phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 08:49:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/main' into stainless

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-20 14:28:53 -07:00
commit a7baebbb09
191 changed files with 13295 additions and 7926 deletions
Download patch file Download diff file Expand all files Collapse all files

28
docs/docs/building_applications/rag.mdx
View file

@ -88,18 +88,19 @@ Llama Stack provides OpenAI-compatible RAG capabilities through:
To enable automatic vector store creation without specifying embedding models, configure a default embedding model in your run.yaml like so:
```yaml
models:
- model_id: nomic-ai/nomic-embed-text-v1.5
provider_id: inline::sentence-transformers
metadata:
embedding_dimension: 768
default_configured: true
vector_stores:
default_provider_id: faiss
default_embedding_model:
provider_id: sentence-transformers
model_id: nomic-ai/nomic-embed-text-v1.5
```
With this configuration:
- `client.vector_stores.create()` works without requiring embedding model parameters
- The system automatically uses the default model and its embedding dimension for any newly created vector store
- Only one model can be marked as `default_configured: true`
- `client.vector_stores.create()` works without requiring embedding model or provider parameters
- The system automatically uses the default vector store provider (`faiss`) when multiple providers are available
- The system automatically uses the default embedding model (`sentence-transformers/nomic-ai/nomic-embed-text-v1.5`) for any newly created vector store
- The `default_provider_id` specifies which vector storage backend to use
- The `default_embedding_model` specifies both the inference provider and model for embeddings
## Vector Store Operations
@ -108,14 +109,15 @@ With this configuration:
You can create vector stores with automatic or explicit embedding model selection:
```python
# Automatic - uses default configured embedding model
# Automatic - uses default configured embedding model and vector store provider
vs = client.vector_stores.create()
# Explicit - specify embedding model when you need a specific one
# Explicit - specify embedding model and/or provider when you need specific ones
vs = client.vector_stores.create(
extra_body={
"embedding_model": "nomic-ai/nomic-embed-text-v1.5",
"embedding_dimension": 768
"provider_id": "faiss", # Optional: specify vector store provider
"embedding_model": "sentence-transformers/nomic-ai/nomic-embed-text-v1.5",
"embedding_dimension": 768 # Optional: will be auto-detected if not provided
}
)
```

30
docs/docs/distributions/configuration.mdx
View file

@ -44,18 +44,32 @@ providers:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/agents_store.db
persistence:
agent_state:
backend: kv_default
namespace: agents
responses:
backend: sql_default
table_name: responses
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config: {}
metadata_store:
namespace: null
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/registry.db
storage:
backends:
kv_default:
type: kv_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/kvstore.db
sql_default:
type: sql_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/ollama}/sqlstore.db
references:
metadata:
backend: kv_default
namespace: registry
inference:
backend: sql_default
table_name: inference_store
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

