phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-07 20:50:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore!: remove --image-type and --image-name from llama stack run

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-10-06 16:11:40 -07:00
parent 0751002bf3
commit ea30c24595
13 changed files with 4659 additions and 5171 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.github/workflows/integration-auth-tests.yml vendored
View file

@ -86,7 +86,7 @@ jobs:
# avoid line breaks in the server log, especially because we grep it below. # avoid line breaks in the server log, especially because we grep it below.
export COLUMNS=1984 export COLUMNS=1984
nohup uv run llama stack run $run_dir/run.yaml --image-type venv > server.log 2>&1 & nohup uv run llama stack run $run_dir/run.yaml > server.log 2>&1 &
- name: Wait for Llama Stack server to be ready - name: Wait for Llama Stack server to be ready
run: | run: |

2
.github/workflows/test-external-provider-module.yml vendored
View file

@ -59,7 +59,7 @@ jobs:
# Use the virtual environment created by the build step (name comes from build config) # Use the virtual environment created by the build step (name comes from build config)
source ramalama-stack-test/bin/activate source ramalama-stack-test/bin/activate
uv pip list uv pip list
nohup llama stack run tests/external/ramalama-stack/run.yaml --image-type ${{ matrix.image-type }} > server.log 2>&1 & nohup llama stack run tests/external/ramalama-stack/run.yaml > server.log 2>&1 &
- name: Wait for Llama Stack server to be ready - name: Wait for Llama Stack server to be ready
run: | run: |

2
.github/workflows/test-external.yml vendored
View file

@ -59,7 +59,7 @@ jobs:
# Use the virtual environment created by the build step (name comes from build config) # Use the virtual environment created by the build step (name comes from build config)
source ci-test/bin/activate source ci-test/bin/activate
uv pip list uv pip list
nohup llama stack run tests/external/run-byoa.yaml --image-type ${{ matrix.image-type }} > server.log 2>&1 & nohup llama stack run tests/external/run-byoa.yaml > server.log 2>&1 &
- name: Wait for Llama Stack server to be ready - name: Wait for Llama Stack server to be ready
run: | run: |

2
docs/docs/advanced_apis/post_training.mdx
View file

@ -52,7 +52,7 @@ You can access the HuggingFace trainer via the `starter` distribution:
```bash ```bash
llama stack build --distro starter --image-type venv llama stack build --distro starter --image-type venv
llama stack run --image-type venv ~/.llama/distributions/starter/starter-run.yaml llama stack run ~/.llama/distributions/starter/starter-run.yaml
``` ```
### Usage Example ### Usage Example

11
docs/docs/distributions/building_distro.mdx
View file

@ -322,20 +322,20 @@ Now, let's start the Llama Stack Distribution Server. You will need the YAML con
llama stack run -h llama stack run -h
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME]
[--image-type {venv}] [--enable-ui] [--image-type {venv}] [--enable-ui]
[config | template] [config | distro]
Start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution. Start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution.
positional arguments: positional arguments:
config | template Path to config file to use for the run or name of known template (`llama stack list` for a list). (default: None) config | distro Path to config file to use for the run or name of known distro (`llama stack list` for a list). (default: None)
options: options:
-h, --help show this help message and exit -h, --help show this help message and exit
--port PORT Port to run the server on. It can also be passed via the env var LLAMA_STACK_PORT. (default: 8321) --port PORT Port to run the server on. It can also be passed via the env var LLAMA_STACK_PORT. (default: 8321)
--image-name IMAGE_NAME --image-name IMAGE_NAME
Name of the image to run. Defaults to the current environment (default: None) [DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running. (default: None)
--image-type {venv} --image-type {venv}
Image Type used during the build. This should be venv. (default: None) [DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running. (default: None)
--enable-ui Start the UI server (default: False) --enable-ui Start the UI server (default: False)
``` ```
@ -347,9 +347,6 @@ llama stack run tgi
