* feat: add argument for cpu arch in dockerfile * feat: add argument for cpu arch in docker compose * docs: add steps about cpu arch based docker build
2.1 KiB
How to use Dockerized Anything LLM
Use the Dockerized version of AnythingLLM for a much faster and complete startup of AnythingLLM.
Requirements
- Install Docker on your computer or machine.
How to install
-
git clone
this repo andcd anything-llm
to get to the root directory. -
yarn setup:envs
from repo root & fill out the.env
file that is then created in./docker/
-
cd docker/
-
To build the image, use any of these commands based on your CPU architecture.
This will use
amd64
(common on Windows/Intel Mac)docker-compose up -d --build
This will use
arm64
(M1/M2 Mac)ARCH=arm64 docker-compose up -d --build
This step will take a few moments on the first run.
Your docker host will show the image as online once the build process is completed. This will build the app to http://localhost:3001
.
How to use the user interface
- To access the full application, visit
http://localhost:3001
in your browser.
How to add files to my system
-
To run the collector scripts to grab external data (articles, URLs, etc.)
docker exec -it --workdir=/app/collector anything-llm python main.py
-
To run the collector on local documents you want to provide to it
docker exec -it --workdir=/app/collector anything-llm python watch.py
- Upload compliant files to
./collector/hotdir
and they will be processed and made available in the UI.
How to update and rebuild the ENV?
- Update the
./docker/.env
and rundocker-compose up -d --build
to rebuild with new environments.
⚠️ Vector DB support ⚠️
Out of the box, all vector databases are supported. Any vector databases requiring special configuration are listed below.
Using local ChromaDB with Dockerized AnythingLLM
- Ensure in your
./docker/.env
file that you have
#./docker/.env
...other configs
VECTOR_DB="chroma"
CHROMA_ENDPOINT='http://host.docker.internal:8000' # Allow docker to look on host port, not container.
...other configs