mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-23 12:57:11 +00:00
6609d4ada4
# What does this PR do?
We want to bundle a bunch of (typically remote) providers in a distro
template and be able to configure them "on the fly" via environment
variables. So far, we have been able to do this with simple env var
replacements. However, sometimes you want to only conditionally enable
providers (because the relevant remote services may not be alive, or
relevant.) This was not possible until now.
To aid this, we add a simple (bash-like) env var replacement
enhancement: `${env.FOO+bar}` evaluates to `bar` if the variable is SET
and evaluates to empty string if it is not. On top of that, we update
our main resolver to ignore any provider whose ID is null.
This allows using the distro like this:
```bash
llama stack run dev --env CHROMADB_URL=http://localhost:6001 --env ENABLE_CHROMADB=1
```
when only Chroma is UP. This disables the other `pgvector` provider in
the run configuration.
## Test Plan
Hard code `chromadb` as the vector io provider inside
`test_vector_io.py` and run:
```bash
LLAMA_STACK_BASE_URL=http://localhost:8321 pytest -s -v tests/client-sdk/vector_io/ --embedding-model all-MiniLM-L6-v2
```
181 lines
5.1 KiB
YAML
181 lines
5.1 KiB
YAML
version: '2'
|
|
image_name: sambanova
|
|
apis:
|
|
- agents
|
|
- inference
|
|
- safety
|
|
- telemetry
|
|
- tool_runtime
|
|
- vector_io
|
|
providers:
|
|
inference:
|
|
- provider_id: sambanova
|
|
provider_type: remote::sambanova
|
|
config:
|
|
url: https://api.sambanova.ai/v1
|
|
api_key: ${env.SAMBANOVA_API_KEY}
|
|
vector_io:
|
|
- provider_id: faiss
|
|
provider_type: inline::faiss
|
|
config:
|
|
kvstore:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/faiss_store.db
|
|
- provider_id: ${env.ENABLE_CHROMADB+chromadb}
|
|
provider_type: remote::chromadb
|
|
config:
|
|
url: ${env.CHROMADB_URL:}
|
|
- provider_id: ${env.ENABLE_PGVECTOR+pgvector}
|
|
provider_type: remote::pgvector
|
|
config:
|
|
host: ${env.PGVECTOR_HOST:localhost}
|
|
port: ${env.PGVECTOR_PORT:5432}
|
|
db: ${env.PGVECTOR_DB:}
|
|
user: ${env.PGVECTOR_USER:}
|
|
password: ${env.PGVECTOR_PASSWORD:}
|
|
safety:
|
|
- provider_id: llama-guard
|
|
provider_type: inline::llama-guard
|
|
config: {}
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
type: sqlite
|
|
namespace: null
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/agents_store.db
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
|
|
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
|
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/sambanova/trace_store.db}
|
|
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: code-interpreter
|
|
provider_type: inline::code-interpreter
|
|
config: {}
|
|
- provider_id: rag-runtime
|
|
provider_type: inline::rag-runtime
|
|
config: {}
|
|
metadata_store:
|
|
type: sqlite
|
|
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/sambanova}/registry.db
|
|
models:
|
|
- metadata: {}
|
|
model_id: Meta-Llama-3.1-8B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.1-8B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-8B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.1-8B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: Meta-Llama-3.1-70B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.1-70B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-70B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.1-70B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: Meta-Llama-3.1-405B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.1-405B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.1-405B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: Meta-Llama-3.2-1B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.2-1B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-1B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.2-1B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: Meta-Llama-3.2-3B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.2-3B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-3B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.2-3B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: Meta-Llama-3.3-70B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.3-70B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.3-70B-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-3.3-70B-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: Llama-3.2-11B-Vision-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Llama-3.2-11B-Vision-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Llama-3.2-11B-Vision-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: Llama-3.2-90B-Vision-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Llama-3.2-90B-Vision-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
|
|
provider_id: sambanova
|
|
provider_model_id: Llama-3.2-90B-Vision-Instruct
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: Meta-Llama-Guard-3-8B
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-Guard-3-8B
|
|
model_type: llm
|
|
- metadata: {}
|
|
model_id: meta-llama/Llama-Guard-3-8B
|
|
provider_id: sambanova
|
|
provider_model_id: Meta-Llama-Guard-3-8B
|
|
model_type: llm
|
|
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
|
|
- toolgroup_id: builtin::code_interpreter
|
|
provider_id: code-interpreter
|
|
server:
|
|
port: 8321
|