201
docs/docs/distributions/k8s/stack-configmap.yaml
View file

@ -1,56 +1,155 @@
apiVersion: v1
data:
stack_run_config.yaml: "version: '2'\nimage_name: kubernetes-demo\napis:\n- agents\n-
inference\n- files\n- safety\n- telemetry\n- tool_runtime\n- vector_io\nproviders:\n
\ inference:\n - provider_id: vllm-inference\n provider_type: remote::vllm\n
\ config:\n url: ${env.VLLM_URL:=http://localhost:8000/v1}\n max_tokens:
${env.VLLM_MAX_TOKENS:=4096}\n api_token: ${env.VLLM_API_TOKEN:=fake}\n tls_verify:
${env.VLLM_TLS_VERIFY:=true}\n - provider_id: vllm-safety\n provider_type:
remote::vllm\n config:\n url: ${env.VLLM_SAFETY_URL:=http://localhost:8000/v1}\n
\ max_tokens: ${env.VLLM_MAX_TOKENS:=4096}\n api_token: ${env.VLLM_API_TOKEN:=fake}\n
\ tls_verify: ${env.VLLM_TLS_VERIFY:=true}\n - provider_id: sentence-transformers\n
\ provider_type: inline::sentence-transformers\n config: {}\n vector_io:\n
\ - provider_id: ${env.ENABLE_CHROMADB:+chromadb}\n provider_type: remote::chromadb\n
\ config:\n url: ${env.CHROMADB_URL:=}\n kvstore:\n type: postgres\n
\ host: ${env.POSTGRES_HOST:=localhost}\n port: ${env.POSTGRES_PORT:=5432}\n
\ db: ${env.POSTGRES_DB:=llamastack}\n user: ${env.POSTGRES_USER:=llamastack}\n
\ password: ${env.POSTGRES_PASSWORD:=llamastack}\n files:\n - provider_id:
meta-reference-files\n provider_type: inline::localfs\n config:\n storage_dir:
${env.FILES_STORAGE_DIR:=~/.llama/distributions/starter/files}\n metadata_store:\n
\ type: sqlite\n db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/starter}/files_metadata.db
\ \n safety:\n - provider_id: llama-guard\n provider_type: inline::llama-guard\n
\ config:\n excluded_categories: []\n agents:\n - provider_id: meta-reference\n
\ provider_type: inline::meta-reference\n config:\n persistence_store:\n
\ type: postgres\n host: ${env.POSTGRES_HOST:=localhost}\n port:
${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n user:
${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\n
\ responses_store:\n type: postgres\n host: ${env.POSTGRES_HOST:=localhost}\n
\ port: ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n
\ user: ${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\n
\ telemetry:\n - provider_id: meta-reference\n provider_type: inline::meta-reference\n
\ config:\n service_name: \"${env.OTEL_SERVICE_NAME:=\\u200B}\"\n sinks:
${env.TELEMETRY_SINKS:=console}\n tool_runtime:\n - provider_id: brave-search\n
\ provider_type: remote::brave-search\n config:\n api_key: ${env.BRAVE_SEARCH_API_KEY:+}\n
\ max_results: 3\n - provider_id: tavily-search\n provider_type: remote::tavily-search\n
\ config:\n api_key: ${env.TAVILY_SEARCH_API_KEY:+}\n max_results:
3\n - provider_id: rag-runtime\n provider_type: inline::rag-runtime\n config:
{}\n - provider_id: model-context-protocol\n provider_type: remote::model-context-protocol\n
\ config: {}\nmetadata_store:\n type: postgres\n host: ${env.POSTGRES_HOST:=localhost}\n
\ port: ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n user:
${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\n
\ table_name: llamastack_kvstore\ninference_store:\n type: postgres\n host:
${env.POSTGRES_HOST:=localhost}\n port: ${env.POSTGRES_PORT:=5432}\n db: ${env.POSTGRES_DB:=llamastack}\n
\ user: ${env.POSTGRES_USER:=llamastack}\n password: ${env.POSTGRES_PASSWORD:=llamastack}\nmodels:\n-
metadata:\n embedding_dimension: 384\n model_id: all-MiniLM-L6-v2\n provider_id:
sentence-transformers\n model_type: embedding\n- metadata: {}\n model_id: ${env.INFERENCE_MODEL}\n
\ provider_id: vllm-inference\n model_type: llm\n- metadata: {}\n model_id:
${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}\n provider_id: vllm-safety\n
\ model_type: llm\nshields:\n- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}\nvector_dbs:
[]\ndatasets: []\nscoring_fns: []\nbenchmarks: []\ntool_groups:\n- toolgroup_id:
builtin::websearch\n provider_id: tavily-search\n- toolgroup_id: builtin::rag\n
\ provider_id: rag-runtime\nserver:\n port: 8321\n auth:\n provider_config:\n
\ type: github_token\n"
stack_run_config.yaml: |
version: '2'
image_name: kubernetes-demo
apis:
- agents
- inference
- files
- 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: vllm-safety
provider_type: remote::vllm
config:
url: ${env.VLLM_SAFETY_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
config: {}
vector_io:
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:=}
kvstore:
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}
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
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}
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
config: {}
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
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}
references:
metadata:
backend: kv_default
namespace: registry
inference:
backend: sql_default
table_name: inference_store
models:
- metadata:
embedding_dimension: 768
model_id: nomic-embed-text-v1.5
provider_id: sentence-transformers
model_type: embedding
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: vllm-inference
model_type: llm
- metadata: {}
model_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
provider_id: vllm-safety
model_type: llm
shields:
- shield_id: ${env.SAFETY_MODEL:=meta-llama/Llama-Guard-3-1B}
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
auth:
provider_config:
type: github_token
kind: ConfigMap
metadata:
creationTimestamp: null
name: llama-stack-config

39
docs/docs/distributions/k8s/stack_run_config.yaml
View file

@ -93,21 +93,30 @@ providers:
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
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: 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}
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}
references:
metadata:
backend: kv_default
namespace: registry
inference:
backend: sql_default
table_name: inference_store
models:
- metadata:
embedding_dimension: 768