# Start using config file # Start using config file
llama stack run ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml llama stack run ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml
# Start using a venv
llama stack run --image-type venv ~/.llama/distributions/llamastack-my-local-stack/my-local-stack-run.yaml
``` ```
``` ```

5880
docs/getting_started.ipynb
View file

File diff suppressed because one or more lines are too long

1565
docs/getting_started_llama4.ipynb
View file

File diff suppressed because one or more lines are too long

1626
docs/getting_started_llama_api.ipynb
View file

File diff suppressed because one or more lines are too long

677
docs/quick_start.ipynb
View file

@ -1,366 +1,315 @@
{ {
"cells": [ "cells": [
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "c1e7571c", "id": "c1e7571c",
"metadata": { "metadata": {
"id": "c1e7571c" "id": "c1e7571c"
}, },
"source": [ "source": [
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb)\n", "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb)\n",
"\n", "\n",
"# Llama Stack - Building AI Applications\n", "# Llama Stack - Building AI Applications\n",
"\n", "\n",
"<img src=\"https://llamastack.github.io/latest/_images/llama-stack.png\" alt=\"drawing\" width=\"500\"/>\n", "<img src=\"https://llamastack.github.io/latest/_images/llama-stack.png\" alt=\"drawing\" width=\"500\"/>\n",
"\n", "\n",
"Get started with Llama Stack in minutes!\n", "Get started with Llama Stack in minutes!\n",
"\n", "\n",
"[Llama Stack](https://github.com/meta-llama/llama-stack) is a stateful service with REST APIs to support the seamless transition of AI applications across different environments. You can build and test using a local server first and deploy to a hosted endpoint for production.\n", "[Llama Stack](https://github.com/meta-llama/llama-stack) is a stateful service with REST APIs to support the seamless transition of AI applications across different environments. You can build and test using a local server first and deploy to a hosted endpoint for production.\n",
"\n", "\n",
"In this guide, we'll walk through how to build a RAG application locally using Llama Stack with [Ollama](https://ollama.com/)\n", "In this guide, we'll walk through how to build a RAG application locally using Llama Stack with [Ollama](https://ollama.com/)\n",
"as the inference [provider](docs/source/providers/index.md#inference) for a Llama Model.\n" "as the inference [provider](docs/source/providers/index.md#inference) for a Llama Model.\n"
] ]
},
{
"cell_type": "markdown",
"id": "4CV1Q19BDMVw",
"metadata": {
"id": "4CV1Q19BDMVw"
},
"source": [
"## Step 1: Install and setup"
]
},
{
"cell_type": "markdown",
"id": "K4AvfUAJZOeS",
"metadata": {
"id": "K4AvfUAJZOeS"
},
"source": [
"### 1.1. Install uv and test inference with Ollama\n",
"\n",
"We'll install [uv](https://docs.astral.sh/uv/) to setup the Python virtual environment, along with [colab-xterm](https://github.com/InfuseAI/colab-xterm) for running command-line tools, and [Ollama](https://ollama.com/download) as the inference provider."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7a2d7b85",
"metadata": {},
"outputs": [],
"source": [
"%pip install uv llama_stack llama-stack-client\n",
"\n",
"## If running on Collab:\n",
"# !pip install colab-xterm\n",
"# %load_ext colabxterm\n",
"\n",
"!curl https://ollama.ai/install.sh | sh"
]
},
{
"cell_type": "markdown",
"id": "39fa584b",
"metadata": {},
"source": [
"### 1.2. Test inference with Ollama"
]
},
{
"cell_type": "markdown",
"id": "3bf81522",
"metadata": {},
"source": [
"We’ll now launch a terminal and run inference on a Llama model with Ollama to verify that the model is working correctly."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a7e8e0f1",
"metadata": {},
"outputs": [],
"source": [
"## If running on Colab:\n",
"# %xterm\n",
"\n",
"## To be ran in the terminal:\n",
"# ollama serve &\n",
"# ollama run llama3.2:3b --keepalive 60m"
]
},
{
"cell_type": "markdown",
"id": "f3c5f243",
"metadata": {},
"source": [
"If successful, you should see the model respond to a prompt.\n",
"\n",
"...\n",
"```\n",
">>> hi\n",
"Hello! How can I assist you today?\n",
"```"
]
},
{
"cell_type": "markdown",
"id": "oDUB7M_qe-Gs",
"metadata": {
"id": "oDUB7M_qe-Gs"
},
"source": [
"## Step 2: Run the Llama Stack server\n",
"\n",
"In this showcase, we will start a Llama Stack server that is running locally."
