mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-22 16:23:08 +00:00
feat(stores)!: use backend storage references instead of configs (#3697)
**This PR changes configurations in a backward incompatible way.**
Run configs today repeat full SQLite/Postgres snippets everywhere a
store is needed, which means duplicated credentials, extra connection
pools, and lots of drift between files. This PR introduces named storage
backends so the stack and providers can share a single catalog and
reference those backends by name.
## Key Changes
- Add `storage.backends` to `StackRunConfig`, register each KV/SQL
backend once at startup, and validate that references point to the right
family.
- Move server stores under `storage.stores` with lightweight references
(backend + namespace/table) instead of full configs.
- Update every provider/config/doc to use the new reference style;
docs/codegen now surface the simplified YAML.
## Migration
Before:
```yaml
metadata_store:
type: sqlite
db_path: ~/.llama/distributions/foo/registry.db
inference_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
conversations_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
```
After:
```yaml
storage:
backends:
kv_default:
type: kv_sqlite
db_path: ~/.llama/distributions/foo/kvstore.db
sql_default:
type: sql_postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
stores:
metadata:
backend: kv_default
namespace: registry
inference:
backend: sql_default
table_name: inference_store
max_write_queue_size: 10000
num_writers: 4
conversations:
backend: sql_default
table_name: openai_conversations
```
Provider configs follow the same pattern—for example, a Chroma vector
adapter switches from:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
kvstore:
type: sqlite
db_path: ~/.llama/distributions/foo/chroma.db
```
to:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
persistence:
backend: kv_default
namespace: vector_io::chroma_remote
```
Once the backends are declared, everything else just points at them, so
rotating credentials or swapping to Postgres happens in one place and
the stack reuses a single connection pool.
This commit is contained in:
Ashwin Bharambe
GitHub
parent
add64e8e2a
commit
2c43285e22
105 changed files with 2290 additions and 1292 deletions
|
|
@ -93,30 +93,30 @@ providers:
|
|||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/faiss_store.db
|
||||
persistence:
|
||||
namespace: vector_io::faiss
|
||||
backend: kv_default
|
||||
- provider_id: sqlite-vec
|
||||
provider_type: inline::sqlite-vec
|
||||
config:
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/sqlite_vec.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/sqlite_vec_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::sqlite_vec
|
||||
backend: kv_default
|
||||
- provider_id: ${env.MILVUS_URL:+milvus}
|
||||
provider_type: inline::milvus
|
||||
config:
|
||||
db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/ci-tests}/milvus.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/milvus_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::milvus
|
||||
backend: kv_default
|
||||
- provider_id: ${env.CHROMADB_URL:+chromadb}
|
||||
provider_type: remote::chromadb
|
||||
config:
|
||||
url: ${env.CHROMADB_URL:=}
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests/}/chroma_remote_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::chroma_remote
|
||||
backend: kv_default
|
||||
- provider_id: ${env.PGVECTOR_DB:+pgvector}
|
||||
provider_type: remote::pgvector
|
||||
config:
|
||||
|
|
@ -125,17 +125,17 @@ providers:
|
|||
db: ${env.PGVECTOR_DB:=}
|
||||
user: ${env.PGVECTOR_USER:=}
|
||||
password: ${env.PGVECTOR_PASSWORD:=}
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/pgvector_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::pgvector
|
||||
backend: kv_default
|
||||
files:
|
||||
- provider_id: meta-reference-files
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/ci-tests/files}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/files_metadata.db
|
||||
table_name: files_metadata
|
||||
backend: sql_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -147,12 +147,15 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/responses_store.db
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
post_training:
|
||||
- provider_id: torchtune-cpu
|
||||
provider_type: inline::torchtune-cpu
|
||||
|
|
@ -163,21 +166,21 @@ providers:
|
|||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/meta_reference_eval.db
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/huggingface_datasetio.db
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
|
|
@ -207,17 +210,28 @@ providers:
|
|||
provider_type: inline::reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/batches.db