18
docs/docs/providers/agents/inline_meta-reference.mdx
View file

@ -14,16 +14,18 @@ Meta's reference implementation of an agent system that can use tools, access ve
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `persistence_store` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | |
| `responses_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite | |
| `persistence` | `<class 'inline.agents.meta_reference.config.AgentPersistenceConfig'>` | No | | |
## Sample Configuration
```yaml
persistence_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/agents_store.db
responses_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/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
```

6
docs/docs/providers/batches/inline_reference.mdx
View file

@ -14,7 +14,7 @@ Reference implementation of batches API with KVStore persistence.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Configuration for the key-value store backend. |
| `kvstore` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | Configuration for the key-value store backend. |
| `max_concurrent_batches` | `<class 'int'>` | No | 1 | Maximum number of concurrent batches to process simultaneously. |
| `max_concurrent_requests_per_batch` | `<class 'int'>` | No | 10 | Maximum number of concurrent requests to process per batch. |
@ -22,6 +22,6 @@ Reference implementation of batches API with KVStore persistence.
```yaml
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/batches.db
namespace: batches
backend: kv_default
```

6
docs/docs/providers/datasetio/inline_localfs.mdx
View file

@ -14,12 +14,12 @@ Local filesystem-based dataset I/O provider for reading and writing datasets to
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | |
| `kvstore` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | |
## Sample Configuration
```yaml
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/localfs_datasetio.db
namespace: datasetio::localfs
backend: kv_default
```

6
docs/docs/providers/datasetio/remote_huggingface.mdx
View file

@ -14,12 +14,12 @@ HuggingFace datasets provider for accessing and managing datasets from the Huggi
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | |
| `kvstore` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | |
## Sample Configuration
```yaml
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/huggingface_datasetio.db
namespace: datasetio::huggingface
backend: kv_default
```

6
docs/docs/providers/eval/inline_meta-reference.mdx
View file

@ -14,12 +14,12 @@ Meta's reference implementation of evaluation tasks with support for multiple la
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | |
| `kvstore` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | |
## Sample Configuration
```yaml
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/meta_reference_eval.db
namespace: eval
backend: kv_default
```

6
docs/docs/providers/files/inline_localfs.mdx
View file

@ -15,7 +15,7 @@ Local filesystem-based file storage provider for managing files and documents lo
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `storage_dir` | `<class 'str'>` | No | | Directory to store uploaded files |
| `metadata_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite | SQL store configuration for file metadata |
| `metadata_store` | `<class 'llama_stack.core.storage.datatypes.SqlStoreReference'>` | No | | SQL store configuration for file metadata |
| `ttl_secs` | `<class 'int'>` | No | 31536000 | |
## Sample Configuration
@ -23,6 +23,6 @@ Local filesystem-based file storage provider for managing files and documents lo
```yaml
storage_dir: ${env.FILES_STORAGE_DIR:=~/.llama/dummy/files}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/files_metadata.db
table_name: files_metadata
backend: sql_default
```