]
},
{
"cell_type": "markdown",
"id": "732eadc6",
"metadata": {},
"source": [
"### 2.1. Setup the Llama Stack Server"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "J2kGed0R5PSf",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"collapsed": true,
"id": "J2kGed0R5PSf",
"outputId": "2478ea60-8d35-48a1-b011-f233831740c5"
},
"outputs": [],
"source": [
"import os\n",
"import subprocess\n",
"\n",
"if \"UV_SYSTEM_PYTHON\" in os.environ:\n",
" 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 --distro 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\"OLLAMA_URL=http://localhost:11434 uv run --with llama-stack llama stack run starter --image-type venv\n",
" shell=True,\n",
" stdout=log_file,\n",
" stderr=log_file,\n",
" text=True\n",
" )\n",
"\n",
" print(f\"Starting Llama Stack server with PID: {process.pid}\")\n",
" return process\n",
"\n",
"def wait_for_server_to_start():\n",
" import requests\n",
" from requests.exceptions import ConnectionError\n",
" import time\n",
"\n",
" url = \"http://0.0.0.0:8321/v1/health\"\n",
" max_retries = 30\n",
" retry_interval = 1\n",
"\n",
" print(\"Waiting for server to start\", end=\"\")\n",
" for _ in range(max_retries):\n",
" try:\n",
" response = requests.get(url)\n",
" if response.status_code == 200:\n",
" print(\"\\nServer is ready!\")\n",
" return True\n",
" except ConnectionError:\n",
" print(\".\", end=\"\", flush=True)\n",
" time.sleep(retry_interval)\n",
"\n",
" print(\"\\nServer failed to start after\", max_retries * retry_interval, \"seconds\")\n",
" return False\n",
"\n",
"\n",
"# use this helper if needed to kill the server\n",
"def kill_llama_stack_server():\n",
" # Kill any existing llama stack server processes\n",
" os.system(\"ps aux | grep -v grep | grep llama_stack.core.server.server | awk '{print $2}' | xargs kill -9\")\n"
]
},
{
"cell_type": "markdown",
"id": "c40e9efd",
"metadata": {},
"source": [
"### 2.2. Start the Llama Stack Server"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f779283d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Starting Llama Stack server with PID: 787100\n",
"Waiting for server to start\n",
"Server is ready!\n"
]
}
],
"source": [
"server_process = run_llama_stack_server_background()\n",
"assert wait_for_server_to_start()"
]
},
{
"cell_type": "markdown",
"id": "28477c03",
"metadata": {},
"source": [
"## Step 3: Run the demo"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "7da71011",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"rag_tool> Ingesting document: https://www.paulgraham.com/greatwork.html\n",
"prompt> How do you do great work?\n",
"\u001b[33minference> \u001b[0m\u001b[33m[k\u001b[0m\u001b[33mnowledge\u001b[0m\u001b[33m_search\u001b[0m\u001b[33m(query\u001b[0m\u001b[33m=\"\u001b[0m\u001b[33mWhat\u001b[0m\u001b[33m is\u001b[0m\u001b[33m the\u001b[0m\u001b[33m key\u001b[0m\u001b[33m to\u001b[0m\u001b[33m doing\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m\")]\u001b[0m\u001b[97m\u001b[0m\n",
"\u001b[32mtool_execution> Tool:knowledge_search Args:{'query': 'What is the key to doing great work'}\u001b[0m\n",
"\u001b[32mtool_execution> Tool:knowledge_search Response:[TextContentItem(text='knowledge_search tool found 5 chunks:\\nBEGIN of knowledge_search tool results.\\n', type='text'), TextContentItem(text=\"Result 1:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 2:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 3:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 4:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 5:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text='END of knowledge_search tool results.\\n', type='text'), TextContentItem(text='The above results were retrieved to help answer the user\\'s query: \"What is the key to doing great work\". Use them as supporting information only in answering this query.\\n', type='text')]\u001b[0m\n",