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/inference_store.db
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/conversations.db
|
||||
namespace: batches
|
||||
backend: kv_default
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ci-tests}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models: []
|
||||
shields:
|
||||
- shield_id: llama-guard
|
||||
|
|
|
|||
|
|
@ -26,9 +26,9 @@ providers:
|
|||
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
|
||||
persistence:
|
||||
namespace: vector_io::chroma_remote
|
||||
backend: kv_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -38,32 +38,35 @@ providers:
|
|||
- 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
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
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
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/huggingface_datasetio.db
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
|
|
@ -86,15 +89,26 @@ providers:
|
|||
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
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/conversations.db
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
|
|
|
|||
|
|
@ -22,9 +22,9 @@ providers:
|
|||
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
|
||||
persistence:
|
||||
namespace: vector_io::chroma_remote
|
||||
backend: kv_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -34,32 +34,35 @@ providers:
|
|||
- 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
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
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
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/huggingface_datasetio.db
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
|
|
@ -82,15 +85,26 @@ providers:
|
|||
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
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/conversations.db
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
|
|
|
|||
|
|
@ -37,9 +37,9 @@ providers:
|
|||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/faiss_store.db
|
||||
persistence:
|
||||
namespace: vector_io::faiss
|
||||
backend: kv_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -49,32 +49,35 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/responses_store.db
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/meta_reference_eval.db
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/huggingface_datasetio.db
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
|
|
@ -99,15 +102,26 @@ providers:
|
|||
provider_type: inline::rag-runtime
|
||||
- provider_id: model-context-protocol
|
||||
provider_type: remote::model-context-protocol
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/inference_store.db
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/conversations.db
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
|
|
|
|||
|
|
@ -27,9 +27,9 @@ providers:
|
|||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/faiss_store.db
|
||||
persistence:
|
||||
namespace: vector_io::faiss
|
||||
backend: kv_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -39,32 +39,35 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/responses_store.db
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/meta_reference_eval.db
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/huggingface_datasetio.db
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
|
|
@ -89,15 +92,26 @@ providers:
|
|||
provider_type: inline::rag-runtime
|
||||
- provider_id: model-context-protocol
|
||||
provider_type: remote::model-context-protocol
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/inference_store.db
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/conversations.db
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
|
|
|
|||
|
|
@ -28,9 +28,9 @@ providers:
|
|||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/faiss_store.db
|
||||
persistence:
|
||||
namespace: vector_io::faiss
|
||||
backend: kv_default
|
||||
safety:
|
||||
- provider_id: nvidia
|
||||
provider_type: remote::nvidia
|
||||
|
|
@ -41,12 +41,15 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/responses_store.db
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
eval:
|
||||
- provider_id: nvidia
|
||||
provider_type: remote::nvidia
|
||||
|
|
@ -65,8 +68,8 @@ providers:
|
|||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
- provider_id: nvidia
|
||||
provider_type: remote::nvidia
|
||||
config:
|
||||
|
|
@ -86,17 +89,28 @@ providers:
|
|||
config:
|
||||
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/files_metadata.db
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/conversations.db
|
||||
table_name: files_metadata
