOSITORY_ARN"],
+            "tag": event["image_info"]["image_tag"],
+            "type": "ecr",
+        }
 
     response = lambdaClient.invoke(
         FunctionName=os.environ["ECS_MODEL_DEPLOYER_FN_ARN"],

lambda/prompt_templates/lambda_functions.py

@@ -22,7 +22,8 @@
 
 import boto3
 from boto3.dynamodb.conditions import Attr, Key
-from utilities.common_functions import api_wrapper, get_groups, get_item, get_username, is_admin, retry_config
+from utilities.auth import get_username, is_admin
+from utilities.common_functions import api_wrapper, get_groups, get_item, retry_config
 
 from .models import PromptTemplateModel