llama-stack-mirror/docs/source/distributions/self_hosted_distro/clarifai.md

orphan
true

Clarifai Distribution

:maxdepth: 2
:hidden:

self

The llamastack/distribution-clarifai distribution consists of the following provider configurations.

API	Provider(s)
agents	inline::meta-reference
datasetio	remote::huggingface, inline::localfs
eval	inline::meta-reference
inference	remote::clarifai
safety	inline::llama-guard
scoring	inline::basic, inline::llm-as-judge, inline::braintrust
telemetry	inline::meta-reference
tool_runtime	remote::brave-search, remote::tavily-search, inline::code-interpreter, inline::rag-runtime, remote::model-context-protocol
vector_io	inline::faiss

Environment Variables

The following environment variables can be configured:

• LLAMA_STACK_PORT: Port for the Llama Stack distribution server (default: 5001)
• CLARIFAI_PAT: Clarifai PAT (default: ``)

Models

The following models are available by default:

• meta/Llama-3/Llama-3-8B-Instruct (aliases: meta-llama/Llama-3-8B-Instruct)
• meta/Llama-3/llama-3-70B-Instruct (aliases: meta-llama/Llama-3-70B-Instruct)
• meta/Llama-3/llama-3_1-8b-instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)
• meta/Llama-3/llama-3_2-3b-instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)
• meta/Llama-3/llama-3_3-70b-instruct (aliases: meta-llama/Llama-3.3-70B-Instruct)

Prerequisite: PAT

Make sure you have access to a Clarifai PAT. You can get one by visiting Clarifai.

Running Llama Stack with Clarifai

You can do this via Conda (build code) or Docker which has a pre-built image.

Via Docker

This method allows you to get started quickly without having to build the distribution code.

LLAMA_STACK_PORT=5001
docker run \
  -it \
  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
  llamastack/distribution-clarifai \
  --port $LLAMA_STACK_PORT \
  --env CLARIFAI_PAT=$CLARIFAI_PAT

Via Conda

llama stack build --template clarifai --image-type conda
llama stack run ./run.yaml \
  --port $LLAMA_STACK_PORT \
  --env CLARIFAI_PAT=$CLARIFAI_PAT