phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: switch to the new default nomic-embed-text-v1.5 embedding model in LS

Browse source
This commit is contained in:
r3v5 2025-08-18 10:34:46 +01:00
parent f1748e2f92
commit 1d0f0a0d8e
No known key found for this signature in database
GPG key ID: C7611ACB4FECAD54
63 changed files with 16170 additions and 186 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/docs/building_applications/rag.mdx
View file

@ -47,8 +47,8 @@ client = LlamaStackClient(base_url=f"http://localhost:{os.environ['LLAMA_STACK_P
vector_db_id = "my_documents"
response = client.vector_dbs.register(
vector_db_id=vector_db_id,
embedding_model="all-MiniLM-L6-v2",
embedding_dimension=384,
embedding_model="nomic-embed-text-v1.5",
embedding_dimension=768,
provider_id="faiss",
)
```

4
docs/docs/distributions/k8s/stack_run_config.yaml
View file

@ -110,8 +110,8 @@ inference_store:
password: ${env.POSTGRES_PASSWORD:=llamastack}
models:
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
embedding_dimension: 768
model_id: nomic-embed-text-v1.5
provider_id: sentence-transformers
model_type: embedding
- metadata: {}

2
docs/docs/getting_started/detailed_tutorial.mdx
View file

@ -164,7 +164,7 @@ Available Models
┏━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┓
┃ model_type ┃ identifier ┃ provider_resource_id ┃ metadata ┃ provider_id ┃
┡━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━┩
│ embedding │ ollama/all-minilm:l6-v2 │ all-minilm:l6-v2 │ {'embedding_dimension': 384.0} │ ollama │
│ embedding │ ollama/nomic-embed-text:v1.5 │ nomic-embed-text:v1.5 │ {'embedding_dimension': 768.0} │ ollama │
├─────────────────┼─────────────────────────────────────┼─────────────────────────────────────┼───────────────────────────────────────────┼───────────────────────┤
│ ... │ ... │ ... │ │ ... │
├─────────────────┼─────────────────────────────────────┼─────────────────────────────────────┼───────────────────────────────────────────┼───────────────────────┤

8
docs/docs/references/llama_stack_client_cli_reference.md
View file

@ -224,8 +224,8 @@ llama-stack-client vector_dbs list
┏━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ provider_resource_id ┃ vector_db_type ┃ params ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ my_demo_vector_db │ faiss │ my_demo_vector_db │ │ embedding_dimension: 384 │
│ │ │ │ │ embedding_model: all-MiniLM-L6-v2 │
│ my_demo_vector_db │ faiss │ my_demo_vector_db │ │ embedding_dimension: 768 │
│ │ │ │ │ embedding_model: nomic-embed-text-v1.5 │
│ │ │ │ │ type: vector_db │
│ │ │ │ │ │
└──────────────────────────┴─────────────┴──────────────────────────┴────────────────┴───────────────────────────────────┘
@ -244,8 +244,8 @@ Required arguments:
Optional arguments:
- `--provider-id`: Provider ID for the vector db
- `--provider-vector-db-id`: Provider's vector db ID
- `--embedding-model`: Embedding model to use. Default: `all-MiniLM-L6-v2`
- `--embedding-dimension`: Dimension of embeddings. Default: 384
- `--embedding-model`: Embedding model to use. Default: `nomic-embed-text-v1.5`
- `--embedding-dimension`: Dimension of embeddings. Default: 768
### `llama-stack-client vector_dbs unregister`
Delete a vector db

4
docs/getting_started.ipynb
View file

@ -1352,8 +1352,8 @@
"vector_db_id = f\"test-vector-db-{uuid.uuid4().hex}\"\n",
"client.vector_dbs.register(\n",
" vector_db_id=vector_db_id,\n",
" embedding_model=\"all-MiniLM-L6-v2\",\n",
" embedding_dimension=384,\n",
" embedding_model=\"nomic-embed-text-v1.5\",\n",
" embedding_dimension=768,\n",
")\n",
"client.tool_runtime.rag_tool.insert(\n",
" documents=documents,\n",

6
docs/notebooks/Llama_Stack_RAG_Lifecycle.ipynb
View file

@ -831,7 +831,7 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -860,8 +860,8 @@
"vector_db_id = f\"test_vector_db_{uuid.uuid4()}\"\n",
"client.vector_dbs.register(\n",
" vector_db_id=vector_db_id,\n",
" embedding_model=\"all-MiniLM-L6-v2\",\n",
" embedding_dimension=384,\n",
" embedding_model=\"nomic-embed-text-v1.5\",\n",
" embedding_dimension=768,\n",
" provider_id=selected_vector_provider.provider_id,\n",
")\n",
"\n",

2
docs/static/llama-stack-spec.html vendored
View file

@ -11452,7 +11452,7 @@
},
"embedding_dimension": {
"type": "integer",
"description": "The dimension of the embedding vectors (default: 384)."
"description": "The dimension of the embedding vectors (default: 768)."
},
"provider_id": {
"type": "string",

2
docs/static/llama-stack-spec.yaml vendored
View file

@ -8528,7 +8528,7 @@ components:
embedding_dimension:
type: integer
description: >-
The dimension of the embedding vectors (default: 384).
The dimension of the embedding vectors (default: 768).
provider_id:
type: string
description: >-

5
docs/zero_to_hero_guide/05_Memory101.ipynb
View file

@ -161,6 +161,7 @@
{
"cell_type": "code",
"execution_count": null,
"id": "4ad70258",
"metadata": {},
"outputs": [],
"source": [
@ -180,8 +181,8 @@
"# Create a vector database with optimized settings for general use\n",
"client.vector_dbs.register(\n",
" vector_db_id=VECTOR_DB_ID,\n",
" embedding_model=\"all-MiniLM-L6-v2\",\n",
" embedding_dimension=384, # This is the dimension for all-MiniLM-L6-v2\n",
" embedding_model=\"nomic-embed-text-v1.5\",\n",
" embedding_dimension=768, # This is the dimension for nomic-embed-text-v1.5\n",
" provider_id=provider_id,\n",
")"
]