llama-stack-mirror/llama_stack/distributions/postgres-demo/run.yaml
IAN MILLER 007efa6eb5
refactor: replace default all-MiniLM-L6-v2 embedding model by nomic-embed-text-v1.5 in Llama Stack (#3183)
# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
The purpose of this PR is to replace the Llama Stack's default embedding
model by nomic-embed-text-v1.5.

These are the key reasons why Llama Stack community decided to switch
from all-MiniLM-L6-v2 to nomic-embed-text-v1.5:
1. The training data for
[all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2#training-data)
includes a lot of data sets with various licensing terms, so it is
tricky to know when/whether it is appropriate to use this model for
commercial applications.
2. The model is not particularly competitive on major benchmarks. For
example, if you look at the [MTEB
Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) and click
on Miscellaneous/BEIR to see English information retrieval accuracy, you
see that the top of the leaderboard is dominated by enormous models but
also that there are many, many models of relatively modest size whith
much higher Retrieval scores. If you want to look closely at the data, I
recommend clicking "Download Table" because it is easier to browse that
way.

More discussion info can be founded
[here](https://github.com/llamastack/llama-stack/issues/2418)

<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
Closes #2418 

## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->
1. Run `./scripts/unit-tests.sh`
2. Integration tests via CI wokrflow

---------

Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
Co-authored-by: Sébastien Han <seb@redhat.com>
2025-10-14 10:44:20 -04:00

114 lines
3.4 KiB
YAML

version: 2
image_name: postgres-demo
apis:
- agents
- inference
- safety
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: vllm-inference
provider_type: remote::vllm
config:
url: ${env.VLLM_URL:=http://localhost:8000/v1}
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
api_token: ${env.VLLM_API_TOKEN:=fake}
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
vector_io:
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:=}
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/postgres-demo}/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: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
responses_store:
type: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
sinks: ${env.TELEMETRY_SINKS:=console,otel_trace}
otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=http://localhost:4318/v1/traces}
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
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
metadata_store:
type: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
table_name: ${env.POSTGRES_TABLE_NAME:=llamastack_kvstore}
inference_store:
type: postgres
host: ${env.POSTGRES_HOST:=localhost}
port: ${env.POSTGRES_PORT:=5432}
db: ${env.POSTGRES_DB:=llamastack}
user: ${env.POSTGRES_USER:=llamastack}
password: ${env.POSTGRES_PASSWORD:=llamastack}
conversations_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/postgres-demo}/conversations.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: vllm-inference
model_type: llm
- metadata:
embedding_dimension: 768
model_id: nomic-embed-text-v1.5
provider_id: sentence-transformers
model_type: embedding
shields:
- shield_id: meta-llama/Llama-Guard-3-8B
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
server:
port: 8321