"\u001b[33minference> \u001b[0m\u001b[33mDoing\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m means\u001b[0m\u001b[33m doing\u001b[0m\u001b[33m something\u001b[0m\u001b[33m important\u001b[0m\u001b[33m so\u001b[0m\u001b[33m well\u001b[0m\u001b[33m that\u001b[0m\u001b[33m you\u001b[0m\u001b[33m expand\u001b[0m\u001b[33m people\u001b[0m\u001b[33m's\u001b[0m\u001b[33m ideas\u001b[0m\u001b[33m of\u001b[0m\u001b[33m what\u001b[0m\u001b[33m's\u001b[0m\u001b[33m possible\u001b[0m\u001b[33m.\u001b[0m\u001b[33m However\u001b[0m\u001b[33m,\u001b[0m\u001b[33m there\u001b[0m\u001b[33m's\u001b[0m\u001b[33m no\u001b[0m\u001b[33m threshold\u001b[0m\u001b[33m for\u001b[0m\u001b[33m importance\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m it\u001b[0m\u001b[33m's\u001b[0m\u001b[33m often\u001b[0m\u001b[33m hard\u001b[0m\u001b[33m to\u001b[0m\u001b[33m judge\u001b[0m\u001b[33m at\u001b[0m\u001b[33m the\u001b[0m\u001b[33m time\u001b[0m\u001b[33m anyway\u001b[0m\u001b[33m.\u001b[0m\u001b[33m Great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m is\u001b[0m\u001b[33m a\u001b[0m\u001b[33m matter\u001b[0m\u001b[33m of\u001b[0m\u001b[33m degree\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m it\u001b[0m\u001b[33m can\u001b[0m\u001b[33m be\u001b[0m\u001b[33m difficult\u001b[0m\u001b[33m to\u001b[0m\u001b[33m determine\u001b[0m\u001b[33m whether\u001b[0m\u001b[33m someone\u001b[0m\u001b[33m has\u001b[0m\u001b[33m done\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m until\u001b[0m\u001b[33m after\u001b[0m\u001b[33m the\u001b[0m\u001b[33m fact\u001b[0m\u001b[33m.\u001b[0m\u001b[97m\u001b[0m\n",
"\u001b[30m\u001b[0m"
]
}
],
"source": [
"from llama_stack_client import Agent, AgentEventLogger, RAGDocument, LlamaStackClient\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 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",
" embedding_model=embedding_model_id,\n",
" embedding_dimension=embedding_dimension,\n",
" provider_id=\"faiss\",\n",
")\n",
"source = \"https://www.paulgraham.com/greatwork.html\"\n",
"print(\"rag_tool> Ingesting document:\", source)\n",
"document = RAGDocument(\n",
" document_id=\"document_1\",\n",
" content=source,\n",
" mime_type=\"text/html\",\n",
" metadata={},\n",
")\n",
"client.tool_runtime.rag_tool.insert(\n",
" documents=[document],\n",
" vector_db_id=vector_db_id,\n",
" chunk_size_in_tokens=50,\n",
")\n",
"agent = Agent(\n",
" client,\n",
" model=model_id,\n",
" instructions=\"You are a helpful assistant\",\n",
" tools=[\n",
" {\n",
" \"name\": \"builtin::rag/knowledge_search\",\n",
" \"args\": {\"vector_db_ids\": [vector_db_id]},\n",
" }\n",
" ],\n",
")\n",
"\n",
"prompt = \"How do you do great work?\"\n",
"print(\"prompt>\", prompt)\n",
"\n",
"response = agent.create_turn(\n",
" messages=[{\"role\": \"user\", \"content\": prompt}],\n",
" session_id=agent.create_session(\"rag_session\"),\n",
" stream=True,\n",
")\n",
"\n",
"for log in AgentEventLogger().log(response):\n",
" log.print()"
]
},
{
"cell_type": "markdown",
"id": "341aaadf",
"metadata": {},
"source": [
"Congratulations! You've successfully built your first RAG application using Llama Stack! 🎉🥳"
]
},
{
"cell_type": "markdown",
"id": "e88e1185",
"metadata": {},
"source": [
"## Next Steps"
]
},
{
"cell_type": "markdown",
"id": "bcb73600",
"metadata": {},
"source": [
"Now you're ready to dive deeper into Llama Stack!\n",
"- Explore the [Detailed Tutorial](./detailed_tutorial.md).\n",
"- Try the [Getting Started Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb).\n",
"- Browse more [Notebooks on GitHub](https://github.com/meta-llama/llama-stack/tree/main/docs/notebooks).\n",
"- Learn about Llama Stack [Concepts](../concepts/index.md).\n",
"- Discover how to [Build Llama Stacks](../distributions/index.md).\n",
"- Refer to our [References](../references/index.md) for details on the Llama CLI and Python SDK.\n",
"- Check out the [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/examples) repository for example applications and tutorials."