6
docs/docs/providers/files/remote_s3.mdx
View file

@ -20,7 +20,7 @@ AWS S3-based file storage provider for scalable cloud file management with metad
| `aws_secret_access_key` | `str \| None` | No | | AWS secret access key (optional if using IAM roles) |
| `endpoint_url` | `str \| None` | No | | Custom S3 endpoint URL (for MinIO, LocalStack, etc.) |
| `auto_create_bucket` | `<class 'bool'>` | No | False | Automatically create the S3 bucket if it doesn't exist |
| `metadata_store` | `utils.sqlstore.sqlstore.SqliteSqlStoreConfig \| utils.sqlstore.sqlstore.PostgresSqlStoreConfig` | No | sqlite | SQL store configuration for file metadata |
| `metadata_store` | `<class 'llama_stack.core.storage.datatypes.SqlStoreReference'>` | No | | SQL store configuration for file metadata |
## Sample Configuration
@ -32,6 +32,6 @@ aws_secret_access_key: ${env.AWS_SECRET_ACCESS_KEY:=}
endpoint_url: ${env.S3_ENDPOINT_URL:=}
auto_create_bucket: ${env.S3_AUTO_CREATE_BUCKET:=false}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/s3_files_metadata.db
table_name: s3_files_metadata
backend: sql_default
```

8
docs/docs/providers/vector_io/inline_chromadb.mdx
View file

@ -79,13 +79,13 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `db_path` | `<class 'str'>` | No | | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | Config for KV store backend |
## Sample Configuration
```yaml
db_path: ${env.CHROMADB_PATH}
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/chroma_inline_registry.db
persistence:
namespace: vector_io::chroma
backend: kv_default
```

8
docs/docs/providers/vector_io/inline_faiss.mdx
View file

@ -95,12 +95,12 @@ more details about Faiss in general.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | |
## Sample Configuration
```yaml
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/faiss_store.db
persistence:
namespace: vector_io::faiss
backend: kv_default
```

8
docs/docs/providers/vector_io/inline_meta-reference.mdx
View file

@ -14,14 +14,14 @@ Meta's reference implementation of a vector database.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | |
## Sample Configuration
```yaml
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/faiss_store.db
persistence:
namespace: vector_io::faiss
backend: kv_default
```
## Deprecation Notice

8
docs/docs/providers/vector_io/inline_milvus.mdx
View file

@ -17,14 +17,14 @@ Please refer to the remote provider documentation.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `db_path` | `<class 'str'>` | No | | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | Config for KV store backend (SQLite only for now) |
| `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
## Sample Configuration
```yaml
db_path: ${env.MILVUS_DB_PATH:=~/.llama/dummy}/milvus.db
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/milvus_registry.db
persistence:
namespace: vector_io::milvus
backend: kv_default
```

8
docs/docs/providers/vector_io/inline_qdrant.mdx
View file

@ -98,13 +98,13 @@ See the [Qdrant documentation](https://qdrant.tech/documentation/) for more deta
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `path` | `<class 'str'>` | No | | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | |
## Sample Configuration
```yaml
path: ${env.QDRANT_PATH:=~/.llama/~/.llama/dummy}/qdrant.db
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/qdrant_registry.db
persistence:
namespace: vector_io::qdrant
backend: kv_default
```

8
docs/docs/providers/vector_io/inline_sqlite-vec.mdx
View file

@ -408,13 +408,13 @@ See [sqlite-vec's GitHub repo](https://github.com/asg017/sqlite-vec/tree/main) f
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `db_path` | `<class 'str'>` | No | | Path to the SQLite database file |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | Config for KV store backend (SQLite only for now) |
## Sample Configuration
```yaml
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec.db
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec_registry.db
persistence:
namespace: vector_io::sqlite_vec
backend: kv_default
```

8
docs/docs/providers/vector_io/inline_sqlite_vec.mdx
View file

@ -17,15 +17,15 @@ Please refer to the sqlite-vec provider documentation.
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `db_path` | `<class 'str'>` | No | | Path to the SQLite database file |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend (SQLite only for now) |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | Config for KV store backend (SQLite only for now) |
## Sample Configuration
```yaml
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec.db
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/sqlite_vec_registry.db
persistence:
namespace: vector_io::sqlite_vec
backend: kv_default
```
## Deprecation Notice

8
docs/docs/providers/vector_io/remote_chromadb.mdx
View file

@ -78,13 +78,13 @@ See [Chroma's documentation](https://docs.trychroma.com/docs/overview/introducti
| Field | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| `url` | `str \| None` | No | | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | Config for KV store backend |
## Sample Configuration
```yaml
url: ${env.CHROMADB_URL}
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/chroma_remote_registry.db
persistence:
namespace: vector_io::chroma_remote
backend: kv_default
```

8
docs/docs/providers/vector_io/remote_milvus.mdx
View file

@ -408,7 +408,7 @@ For more details on TLS configuration, refer to the [TLS setup guide](https://mi
| `uri` | `<class 'str'>` | No | | The URI of the Milvus server |
| `token` | `str \| None` | No | | The token of the Milvus server |
| `consistency_level` | `<class 'str'>` | No | Strong | The consistency level of the Milvus server |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | Config for KV store backend |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | Config for KV store backend |
| `config` | `dict` | No | `{}` | This configuration allows additional fields to be passed through to the underlying Milvus client. See the [Milvus](https://milvus.io/docs/install-overview.md) documentation for more details about Milvus in general. |
:::note
@ -420,7 +420,7 @@ This configuration class accepts additional fields beyond those listed above. Yo
```yaml
uri: ${env.MILVUS_ENDPOINT}
token: ${env.MILVUS_TOKEN}
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/milvus_remote_registry.db
persistence:
namespace: vector_io::milvus_remote
backend: kv_default
```

8
docs/docs/providers/vector_io/remote_pgvector.mdx
View file

@ -218,7 +218,7 @@ See [PGVector's documentation](https://github.com/pgvector/pgvector) for more de
| `db` | `str \| None` | No | postgres | |
| `user` | `str \| None` | No | postgres | |
| `password` | `str \| None` | No | mysecretpassword | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig, annotation=NoneType, required=False, default='sqlite', discriminator='type'` | No | | Config for KV store backend (SQLite only for now) |
| `persistence` | `llama_stack.core.storage.datatypes.KVStoreReference \| None` | No | | Config for KV store backend (SQLite only for now) |
## Sample Configuration
@ -228,7 +228,7 @@ port: ${env.PGVECTOR_PORT:=5432}
db: ${env.PGVECTOR_DB}
user: ${env.PGVECTOR_USER}
password: ${env.PGVECTOR_PASSWORD}
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/pgvector_registry.db
persistence:
namespace: vector_io::pgvector
backend: kv_default
```

