forked from phoenix-oss/llama-stack-mirror
22dc684da6
# What does this PR do? This PR adds SambaNova as one of the Provider - Add SambaNova as a provider ## Test Plan Test the functional command ``` pytest -s -v --providers inference=sambanova llama_stack/providers/tests/inference/test_embeddings.py llama_stack/providers/tests/inference/test_prompt_adapter.py llama_stack/providers/tests/inference/test_text_inference.py llama_stack/providers/tests/inference/test_vision_inference.py --env SAMBANOVA_API_KEY=<sambanova-api-key> ``` Test the distribution template: ``` # Docker LLAMA_STACK_PORT=5001 docker run -it -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \ llamastack/distribution-sambanova \ --port $LLAMA_STACK_PORT \ --env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY # Conda llama stack build --template sambanova --image-type conda llama stack run ./run.yaml \ --port $LLAMA_STACK_PORT \ --env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY ``` ## Source [SambaNova API Documentation](https://cloud.sambanova.ai/apis) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [Y] Ran pre-commit to handle lint / formatting issues. - [Y] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [Y] Updated relevant documentation. - [Y ] Wrote necessary unit or integration tests. --------- Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
16 lines
474 B
YAML
16 lines
474 B
YAML
services:
|
|
llamastack:
|
|
image: llamastack/distribution-sambanova
|
|
network_mode: "host"
|
|
volumes:
|
|
- ~/.llama:/root/.llama
|
|
- ./run.yaml:/root/llamastack-run-sambanova.yaml
|
|
ports:
|
|
- "5000:5000"
|
|
entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-sambanova.yaml"
|
|
deploy:
|
|
restart_policy:
|
|
condition: on-failure
|
|
delay: 3s
|
|
max_attempts: 5
|
|
window: 60s
|