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.6"
}
}, },
"nbformat": 4, {
"nbformat_minor": 5 "cell_type": "markdown",
} "id": "4CV1Q19BDMVw",
"metadata": {
"id": "4CV1Q19BDMVw"
},
"source": [
"## Step 1: Install and setup"
]
},
{
"cell_type": "markdown",
"id": "K4AvfUAJZOeS",
"metadata": {
"id": "K4AvfUAJZOeS"
},
"source": [
"### 1.1. Install uv and test inference with Ollama\n",
"\n",
"We'll install [uv](https://docs.astral.sh/uv/) to setup the Python virtual environment, along with [colab-xterm](https://github.com/InfuseAI/colab-xterm) for running command-line tools, and [Ollama](https://ollama.com/download) as the inference provider."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7a2d7b85",
"metadata": {},
"outputs": [],
"source": [
"%pip install uv llama_stack llama-stack-client\n",
"\n",
"## If running on Collab:\n",
"# !pip install colab-xterm\n",
"# %load_ext colabxterm\n",
"\n",
"!curl https://ollama.ai/install.sh | sh"
]
},
{
"cell_type": "markdown",
"id": "39fa584b",
"metadata": {},
"source": [
"### 1.2. Test inference with Ollama"
]
},
{
"cell_type": "markdown",
"id": "3bf81522",
"metadata": {},
"source": [
"We’ll now launch a terminal and run inference on a Llama model with Ollama to verify that the model is working correctly."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a7e8e0f1",
"metadata": {},
"outputs": [],
"source": [
"## If running on Colab:\n",
"# %xterm\n",
"\n",
"## To be ran in the terminal:\n",
"# ollama serve &\n",
"# ollama run llama3.2:3b --keepalive 60m"
]
},
{
"cell_type": "markdown",
"id": "f3c5f243",
"metadata": {},
"source": [
"If successful, you should see the model respond to a prompt.\n",
"\n",
"...\n",
"```\n",
">>> hi\n",
"Hello! How can I assist you today?\n",
"```"
]
},
{
"cell_type": "markdown",
"id": "oDUB7M_qe-Gs",
"metadata": {
"id": "oDUB7M_qe-Gs"
},
"source": [
"## Step 2: Run the Llama Stack server\n",
"\n",
"In this showcase, we will start a Llama Stack server that is running locally."
]
},
{
"cell_type": "markdown",
"id": "732eadc6",
"metadata": {},
"source": [
"### 2.1. Setup the Llama Stack Server"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "J2kGed0R5PSf",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"collapsed": true,
"id": "J2kGed0R5PSf",
"outputId": "2478ea60-8d35-48a1-b011-f233831740c5"
},
"outputs": [],
"source": "import os\nimport subprocess\n\nif \"UV_SYSTEM_PYTHON\" in os.environ:\n 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 --distro starter --image-type venv\n\ndef run_llama_stack_server_background():\n log_file = open(\"llama_stack_server.log\", \"w\")\n process = subprocess.Popen(\n f\"OLLAMA_URL=http://localhost:11434 uv run --with llama-stack llama stack run starter\",\n shell=True,\n stdout=log_file,\n stderr=log_file,\n text=True\n )\n\n print(f\"Starting Llama Stack server with PID: {process.pid}\")\n return process\n\ndef wait_for_server_to_start():\n import requests\n from requests.exceptions import ConnectionError\n import time\n\n url = \"http://0.0.0.0:8321/v1/health\"\n max_retries = 30\n retry_interval = 1\n\n print(\"Waiting for server to start\", end=\"\")\n for _ in range(max_retries):\n try:\n response = requests.get(url)\n if response.status_code == 200:\n print(\"\\nServer is ready!\")\n return True\n except ConnectionError:\n print(\".\", end=\"\", flush=True)\n time.sleep(retry_interval)\n\n print(\"\\nServer failed to start after\", max_retries * retry_interval, \"seconds\")\n return False\n\n\n# use this helper if needed to kill the server\ndef kill_llama_stack_server():\n # Kill any existing llama stack server processes\n os.system(\"ps aux | grep -v grep | grep llama_stack.core.server.server | awk '{print $2}' | xargs kill -9\")\n"
},
{
"cell_type": "markdown",
"id": "c40e9efd",
"metadata": {},
"source": [
