AWS Serverless update (#1115)

* update deepsparse version

* cleanup

Author: InquestGeronimo

examples/aws-serverless/README.md

@@ -90,7 +90,7 @@ python endpoint.py create-realtime
 
 #### Call Realtime Endpoint
 
-After the endpoint has been staged (~3 minute), AWS SAM will provide your API Gateway endpoint URL in CLI. You can start making requests by passing this URL into the LambdaClient object. Afterwards, you can run inference by passing in your text input:
+After the endpoint has been staged (~3 minutes), AWS SAM will provide your API Gateway endpoint URL in terminal. You can start making requests by passing this URL into the LambdaClient object. Afterwards, you can run inference by passing in your text input:
 
 ```python
 from client import LambdaClient

examples/aws-serverless/batch/app_inf/requirements.txt

@@ -1,3 +1,2 @@
 boto3>=1.18.34
-https://github.com/neuralmagic/transformers/releases/download/v1.4/transformers-4.23.1-py3-none-any.whl
-deepsparse>=1.4.0
+deepsparse[transformers]>=1.5.2

examples/aws-serverless/realtime/app/Dockerfile

@@ -1,27 +1,19 @@
-# Pull the base image with python 3.8 as a runtime for your Lambda
-FROM public.ecr.aws/lambda/python:3.8
+# Pull the base image with python 3.10 as a runtime for your Lambda
+FROM public.ecr.aws/lambda/python:3.10.2023.07.11.09
 
-ENV VIRTUAL_ENV=/venv
-ENV PATH="$VIRTUAL_ENV/bin:$PATH"
-
-COPY topo-four-core.json ./
-ENV NM_ARCH_FILE=./topo-four-core.json
-
-# Copy the earlier created requirements.txt file to the container
+# Copy the requirements.txt file to the container
 COPY requirements.txt ./
 
 # Install the python requirements from requirements.txt
-RUN python3 -m venv $VIRTUAL_ENV && \
-    pip install --no-cache-dir --upgrade pip && \
-    python3.8 -m pip install -r requirements.txt
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install -r requirements.txt
 
 # Copy the earlier created app.py file to the container
 COPY app.py ./
 
-# Load the BERT model from SparseZoo and store it in the model directory
+# Load model from SparseZoo and store it in the model directory
 RUN mkdir model
 
-# RUN sparsezoo.download zoo:nlp/question_answering/distilbert-none/pytorch/huggingface/squad/pruned80_quant-none-vnni --save-dir ./model
 RUN sparsezoo.download zoo:nlp/sentiment_analysis/obert-base/pytorch/huggingface/sst2/pruned90_quant-none --save-dir ./model
 
 # Set the CMD to your handler

examples/aws-serverless/realtime/app/requirements.txt

@@ -1,2 +1 @@
-https://github.com/neuralmagic/transformers/releases/download/v1.4/transformers-4.23.1-py3-none-any.whl
-deepsparse>=1.2.0
+deepsparse[transformers]>=1.5.2

examples/aws-serverless/realtime/app/topo-four-core.json

@@ -7,7 +7,7 @@ Resources:
     Type: AWS::Serverless::Function
     Properties:
       PackageType: Image
-      ImageUri: deepsparseendpoint:python3.8-v1
+      ImageUri: deepsparseendpoint:python3.10-v1
       MemorySize: 2000
       Timeout: 300
       Role: !GetAtt LambdaExecutionRole.Arn
@@ -21,7 +21,7 @@ Resources:
     Metadata:
       Dockerfile: Dockerfile
       DockerContext: ./app
-      DockerTag: python3.8-v1
+      DockerTag: python3.10-v1
 
   LambdaExecutionRole:
     Type: AWS::IAM::Role