|
||||
backend: sql_default
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
|
|
|
|||
|
|
@ -23,9 +23,9 @@ providers:
|
|||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/faiss_store.db
|
||||
persistence:
|
||||
namespace: vector_io::faiss
|
||||
backend: kv_default
|
||||
safety:
|
||||
- provider_id: nvidia
|
||||
provider_type: remote::nvidia
|
||||
|
|
@ -36,12 +36,15 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/responses_store.db
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
eval:
|
||||
- provider_id: nvidia
|
||||
provider_type: remote::nvidia
|
||||
|
|
@ -75,17 +78,28 @@ providers:
|
|||
config:
|
||||
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/nvidia/files}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/files_metadata.db
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/inference_store.db
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/conversations.db
|
||||
table_name: files_metadata
|
||||
backend: sql_default
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/nvidia}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models: []
|
||||
shields: []
|
||||
vector_dbs: []
|
||||
|
|
|
|||
|
|
@ -39,16 +39,16 @@ providers:
|
|||
provider_type: inline::sqlite-vec
|
||||
config:
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/sqlite_vec.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/sqlite_vec_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::sqlite_vec
|
||||
backend: kv_default
|
||||
- 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/open-benchmark}/chroma_remote_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::chroma_remote
|
||||
backend: kv_default
|
||||
- provider_id: ${env.ENABLE_PGVECTOR:+pgvector}
|
||||
provider_type: remote::pgvector
|
||||
config:
|
||||
|
|
@ -57,9 +57,9 @@ providers:
|
|||
db: ${env.PGVECTOR_DB:=}
|
||||
user: ${env.PGVECTOR_USER:=}
|
||||
password: ${env.PGVECTOR_PASSWORD:=}
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/pgvector_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::pgvector
|
||||
backend: kv_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -69,32 +69,35 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/responses_store.db
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/meta_reference_eval.db
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/huggingface_datasetio.db
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
|
|
@ -119,15 +122,26 @@ providers:
|
|||
provider_type: inline::rag-runtime
|
||||
- provider_id: model-context-protocol
|
||||
provider_type: remote::model-context-protocol
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/inference_store.db
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/conversations.db
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/open-benchmark}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: gpt-4o
|
||||
|
|
|
|||
|
|
@ -91,7 +91,6 @@ def get_distribution_template() -> DistributionTemplate:
|
|||
"embedding_dimension": 768,
|
||||
},
|
||||
)
|
||||
postgres_config = PostgresSqlStoreConfig.sample_run_config()
|
||||
return DistributionTemplate(
|
||||
name=name,
|
||||
distro_type="self_hosted",
|
||||
|
|
@ -105,22 +104,16 @@ def get_distribution_template() -> DistributionTemplate:
|
|||
provider_overrides={
|
||||
"inference": inference_providers + [embedding_provider],
|
||||
"vector_io": vector_io_providers,
|
||||
"agents": [
|
||||
Provider(
|
||||
provider_id="meta-reference",
|
||||
provider_type="inline::meta-reference",
|
||||
config=dict(
|
||||
persistence_store=postgres_config,
|
||||
responses_store=postgres_config,
|
||||
),
|
||||
)
|
||||
],
|
||||
},
|
||||
default_models=default_models + [embedding_model],
|
||||
default_tool_groups=default_tool_groups,
|
||||
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
|
||||
metadata_store=PostgresKVStoreConfig.sample_run_config(),
|
||||
inference_store=postgres_config,
|
||||
storage_backends={
|
||||
"kv_default": PostgresKVStoreConfig.sample_run_config(
|
||||
table_name="llamastack_kvstore",
|
||||
),
|
||||
"sql_default": PostgresSqlStoreConfig.sample_run_config(),
|
||||
},
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
|
|
|
|||
|
|
@ -22,9 +22,9 @@ providers:
|
|||
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
|
||||
persistence:
|
||||
namespace: vector_io::chroma_remote
|
||||
backend: kv_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -34,20 +34,15 @@ providers:
|
|||
- 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}
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
tool_runtime:
|
||||
- provider_id: brave-search
|
||||
provider_type: remote::brave-search
|
||||
|
|
@ -63,24 +58,35 @@ providers:
