phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 07:14:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into fix/milvus-missing-files-api-parameter

Browse source
This commit is contained in:
raghotham 2025-07-04 21:08:03 -07:00 • committed by GitHub
commit 6d13591ef4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 25 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/getting_started_llama4.ipynb
View file

@ -55,7 +55,7 @@
"\n",
"MODEL=\"Llama-4-Scout-17B-16E-Instruct\"\n",
"# get meta url from llama.com\n",
"!uv run --with llama-stackllama model download --source meta --model-id $MODEL --meta-url <META_URL>\n",
"!uv run --with llama-stack llama model download --source meta --model-id $MODEL --meta-url <META_URL>\n",
"\n",
"model_id = f\"meta-llama/{MODEL}\""
]

21
docs/quick_start.ipynb
View file

@ -145,12 +145,12 @@
" del os.environ[\"UV_SYSTEM_PYTHON\"]\n",
"\n",
"# this command installs all the dependencies needed for the llama stack server with the ollama inference provider\n",
"!uv run --with llama-stack llama stack build --template ollama --image-type venv --image-name myvenv\n",
"!uv run --with llama-stack llama stack build --template starter --image-type venv\n",
"\n",
"def run_llama_stack_server_background():\n",
" log_file = open(\"llama_stack_server.log\", \"w\")\n",
" process = subprocess.Popen(\n",
" f\"uv run --with llama-stack llama stack run ollama --image-type venv --image-name myvenv --env INFERENCE_MODEL=llama3.2:3b\",\n",
" f\"uv run --with llama-stack llama stack run starter --image-type venv --env INFERENCE_MODEL=llama3.2:3b\",\n",
" shell=True,\n",
" stdout=log_file,\n",
" stderr=log_file,\n",
@ -249,18 +249,23 @@
],
"source": [
"from llama_stack_client import Agent, AgentEventLogger, RAGDocument, LlamaStackClient\n",
"import os\n",
"\n",
"os.environ[\"ENABLE_OLLAMA\"] = \"ollama\"\n",
"os.environ[\"OLLAMA_INFERENCE_MODEL\"] = \"llama3.2:3b\"\n",
"os.environ[\"OLLAMA_EMBEDDING_MODEL\"] = \"all-minilm:l6-v2\"\n",
"os.environ[\"OLLAMA_EMBEDDING_DIMENSION\"] = \"384\"\n",
"\n",
"vector_db_id = \"my_demo_vector_db\"\n",
"client = LlamaStackClient(base_url=\"http://0.0.0.0:8321\")\n",
"\n",
"models = client.models.list()\n",
"\n",
"# Select the first LLM and first embedding models\n",
"model_id = next(m for m in models if m.model_type == \"llm\").identifier\n",
"embedding_model_id = (\n",
" em := next(m for m in models if m.model_type == \"embedding\")\n",
").identifier\n",
"embedding_dimension = em.metadata[\"embedding_dimension\"]\n",
"# Select the first ollama and first ollama's embedding model\n",
"model_id = next(m for m in models if m.model_type == \"llm\" and m.provider_id == \"ollama\").identifier\n",
"embedding_model = next(m for m in models if m.model_type == \"embedding\" and m.provider_id == \"ollama\")\n",
"embedding_model_id = embedding_model.identifier\n",
"embedding_dimension = embedding_model.metadata[\"embedding_dimension\"]\n",
"\n",
"_ = client.vector_dbs.register(\n",
" vector_db_id=vector_db_id,\n",

22
docs/source/distributions/self_hosted_distro/starter.md
View file

@ -17,18 +17,18 @@ The `llamastack/distribution-starter` distribution is a comprehensive, multi-pro
The starter distribution consists of the following provider configurations:
| API | Provider(s) |
|-----|-------------|
| agents | `inline::meta-reference` |
| datasetio | `remote::huggingface`, `inline::localfs` |
| eval | `inline::meta-reference` |
| files | `inline::localfs` |
| API | Provider(s) |
|-----|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| agents | `inline::meta-reference` |
| datasetio | `remote::huggingface`, `inline::localfs` |
| eval | `inline::meta-reference` |
| files | `inline::localfs` |
| inference | `remote::openai`, `remote::fireworks`, `remote::together`, `remote::ollama`, `remote::anthropic`, `remote::gemini`, `remote::groq`, `remote::sambanova`, `remote::vllm`, `remote::tgi`, `remote::cerebras`, `remote::llama-openai-compat`, `remote::nvidia`, `remote::hf::serverless`, `remote::hf::endpoint`, `inline::sentence-transformers` |
| safety | `inline::llama-guard` |
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
| telemetry | `inline::meta-reference` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::rag-runtime`, `remote::model-context-protocol` |
| vector_io | `inline::faiss`, `inline::sqlite-vec`, `remote::chromadb`, `remote::pgvector` |
| safety | `inline::llama-guard` |
| scoring | `inline::basic`, `inline::llm-as-judge`, `inline::braintrust` |
| telemetry | `inline::meta-reference` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::rag-runtime`, `remote::model-context-protocol` |
| vector_io | `inline::faiss`, `inline::sqlite-vec`, `inline::milvus`, `remote::chromadb`, `remote::pgvector` |
## Inference Providers