"### 2.2. Start the Llama Stack Server"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "f779283d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Starting Llama Stack server with PID: 787100\n",
"Waiting for server to start\n",
"Server is ready!\n"
]
}
],
"source": [
"server_process = run_llama_stack_server_background()\n",
"assert wait_for_server_to_start()"
]
},
{
"cell_type": "markdown",
"id": "28477c03",
"metadata": {},
"source": [
"## Step 3: Run the demo"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "7da71011",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"rag_tool> Ingesting document: https://www.paulgraham.com/greatwork.html\n",
"prompt> How do you do great work?\n",
"\u001b[33minference> \u001b[0m\u001b[33m[k\u001b[0m\u001b[33mnowledge\u001b[0m\u001b[33m_search\u001b[0m\u001b[33m(query\u001b[0m\u001b[33m=\"\u001b[0m\u001b[33mWhat\u001b[0m\u001b[33m is\u001b[0m\u001b[33m the\u001b[0m\u001b[33m key\u001b[0m\u001b[33m to\u001b[0m\u001b[33m doing\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m\")]\u001b[0m\u001b[97m\u001b[0m\n",
"\u001b[32mtool_execution> Tool:knowledge_search Args:{'query': 'What is the key to doing great work'}\u001b[0m\n",
"\u001b[32mtool_execution> Tool:knowledge_search Response:[TextContentItem(text='knowledge_search tool found 5 chunks:\\nBEGIN of knowledge_search tool results.\\n', type='text'), TextContentItem(text=\"Result 1:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 2:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 3:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 4:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text=\"Result 5:\\nDocument_id:docum\\nContent: work. Doing great work means doing something important\\nso well that you expand people's ideas of what's possible. But\\nthere's no threshold for importance. It's a matter of degree, and\\noften hard to judge at the time anyway.\\n\", type='text'), TextContentItem(text='END of knowledge_search tool results.\\n', type='text'), TextContentItem(text='The above results were retrieved to help answer the user\\'s query: \"What is the key to doing great work\". Use them as supporting information only in answering this query.\\n', type='text')]\u001b[0m\n",
"\u001b[33minference> \u001b[0m\u001b[33mDoing\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m means\u001b[0m\u001b[33m doing\u001b[0m\u001b[33m something\u001b[0m\u001b[33m important\u001b[0m\u001b[33m so\u001b[0m\u001b[33m well\u001b[0m\u001b[33m that\u001b[0m\u001b[33m you\u001b[0m\u001b[33m expand\u001b[0m\u001b[33m people\u001b[0m\u001b[33m's\u001b[0m\u001b[33m ideas\u001b[0m\u001b[33m of\u001b[0m\u001b[33m what\u001b[0m\u001b[33m's\u001b[0m\u001b[33m possible\u001b[0m\u001b[33m.\u001b[0m\u001b[33m However\u001b[0m\u001b[33m,\u001b[0m\u001b[33m there\u001b[0m\u001b[33m's\u001b[0m\u001b[33m no\u001b[0m\u001b[33m threshold\u001b[0m\u001b[33m for\u001b[0m\u001b[33m importance\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m it\u001b[0m\u001b[33m's\u001b[0m\u001b[33m often\u001b[0m\u001b[33m hard\u001b[0m\u001b[33m to\u001b[0m\u001b[33m judge\u001b[0m\u001b[33m at\u001b[0m\u001b[33m the\u001b[0m\u001b[33m time\u001b[0m\u001b[33m anyway\u001b[0m\u001b[33m.\u001b[0m\u001b[33m Great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m is\u001b[0m\u001b[33m a\u001b[0m\u001b[33m matter\u001b[0m\u001b[33m of\u001b[0m\u001b[33m degree\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m it\u001b[0m\u001b[33m can\u001b[0m\u001b[33m be\u001b[0m\u001b[33m difficult\u001b[0m\u001b[33m to\u001b[0m\u001b[33m determine\u001b[0m\u001b[33m whether\u001b[0m\u001b[33m someone\u001b[0m\u001b[33m has\u001b[0m\u001b[33m done\u001b[0m\u001b[33m great\u001b[0m\u001b[33m work\u001b[0m\u001b[33m until\u001b[0m\u001b[33m after\u001b[0m\u001b[33m the\u001b[0m\u001b[33m fact\u001b[0m\u001b[33m.\u001b[0m\u001b[97m\u001b[0m\n",