|
|||
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
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_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}
|
||||
sql_default:
|
||||
type: sql_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}
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: ${env.INFERENCE_MODEL}
|
||||
|
|
|
|||
|
|
@ -93,30 +93,30 @@ providers:
|
|||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/faiss_store.db
|
||||
persistence:
|
||||
namespace: vector_io::faiss
|
||||
backend: kv_default
|
||||
- provider_id: sqlite-vec
|
||||
provider_type: inline::sqlite-vec
|
||||
config:
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/sqlite_vec.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/sqlite_vec_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::sqlite_vec
|
||||
backend: kv_default
|
||||
- provider_id: ${env.MILVUS_URL:+milvus}
|
||||
provider_type: inline::milvus
|
||||
config:
|
||||
db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter-gpu}/milvus.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/milvus_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::milvus
|
||||
backend: kv_default
|
||||
- provider_id: ${env.CHROMADB_URL:+chromadb}
|
||||
provider_type: remote::chromadb
|
||||
config:
|
||||
url: ${env.CHROMADB_URL:=}
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu/}/chroma_remote_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::chroma_remote
|
||||
backend: kv_default
|
||||
- provider_id: ${env.PGVECTOR_DB:+pgvector}
|
||||
provider_type: remote::pgvector
|
||||
config:
|
||||
|
|
@ -125,17 +125,17 @@ providers:
|
|||
db: ${env.PGVECTOR_DB:=}
|
||||
user: ${env.PGVECTOR_USER:=}
|
||||
password: ${env.PGVECTOR_PASSWORD:=}
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/pgvector_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::pgvector
|
||||
backend: kv_default
|
||||
files:
|
||||
- provider_id: meta-reference-files
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter-gpu/files}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/files_metadata.db
|
||||
table_name: files_metadata
|
||||
backend: sql_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -147,12 +147,15 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/responses_store.db
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
post_training:
|
||||
- provider_id: huggingface-gpu
|
||||
provider_type: inline::huggingface-gpu
|
||||
|
|
@ -166,21 +169,21 @@ providers:
|
|||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/meta_reference_eval.db
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/huggingface_datasetio.db
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
|
|
@ -210,17 +213,28 @@ providers:
|
|||
provider_type: inline::reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/batches.db
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/inference_store.db
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/conversations.db
|
||||
namespace: batches
|
||||
backend: kv_default
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter-gpu}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models: []
|
||||
shields:
|
||||
- shield_id: llama-guard
|
||||
|
|
|
|||
|
|
@ -93,30 +93,30 @@ providers:
|
|||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/faiss_store.db
|
||||
persistence:
|
||||
namespace: vector_io::faiss
|
||||
backend: kv_default
|
||||
- provider_id: sqlite-vec
|
||||
provider_type: inline::sqlite-vec
|
||||
config:
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sqlite_vec_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::sqlite_vec
|
||||
backend: kv_default
|
||||
- provider_id: ${env.MILVUS_URL:+milvus}
|
||||
provider_type: inline::milvus
|
||||
config:
|
||||
db_path: ${env.MILVUS_DB_PATH:=~/.llama/distributions/starter}/milvus.db
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/milvus_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::milvus
|
||||
backend: kv_default
|
||||
- provider_id: ${env.CHROMADB_URL:+chromadb}
|
||||
provider_type: remote::chromadb
|
||||
config:
|
||||
url: ${env.CHROMADB_URL:=}
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter/}/chroma_remote_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::chroma_remote
|
||||
backend: kv_default
|
||||
- provider_id: ${env.PGVECTOR_DB:+pgvector}
|
||||
provider_type: remote::pgvector
|
||||
config:
|
||||
|
|
@ -125,17 +125,17 @@ providers:
|
|||
db: ${env.PGVECTOR_DB:=}
|
||||
user: ${env.PGVECTOR_USER:=}
|
||||
password: ${env.PGVECTOR_PASSWORD:=}
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/pgvector_registry.db
|
||||
persistence:
|
||||
namespace: vector_io::pgvector
|
||||
