mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-15 14:08:00 +00:00
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 7s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 7s
Integration Tests (Replay) / discover-tests (push) Successful in 9s
Vector IO Integration Tests / test-matrix (3.12, inline::milvus) (push) Failing after 11s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.12, remote::pgvector) (push) Failing after 20s
Vector IO Integration Tests / test-matrix (3.12, inline::sqlite-vec) (push) Failing after 18s
Vector IO Integration Tests / test-matrix (3.12, remote::weaviate) (push) Failing after 17s
Vector IO Integration Tests / test-matrix (3.13, inline::milvus) (push) Failing after 16s
Test Llama Stack Build / generate-matrix (push) Successful in 6s
Vector IO Integration Tests / test-matrix (3.13, inline::sqlite-vec) (push) Failing after 14s
Vector IO Integration Tests / test-matrix (3.13, remote::pgvector) (push) Failing after 12s
Vector IO Integration Tests / test-matrix (3.12, remote::chromadb) (push) Failing after 27s
Test Llama Stack Build / build-single-provider (push) Failing after 6s
Vector IO Integration Tests / test-matrix (3.12, remote::qdrant) (push) Failing after 26s
Vector IO Integration Tests / test-matrix (3.13, inline::faiss) (push) Failing after 24s
Vector IO Integration Tests / test-matrix (3.12, inline::faiss) (push) Failing after 29s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (3.13, remote::chromadb) (push) Failing after 15s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 9s
Python Package Build Test / build (3.13) (push) Failing after 6s
Vector IO Integration Tests / test-matrix (3.13, remote::weaviate) (push) Failing after 14s
Python Package Build Test / build (3.12) (push) Failing after 9s
Vector IO Integration Tests / test-matrix (3.13, remote::qdrant) (push) Failing after 16s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 10s
Test External API and Providers / test-external (venv) (push) Failing after 11s
Unit Tests / unit-tests (3.12) (push) Failing after 13s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 11s
Test Llama Stack Build / build (push) Failing after 8s
Unit Tests / unit-tests (3.13) (push) Failing after 37s
Pre-commit / pre-commit (push) Successful in 1m44s
# What does this PR do? - Added kvstore config to ChromaDB provider config for Dell distribution similar to [starter config](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/distributions/starter/run.yaml#L110-L112) - Fixed [error](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/inference/_generated/_async_client.py#L3424-L3425) getting endpoint information by adding `hf-inference` as the provider to the `AsyncInferenceClient` (TGI client). ## Test Plan ``` export INFERENCE_PORT=8181 export DEH_URL=http://0.0.0.0:$INFERENCE_PORT export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct export CHROMADB_HOST=localhost export CHROMADB_PORT=8000 export CHROMA_URL=http://$CHROMADB_HOST:$CHROMADB_PORT export CUDA_VISIBLE_DEVICES=0 export LLAMA_STACK_PORT=8321 export HF_TOKEN=[redacted] # TGI Server docker run --rm -it \ --pull always \ --network host \ -v $HOME/.cache/huggingface:/data \ -e HF_TOKEN=$HF_TOKEN \ -e PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \ -p $INFERENCE_PORT:$INFERENCE_PORT \ --gpus all \ ghcr.io/huggingface/text-generation-inference:latest \ --dtype float16 \ --usage-stats off \ --sharded false \ --cuda-memory-fraction 0.8 \ --model-id meta-llama/Llama-3.2-3B-Instruct \ --port $INFERENCE_PORT \ --hostname 0.0.0.0 # Chrome DB docker run --rm -it \ --name chromadb \ --net=host -p 8000:8000 \ -v ~/chroma:/chroma/chroma \ -e IS_PERSISTENT=TRUE \ -e ANONYMIZED_TELEMETRY=FALSE \ chromadb/chroma:latest # Llama Stack llama stack run dell \ --port $LLAMA_STACK_PORT \ --env INFERENCE_MODEL=$INFERENCE_MODEL \ --env DEH_URL=$DEH_URL \ --env CHROMA_URL=$CHROMA_URL ``` --------- Co-authored-by: Connor Hack <connorhack@fb.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
121 lines
3.3 KiB
YAML
121 lines
3.3 KiB
YAML
version: 2
|
|
image_name: dell
|
|
apis:
|
|
- agents
|
|
- datasetio
|
|
- eval
|
|
- inference
|
|
- safety
|
|
- scoring
|
|
- telemetry
|
|
- tool_runtime
|
|
- vector_io
|
|
providers:
|
|
inference:
|
|
- provider_id: tgi0
|
|
provider_type: remote::tgi
|
|
config:
|
|
url: ${env.DEH_URL}
|
|
- provider_id: sentence-transformers
|
|
provider_type: inline::sentence-transformers
|
|
vector_io:
|
|
- provider_id: chromadb
|
|
provider_type: remote::chromadb
|
|
config:
|
|
url: ${env.CHROMADB_URL:=}
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell/}/chroma_remote_registry.db
|
|
safety:
|
|
- provider_id: llama-guard
|
|
provider_type: inline::llama-guard
|
|
config:
|
|
excluded_categories: []
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/agents_store.db
|
|
responses_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/responses_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
|
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/trace_store.db
|
|
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
|
|
eval:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/meta_reference_eval.db
|
|
datasetio:
|
|
- provider_id: huggingface
|
|
provider_type: remote::huggingface
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/huggingface_datasetio.db
|
|
- provider_id: localfs
|
|
provider_type: inline::localfs
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/localfs_datasetio.db
|
|
scoring:
|
|
- provider_id: basic
|
|
provider_type: inline::basic
|
|
- provider_id: llm-as-judge
|
|
provider_type: inline::llm-as-judge
|
|
- provider_id: braintrust
|
|
provider_type: inline::braintrust
|
|
config:
|
|
openai_api_key: ${env.OPENAI_API_KEY:=}
|
|
tool_runtime:
|
|
- provider_id: brave-search
|
|
provider_type: remote::brave-search
|
|
config:
|
|
api_key: ${env.BRAVE_SEARCH_API_KEY:=}
|
|
max_results: 3
|
|
- provider_id: tavily-search
|
|
provider_type: remote::tavily-search
|
|
config:
|
|
api_key: ${env.TAVILY_SEARCH_API_KEY:=}
|
|
max_results: 3
|
|
- provider_id: rag-runtime
|
|
provider_type: inline::rag-runtime
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/registry.db
|
|
inference_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/inference_store.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: ${env.INFERENCE_MODEL}
|
|
provider_id: tgi0
|
|
model_type: llm
|
|
- metadata:
|
|
embedding_dimension: 384
|
|
model_id: all-MiniLM-L6-v2
|
|
provider_id: sentence-transformers
|
|
model_type: embedding
|
|
shields: []
|
|
vector_dbs: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
benchmarks: []
|
|
tool_groups:
|
|
- toolgroup_id: builtin::websearch
|
|
provider_id: brave-search
|
|
- toolgroup_id: builtin::rag
|
|
provider_id: rag-runtime
|
|
server:
|
|
port: 8321
|