OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Infrastructure & Serving

Serverless Transformers On Aws Lambda

A Python repository of deployment pipelines for running Hugging Face Transformer NLP tasks as AWS Lambda functions, with container publishing through Amazon ECR and API exposure through API Gateway.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Serverless Transformers On Aws Lambda — OpenViST project profile in AI Infrastructure & Serving.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a documented starting point for packaging a listed Transformer NLP pipeline as a Lambda container and connecting the function to API Gateway.

Who it is for

  • Developers deploying Transformer-based NLP inference on AWS Lambda.
  • Teams configuring container builds and Lambda updates through GitHub Actions.

Documented uses

  • Deploy classification, token-classification, sentence-encoding, text-generation or zero-shot classification inference endpoints.
  • Build and publish Lambda container images to Amazon ECR through the documented CI/CD workflow.
  • Expose a Lambda inference function through API Gateway.
Before you choose

Requirements & limits

  • The documented deployment path uses AWS Lambda, Amazon ECR, API Gateway and GitHub Actions.
  • The workflow requires AWS credentials with ECR and Lambda access, plus Lambda IAM, timeout and memory configuration.
  • The README lists five pipeline types as available and marks translation as coming soon.
  • The README cites concurrency up to 1,000 as the default AWS limit; it does not guarantee that limit for a specific deployment.
  • The repository identifies its license as Apache-2.0.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare a pipeline for the documented AWS deployment workflow

Configure the repository and AWS resources needed for the documented build-and-deploy process.

Before you start

  • An AWS ECR repository
  • AWS credentials with access to ECR and Lambda, configured as repository secrets
  • A Lambda function, or permission and setup to create one, with an appropriate IAM role

Steps

  1. Clone the repository and retain the pipeline folder you want to use; modify its source and tests.

  2. Keep the corresponding GitHub Actions workflow and configure its directory, registry and Lambda function name.

  3. Create an ECR repository and update the ECR path in the workflow; configure the AWS access key and secret key as repository secrets.

  4. Push the code and create a pull request to trigger the documented container build, tests and ECR push; create the Lambda function if needed, then configure its timeout and memory.

  5. Create an API in API Gateway and link it to the Lambda function.

Expected outcome

The documented workflow builds and publishes a container for Lambda and links the function to an API Gateway API for calling the inference endpoint.

Guide limitations

  • The README says the workflow does not update Lambda with the new container on the first push.
  • Translation is marked as coming soon.
  • The README describes configuration steps but does not establish that a particular deployment will succeed.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
bhavsarpratik/serverless-transformers-on-aws-lambda · Official homepage title · retained in its source language
How we review sourcesSuggest a correction