A collection of notebooks for the course DLAI LangChain for LLM Applications & Chat with Data with local environment setup
- Learn the fundamentals of LLM and LangChain toolkits.
- Understand the prompt and Chains
- Understand how to develop the Chat with Data Applications with LangChain
- Collection of Notebooks
- Local venev setup using Poetry
- Docker Support with Optimisation Cache etc
- Run the Notebook Server with Docker
This repo contains
notebooks\langchain
: LangChain for LLM Application Developmentnotebooks\chat-data
: LangChain: Chat with Your Data
- Sign up on https://platform.openai.com/
- Generate OpenAI API keys
dotenv
can also be used to setup the key. Use theenv.example
to createenv
file
- Clone the repository📂
git clone https://github.com/amjadraza/dlai-langchain.git
- Install dependencies with Poetry and activate virtual environment🔨
poetry install
poetry shell
- Copy and Modify
env.example
to.env
Generate the HF API Key to be able to hosted models for inference and set the variables accordingly.
- Run the JupyterLab server🚀
jupyter lab
This project includes Dockerfile
to run the app in Docker container. In order to optimise the Docker Image
size and building time with cache techniques, I have follow tricks in below Article
https://medium.com/@albertazzir/blazing-fast-python-docker-builds-with-poetry-a78a66f5aed0
Build the docker container
docker build . -t dlai-langchain:latest
To generate Image with DOCKER_BUILDKIT
, follow below command
DOCKER_BUILDKIT=1 docker build --target=runtime . -t dlai-langchain:latest
- Run the docker container directly
docker run -d --name dlai-langchain -p 8888:8888 dlai-langchain:latest
- Run the docker container using docker-compose (Recommended)
docker-compose up
Make sure to include the
.env
SECRETS file when running withdocker-compose
with your own Keys.
As dlai-hf-course:latest
is a template project with minimal example. Report issues if you face any.
We have collected the Notebooks from original course and edited for few lines/functions to make them run locally.
We must give credit to Course Instructores Harrison Chase