This project uses the EXLA backend for Nx. While it has support for computing on GPU, it will not be able to do so without proper configuration. This section will explain how to get EXLA running on a CUDA capable GPU. For further reading (for example, running the app on other architectures, there seems to be an experimental support for ROCm among others), refer to the EXLA documentation and XLA binaries documentation.
You can find it out either with nVidia's GUI tools or with the nvidia-smi command.
The official releases are available here: CUDA, cuDNN. For many platforms, there are special considerations and configuration needed - refer to online documentation for there.
For platforms which are not oficially supported (such as Arch Linux or NixOS) there are community packages available.
If prebuilt XLA bineries for the CUDA version your GPU supports is also available on XLA, you need to export several environment variables. Before doing so, make sure there are no old versions of binaries:
mix deps.clean xla exlaThen, export these variables with correct values. Refer to the documentation to find out what values your platform needs.
export CUDA_HOME="/opt/cuda" # path to where the CUDA libraries have been installed to
export PATH="/opt/cuda/bin:$PATH" # possibly optional
export XLA_TARGET=cuda120 # depending on the CUDA version on your GPU
export ELIXIR_ERL_OPTIONS="+sssdio 128" # grant additional stack space for the XLA compiler
export TF_CUDA_VERSION="12.2" # possibly optional, couldn't get it to work without it, though. Depends on CUDA version
export XLA_FLAGS=--xla_gpu_cuda_data_dir=/opt/cuda # path to where CUDA libraries have been installed toAfter restarting the shell or sourcing appropriate files to update the environment, download and build the libraries again:
$ mix deps.get
$ mix deps.compileYou can check whether it works by launhing the ElixirChatbotCore app in interactive mode:
$ iex -S mixiex(1)> Nx.tensor([1, 2, 3])
#Nx.Tensor<
s64[3]
EXLA.Backend<cuda:0, 0.3902074192.828768286.3250>
[1, 2, 3]
>
While the ElixirChatbotCore app does provide the functionality needed to create a database, a utility module Tests.DocsFetcher in the tests app is provided. It exports the fetch_documentation function, which streamlines documentation preprocessing and database creation.
To use the package, simply enter the interactive Elixir prompt and call the function with the database name and relevant options.
$ cd apps/tests
$ iex -S mixiex(1)> Tests.DocsFetcher.fetch_documentation("db-1", headings_split: 1) # no preprocessing
iex(2)> Tests.DocsFetcher.fetch_documentation("db-2", headings_split: 2, prepend_parent_heading: true, max_token_count: 256) # split with respect to Markdown subheadings, prepend parent heading to fragments and limit fragment length to 256 words
iex(3)> Tests.DocsFetcher.fetch_documentation("db-3", headings_split: 1, allowed_modules: Application.spec(:elixir, :modules)) # fetch core Elixir docs only
The databases will be created in the <project_root>/tmp directory by default.
To run this project, install all necessary dependencies using mix and npm:
$ mix deps.get
$ cd apps/chat_web
$ npm install highlight.js --prefix assetsTo use OpenAI models within our project, you have to create an OpenAI account and configure your OpenAI API Key. Step-by-step instructions can be found in OpenAI Documentation.
To run this project, simply proceed to chat_web app and use mix:
$ cd apps/chat_web
$ mix phx.server