Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/langchain-ai/langchain-aws-template
Build Generative AI applications with Langchain on AWS
https://github.com/langchain-ai/langchain-aws-template
aws cdk generative-ai langchain
Last synced: 5 days ago
JSON representation
Build Generative AI applications with Langchain on AWS
- Host: GitHub
- URL: https://github.com/langchain-ai/langchain-aws-template
- Owner: langchain-ai
- License: other
- Created: 2023-03-03T03:35:24.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-08-18T16:12:08.000Z (over 1 year ago)
- Last Synced: 2025-01-10T06:36:46.157Z (12 days ago)
- Topics: aws, cdk, generative-ai, langchain
- Language: Python
- Homepage:
- Size: 73.2 KB
- Stars: 175
- Watchers: 15
- Forks: 50
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# langchain-aws-template
This package contains code templates to deploy LLM applications built with LangChain to AWS. The templates contain both the infrastructure (CDK code) and the application code to run these services. At present, the following templates are included.1. **[Lambda Service](./service)**: An API Gateway + Lambda based REST service, that can connect to any front end application to create a chat like request-reply application. There is a demo web app included to interact with the deployed service.
2. **[Slack Bot](./slack_bot)**: An API Gateway + Lambda based REST service, that can process slack messages by calling an LLM chain and send reply to the slack channel where the bot is installed.
## Prerequisites
- nodejs 18+
- Python 3.9+
- aws-cdk toolkit (`npm install -g aws-cdk`)
- AWS account configured with credentials (https://docs.aws.amazon.com/cdk/v2/guide/getting_started.html#getting_started_prerequisites)
- openai api key saved in Secrets Manager in your AWS Account
- Expected secret name is `api-keys`
- openai key is expected to be stored with `openai-api-key` key
- conda (https://conda.io/projects/conda/en/latest/user-guide/install/index.html)