"\u001b[30m\u001b[0m"
]
}
],
"source": [
"from llama_stack_client import Agent, AgentEventLogger, RAGDocument, LlamaStackClient\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 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",
" embedding_model=embedding_model_id,\n",
" embedding_dimension=embedding_dimension,\n",
" provider_id=\"faiss\",\n",
")\n",
"source = \"https://www.paulgraham.com/greatwork.html\"\n",
"print(\"rag_tool> Ingesting document:\", source)\n",
"document = RAGDocument(\n",
" document_id=\"document_1\",\n",
" content=source,\n",
" mime_type=\"text/html\",\n",
" metadata={},\n",
")\n",
"client.tool_runtime.rag_tool.insert(\n",
" documents=[document],\n",
" vector_db_id=vector_db_id,\n",
" chunk_size_in_tokens=50,\n",
")\n",
"agent = Agent(\n",
" client,\n",
" model=model_id,\n",
" instructions=\"You are a helpful assistant\",\n",
" tools=[\n",
" {\n",
" \"name\": \"builtin::rag/knowledge_search\",\n",
" \"args\": {\"vector_db_ids\": [vector_db_id]},\n",
" }\n",
" ],\n",
")\n",
"\n",
"prompt = \"How do you do great work?\"\n",
"print(\"prompt>\", prompt)\n",
"\n",
"response = agent.create_turn(\n",
" messages=[{\"role\": \"user\", \"content\": prompt}],\n",
" session_id=agent.create_session(\"rag_session\"),\n",
" stream=True,\n",
")\n",
"\n",
"for log in AgentEventLogger().log(response):\n",
" log.print()"
]
},
{
"cell_type": "markdown",
"id": "341aaadf",
"metadata": {},
"source": [
"Congratulations! You've successfully built your first RAG application using Llama Stack! 🎉🥳"
]
},
{
"cell_type": "markdown",
"id": "e88e1185",
"metadata": {},
"source": [
"## Next Steps"
]
},
{
"cell_type": "markdown",
"id": "bcb73600",
"metadata": {},
"source": [
"Now you're ready to dive deeper into Llama Stack!\n",
"- Explore the [Detailed Tutorial](./detailed_tutorial.md).\n",
"- Try the [Getting Started Notebook](https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb).\n",
"- Browse more [Notebooks on GitHub](https://github.com/meta-llama/llama-stack/tree/main/docs/notebooks).\n",
"- Learn about Llama Stack [Concepts](../concepts/index.md).\n",
"- Discover how to [Build Llama Stacks](../distributions/index.md).\n",
"- Refer to our [References](../references/index.md) for details on the Llama CLI and Python SDK.\n",
"- Check out the [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main/examples) repository for example applications and tutorials."
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

3
docs/zero_to_hero_guide/README.md
View file

@ -88,7 +88,7 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
... ...
Build Successful! Build Successful!
You can find the newly-built template here: ~/.llama/distributions/starter/starter-run.yaml You can find the newly-built template here: ~/.llama/distributions/starter/starter-run.yaml
You can run the new Llama Stack Distro via: uv run --with llama-stack llama stack run starter --image-type venv You can run the new Llama Stack Distro via: uv run --with llama-stack llama stack run starter
``` ```
3. **Set the ENV variables by exporting them to the terminal**: 3. **Set the ENV variables by exporting them to the terminal**:
@ -106,7 +106,6 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
SAFETY_MODEL=$SAFETY_MODEL \ SAFETY_MODEL=$SAFETY_MODEL \
OLLAMA_URL=$OLLAMA_URL \ OLLAMA_URL=$OLLAMA_URL \
uv run --with llama-stack llama stack run starter \ uv run --with llama-stack llama stack run starter \
--image-type venv \
--port $LLAMA_STACK_PORT --port $LLAMA_STACK_PORT
``` ```
Note: Every time you run a new model with `ollama run`, you will need to restart the llama stack. Otherwise it won't see the new model. Note: Every time you run a new model with `ollama run`, you will need to restart the llama stack. Otherwise it won't see the new model.