8
docs/docs/providers/vector_io/remote_qdrant.mdx
View file

@ -26,13 +26,13 @@ Please refer to the inline provider documentation.
| `prefix` | `str \| None` | No | | |
| `timeout` | `int \| None` | No | | |
| `host` | `str \| None` | No | | |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig` | No | sqlite | |
| `persistence` | `<class 'llama_stack.core.storage.datatypes.KVStoreReference'>` | No | | |
## Sample Configuration
```yaml
api_key: ${env.QDRANT_API_KEY:=}
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/qdrant_registry.db
persistence:
namespace: vector_io::qdrant_remote
backend: kv_default
```

8
docs/docs/providers/vector_io/remote_weaviate.mdx
View file

@ -75,14 +75,14 @@ See [Weaviate's documentation](https://weaviate.io/developers/weaviate) for more
|-------|------|----------|---------|-------------|
| `weaviate_api_key` | `str \| None` | No | | The API key for the Weaviate instance |
| `weaviate_cluster_url` | `str \| None` | No | localhost:8080 | The URL of the Weaviate cluster |
| `kvstore` | `utils.kvstore.config.RedisKVStoreConfig \| utils.kvstore.config.SqliteKVStoreConfig \| utils.kvstore.config.PostgresKVStoreConfig \| utils.kvstore.config.MongoDBKVStoreConfig, annotation=NoneType, required=False, default='sqlite', discriminator='type'` | No | | Config for KV store backend (SQLite only for now) |
| `persistence` | `llama_stack.core.storage.datatypes.KVStoreReference \| None` | No | | Config for KV store backend (SQLite only for now) |
## Sample Configuration
```yaml
weaviate_api_key: null
weaviate_cluster_url: ${env.WEAVIATE_CLUSTER_URL:=localhost:8080}
kvstore:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/dummy}/weaviate_registry.db
persistence:
namespace: vector_io::weaviate
backend: kv_default
```

8
docs/static/deprecated-llama-stack-spec.html vendored
View file

@ -9024,6 +9024,10 @@
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
},
"input": {
"type": "array",
"items": {
@ -9901,6 +9905,10 @@
"usage": {
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
}
},
"additionalProperties": false,

8
docs/static/deprecated-llama-stack-spec.yaml vendored
View file

@ -6734,6 +6734,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
input:
type: array
items:
@ -7403,6 +7407,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
additionalProperties: false
required:
- created_at

8
docs/static/llama-stack-spec.html vendored
View file

@ -7600,6 +7600,10 @@
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
},
"input": {
"type": "array",
"items": {
@ -8148,6 +8152,10 @@
"usage": {
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
}
},
"additionalProperties": false,

8
docs/static/llama-stack-spec.yaml vendored
View file

@ -5815,6 +5815,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
input:
type: array
items:
@ -6218,6 +6222,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
additionalProperties: false
required:
- created_at

8
docs/static/stainless-llama-stack-spec.html vendored
View file

@ -9272,6 +9272,10 @@
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
},
"input": {
"type": "array",
"items": {
@ -9820,6 +9824,10 @@
"usage": {
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
}
},
"additionalProperties": false,

8
docs/static/stainless-llama-stack-spec.yaml vendored
View file

@ -7028,6 +7028,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
input:
type: array
items:
@ -7431,6 +7435,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
additionalProperties: false
required:
- created_at