backend: kv_default
|
||||
files:
|
||||
- provider_id: meta-reference-files
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
|
||||
table_name: files_metadata
|
||||
backend: sql_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -147,12 +147,15 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/responses_store.db
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
post_training:
|
||||
- provider_id: torchtune-cpu
|
||||
provider_type: inline::torchtune-cpu
|
||||
|
|
@ -163,21 +166,21 @@ providers:
|
|||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/meta_reference_eval.db
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/huggingface_datasetio.db
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
|
|
@ -207,17 +210,28 @@ providers:
|
|||
provider_type: inline::reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/batches.db
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/inference_store.db
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/conversations.db
|
||||
namespace: batches
|
||||
backend: kv_default
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models: []
|
||||
shields:
|
||||
- shield_id: llama-guard
|
||||
|
|
|
|||
|
|
@ -29,6 +29,12 @@ from llama_stack.core.datatypes import (
|
|||
ToolGroupInput,
|
||||
)
|
||||
from llama_stack.core.distribution import get_provider_registry
|
||||
from llama_stack.core.storage.datatypes import (
|
||||
InferenceStoreReference,
|
||||
KVStoreReference,
|
||||
SqlStoreReference,
|
||||
StorageBackendType,
|
||||
)
|
||||
from llama_stack.core.utils.dynamic import instantiate_class_type
|
||||
from llama_stack.core.utils.image_types import LlamaStackImageType
|
||||
from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
|
||||
|
|
@ -180,10 +186,9 @@ class RunConfigSettings(BaseModel):
|
|||
default_tool_groups: list[ToolGroupInput] | None = None
|
||||
default_datasets: list[DatasetInput] | None = None
|
||||
default_benchmarks: list[BenchmarkInput] | None = None
|
||||
metadata_store: dict | None = None
|
||||
inference_store: dict | None = None
|
||||
conversations_store: dict | None = None
|
||||
telemetry: TelemetryConfig = Field(default_factory=lambda: TelemetryConfig(enabled=True))
|
||||
storage_backends: dict[str, Any] | None = None
|
||||
storage_stores: dict[str, Any] | None = None
|
||||
|
||||
def run_config(
|
||||
self,
|
||||
|
|
@ -226,6 +231,37 @@ class RunConfigSettings(BaseModel):
|
|||
# Get unique set of APIs from providers
|
||||
apis = sorted(providers.keys())
|
||||
|
||||
storage_backends = self.storage_backends or {
|
||||
"kv_default": SqliteKVStoreConfig.sample_run_config(
|
||||
__distro_dir__=f"~/.llama/distributions/{name}",
|
||||
db_name="kvstore.db",
|
||||
),
|
||||
"sql_default": SqliteSqlStoreConfig.sample_run_config(
|
||||
__distro_dir__=f"~/.llama/distributions/{name}",
|
||||
db_name="sql_store.db",
|
||||
),
|
||||
}
|
||||
|
||||
storage_stores = self.storage_stores or {
|
||||
"metadata": KVStoreReference(
|
||||
backend="kv_default",
|
||||
namespace="registry",
|
||||
).model_dump(exclude_none=True),
|
||||
"inference": InferenceStoreReference(
|
||||
backend="sql_default",
|
||||
table_name="inference_store",
|
||||
).model_dump(exclude_none=True),
|
||||
"conversations": SqlStoreReference(
|
||||
backend="sql_default",
|
||||
table_name="openai_conversations",
|
||||
).model_dump(exclude_none=True),
|
||||
}
|
||||
|
||||
storage_config = dict(
|
||||
backends=storage_backends,
|
||||
stores=storage_stores,
|
||||
)
|
||||
|
||||
# Return a dict that matches StackRunConfig structure
|
||||
return {
|
||||
"version": LLAMA_STACK_RUN_CONFIG_VERSION,
|
||||
|
|
@ -233,21 +269,7 @@ class RunConfigSettings(BaseModel):
|
|||
"container_image": container_image,
|
||||
"apis": apis,
|
||||
"providers": provider_configs,
|
||||
"metadata_store": self.metadata_store
|
||||
or SqliteKVStoreConfig.sample_run_config(
|
||||
__distro_dir__=f"~/.llama/distributions/{name}",
|
||||
db_name="registry.db",
|
||||
),
|
||||
"inference_store": self.inference_store
|
||||
or SqliteSqlStoreConfig.sample_run_config(
|
||||
__distro_dir__=f"~/.llama/distributions/{name}",
|
||||
db_name="inference_store.db",
|
||||
),
|
||||
"conversations_store": self.conversations_store
|
||||
or SqliteSqlStoreConfig.sample_run_config(
|
||||
__distro_dir__=f"~/.llama/distributions/{name}",
|
||||
db_name="conversations.db",
|
||||
),
|
||||
"storage": storage_config,
|
||||
"models": [m.model_dump(exclude_none=True) for m in (self.default_models or [])],
|
||||
"shields": [s.model_dump(exclude_none=True) for s in (self.default_shields or [])],
|
||||
"vector_dbs": [],
|
||||
|
|
@ -297,11 +319,15 @@ class DistributionTemplate(BaseModel):