22
llama_stack/cli/stack/_build.py
View file

@ -444,12 +444,22 @@ def _run_stack_build_command_from_build_config(
cprint("Build Successful!", color="green", file=sys.stderr) cprint("Build Successful!", color="green", file=sys.stderr)
cprint(f"You can find the newly-built distribution here: {run_config_file}", color="blue", file=sys.stderr) cprint(f"You can find the newly-built distribution here: {run_config_file}", color="blue", file=sys.stderr)
cprint( if build_config.image_type == LlamaStackImageType.VENV:
"You can run the new Llama Stack distro via: " cprint(
+ colored(f"llama stack run {run_config_file} --image-type {build_config.image_type}", "blue"), "You can run the new Llama Stack distro (after activating "
color="green", + colored(image_name, "cyan")
file=sys.stderr, + ") via: "
) + colored(f"llama stack run {run_config_file}", "blue"),
color="green",
file=sys.stderr,
)
elif build_config.image_type == LlamaStackImageType.CONTAINER:
cprint(
"You can run the container with: "
+ colored(f"docker run -p 8321:8321 -v ~/.llama:/root/.llama localhost/{image_name} --port 8321", "blue"),
color="green",
file=sys.stderr,
)
return distro_path return distro_path
else: else:
return _generate_run_config(build_config, build_dir, image_name) return _generate_run_config(build_config, build_dir, image_name)

36
llama_stack/cli/stack/run.py
View file

@ -55,12 +55,12 @@ class StackRun(Subcommand):
"--image-name", "--image-name",
type=str, type=str,
default=None, default=None,
help="Name of the image to run. Defaults to the current environment", help="[DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running.",
) )
self.parser.add_argument( self.parser.add_argument(
"--image-type", "--image-type",
type=str, type=str,
help="Image Type used during the build. This can be only venv.", help="[DEPRECATED] This flag is no longer supported. Please activate your virtual environment before running.",
choices=[e.value for e in ImageType if e.value != ImageType.CONTAINER.value], choices=[e.value for e in ImageType if e.value != ImageType.CONTAINER.value],
) )
self.parser.add_argument( self.parser.add_argument(
@ -106,11 +106,18 @@ class StackRun(Subcommand):
import yaml import yaml
from llama_stack.core.configure import parse_and_maybe_upgrade_config from llama_stack.core.configure import parse_and_maybe_upgrade_config
from llama_stack.core.utils.exec import formulate_run_args, run_command
if args.image_type or args.image_name:
self.parser.error(
"The --image-type and --image-name flags are no longer supported.\n\n"
"Please activate your virtual environment manually before running `llama stack run`.\n\n"
"For example:\n"
" source /path/to/venv/bin/activate\n"
" llama stack run <config>\n"
)
if args.enable_ui: if args.enable_ui:
self._start_ui_development_server(args.port) self._start_ui_development_server(args.port)
image_type, image_name = args.image_type, args.image_name
if args.config: if args.config:
try: try:
@ -122,10 +129,6 @@ class StackRun(Subcommand):
else: else:
config_file = None config_file = None
# Check if config is required based on image type
if image_type == ImageType.VENV.value and not config_file:
self.parser.error("Config file is required for venv environment")
if config_file: if config_file:
logger.info(f"Using run configuration: {config_file}") logger.info(f"Using run configuration: {config_file}")
@ -140,23 +143,8 @@ class StackRun(Subcommand):
os.makedirs(str(config.external_providers_dir), exist_ok=True) os.makedirs(str(config.external_providers_dir), exist_ok=True)
except AttributeError as e: except AttributeError as e:
self.parser.error(f"failed to parse config file '{config_file}':\n {e}") self.parser.error(f"failed to parse config file '{config_file}':\n {e}")
else:
config = None
# If neither image type nor image name is provided, assume the server should be run directly self._uvicorn_run(config_file, args)
# using the current environment packages.
if not image_type and not image_name:
logger.info("No image type or image name provided. Assuming environment packages.")
self._uvicorn_run(config_file, args)
else:
run_args = formulate_run_args(image_type, image_name)
run_args.extend([str(args.port)])
if config_file:
run_args.extend(["--config", str(config_file)])
run_command(run_args)
def _uvicorn_run(self, config_file: Path | None, args: argparse.Namespace) -> None: def _uvicorn_run(self, config_file: Path | None, args: argparse.Namespace) -> None:
if not config_file: if not config_file:

2
scripts/integration-tests.sh
View file

@ -186,7 +186,7 @@ if [[ "$STACK_CONFIG" == *"server:"* ]]; then
echo "Llama Stack Server is already running, skipping start" echo "Llama Stack Server is already running, skipping start"
else else
echo "=== Starting Llama Stack Server ===" echo "=== Starting Llama Stack Server ==="
nohup llama stack run ci-tests --image-type venv > server.log 2>&1 & nohup llama stack run ci-tests > server.log 2>&1 &
echo "Waiting for Llama Stack Server to start..." echo "Waiting for Llama Stack Server to start..."
for i in {1..30}; do for i in {1..30}; do