|
|||
# We should have a better way to do this by formalizing the concept of "internal" APIs
|
||||
# and providers, with a way to specify dependencies for them.
|
||||
|
||||
if run_config_.get("inference_store"):
|
||||
additional_pip_packages.extend(get_sql_pip_packages(run_config_["inference_store"]))
|
||||
|
||||
if run_config_.get("metadata_store"):
|
||||
additional_pip_packages.extend(get_kv_pip_packages(run_config_["metadata_store"]))
|
||||
storage_cfg = run_config_.get("storage", {})
|
||||
for backend_cfg in storage_cfg.get("backends", {}).values():
|
||||
store_type = backend_cfg.get("type")
|
||||
if not store_type:
|
||||
continue
|
||||
if str(store_type).startswith("kv_"):
|
||||
additional_pip_packages.extend(get_kv_pip_packages(backend_cfg))
|
||||
elif str(store_type).startswith("sql_"):
|
||||
additional_pip_packages.extend(get_sql_pip_packages(backend_cfg))
|
||||
|
||||
if self.additional_pip_packages:
|
||||
additional_pip_packages.extend(self.additional_pip_packages)
|
||||
|
|
@ -387,11 +413,13 @@ class DistributionTemplate(BaseModel):
|
|||
def enum_representer(dumper, data):
|
||||
return dumper.represent_scalar("tag:yaml.org,2002:str", data.value)
|
||||
|
||||
# Register YAML representer for ModelType
|
||||
# Register YAML representer for enums
|
||||
yaml.add_representer(ModelType, enum_representer)
|
||||
yaml.add_representer(DatasetPurpose, enum_representer)
|
||||
yaml.add_representer(StorageBackendType, enum_representer)
|
||||
yaml.SafeDumper.add_representer(ModelType, enum_representer)
|
||||
yaml.SafeDumper.add_representer(DatasetPurpose, enum_representer)
|
||||
yaml.SafeDumper.add_representer(StorageBackendType, enum_representer)
|
||||
|
||||
for output_dir in [yaml_output_dir, doc_output_dir]:
|
||||
output_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
|
|
|||
|
|
@ -22,9 +22,9 @@ providers:
|
|||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/faiss_store.db
|
||||
persistence:
|
||||
namespace: vector_io::faiss
|
||||
backend: kv_default
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
|
|
@ -34,32 +34,35 @@ providers:
|
|||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/responses_store.db
|
||||
persistence:
|
||||
agent_state:
|
||||
namespace: agents
|
||||
backend: kv_default
|
||||
responses:
|
||||
table_name: responses
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/meta_reference_eval.db
|
||||
namespace: eval
|
||||
backend: kv_default
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/huggingface_datasetio.db
|
||||
namespace: datasetio::huggingface
|
||||
backend: kv_default
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/localfs_datasetio.db
|
||||
namespace: datasetio::localfs
|
||||
backend: kv_default
|
||||
scoring:
|
||||
- provider_id: basic
|
||||
provider_type: inline::basic
|
||||
|
|
@ -90,17 +93,28 @@ providers:
|
|||
config:
|
||||
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/distributions/watsonx/files}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/files_metadata.db
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/inference_store.db
|
||||
conversations_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/conversations.db
|
||||
table_name: files_metadata
|
||||
backend: sql_default
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/watsonx}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
max_write_queue_size: 10000
|
||||
num_writers: 4
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
models: []
|
||||
shields: []
|
||||
vector_dbs: []
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue