phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 10:23:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

pre-commit fixes

Browse source
This commit is contained in:
Chantal D Gama Rose 2025-03-14 13:56:05 -07:00
parent 967dd0aa08
commit 7e211f8553
314 changed files with 5574 additions and 11369 deletions
Download patch file Download diff file Expand all files Collapse all files

625
docs/_static/llama-stack-spec.html vendored
View file

File diff suppressed because it is too large Load diff

419
docs/_static/llama-stack-spec.yaml vendored
View file

File diff suppressed because it is too large Load diff

400
docs/getting_started.ipynb
View file

@ -141,7 +141,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 18,
"id": "E1UFuJC570Tk",
"metadata": {
"colab": {
@ -326,54 +326,108 @@
" type: sqlite\n",
"models:\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Meta-Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-8B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-8B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-8B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-8B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Meta-Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-70B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-70B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-70B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-70B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Meta-Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-405B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-405B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-405B-Instruct-FP8\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.1</span>-405B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-3B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-3B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-3B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-3B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-11B-Vision-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-11B-Vision-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-11B-Vision-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-11B-Vision-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-90B-Vision-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-90B-Vision-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-90B-Vision-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.2</span>-90B-Vision-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.3</span>-70B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.3</span>-70B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.3</span>-70B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3.3</span>-70B-Instruct-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Meta-Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-8B\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-8B\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-8B\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-8B\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-11B-Vision-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-11B-Vision-Turbo\n",
"- metadata: <span style=\"font-weight: bold\">{}</span>\n",
" model_id: meta-llama/Llama-Guard-<span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">3</span>-11B-Vision\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
@ -473,6 +527,9 @@
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: model-context-protocol\n",
" provider_type: remote::model-context-protocol\n",
" - config: <span style=\"font-weight: bold\">{}</span>\n",
" provider_id: wolfram-alpha\n",
" provider_type: remote::wolfram-alpha\n",
" vector_io:\n",
" - config:\n",
" kvstore:\n",
@ -504,6 +561,10 @@
" mcp_endpoint: null\n",
" provider_id: code-interpreter\n",
" toolgroup_id: builtin::code_interpreter\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: wolfram-alpha\n",
" toolgroup_id: builtin::wolfram_alpha\n",
"vector_dbs: <span style=\"font-weight: bold\">[]</span>\n",
"version: <span style=\"color: #008000; text-decoration-color: #008000\">'2'</span>\n",
"\n",
@ -530,54 +591,108 @@
" type: sqlite\n",
"models:\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Meta-Llama-\u001b[1;36m3.1\u001b[0m-8B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-\u001b[1;36m3.1\u001b[0m-8B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.1\u001b[0m-8B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-\u001b[1;36m3.1\u001b[0m-8B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Meta-Llama-\u001b[1;36m3.1\u001b[0m-70B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-\u001b[1;36m3.1\u001b[0m-70B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.1\u001b[0m-70B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-\u001b[1;36m3.1\u001b[0m-70B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Meta-Llama-\u001b[1;36m3.1\u001b[0m-405B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-\u001b[1;36m3.1\u001b[0m-405B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.1\u001b[0m-405B-Instruct-FP8\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-\u001b[1;36m3.1\u001b[0m-405B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-3B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-3B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-3B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-3B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-11B-Vision-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-11B-Vision-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-11B-Vision-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-11B-Vision-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-90B-Vision-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-90B-Vision-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-90B-Vision-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-\u001b[1;36m3.2\u001b[0m-90B-Vision-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.3\u001b[0m-70B-Instruct-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-\u001b[1;36m3.3\u001b[0m-70B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-\u001b[1;36m3.3\u001b[0m-70B-Instruct\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-\u001b[1;36m3.3\u001b[0m-70B-Instruct-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Meta-Llama-Guard-\u001b[1;36m3\u001b[0m-8B\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-Guard-\u001b[1;36m3\u001b[0m-8B\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-Guard-\u001b[1;36m3\u001b[0m-8B\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Meta-Llama-Guard-\u001b[1;36m3\u001b[0m-8B\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-Guard-\u001b[1;36m3\u001b[0m-11B-Vision-Turbo\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
" provider_id: together\n",
" provider_model_id: meta-llama/Llama-Guard-\u001b[1;36m3\u001b[0m-11B-Vision-Turbo\n",
"- metadata: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" model_id: meta-llama/Llama-Guard-\u001b[1;36m3\u001b[0m-11B-Vision\n",
" model_type: !!python/object/apply:llama_stack.apis.models.models.ModelType\n",
" - llm\n",
@ -677,6 +792,9 @@
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: model-context-protocol\n",
" provider_type: remote::model-context-protocol\n",
" - config: \u001b[1m{\u001b[0m\u001b[1m}\u001b[0m\n",
" provider_id: wolfram-alpha\n",
" provider_type: remote::wolfram-alpha\n",
" vector_io:\n",
" - config:\n",
" kvstore:\n",
@ -708,6 +826,10 @@
" mcp_endpoint: null\n",
" provider_id: code-interpreter\n",
" toolgroup_id: builtin::code_interpreter\n",
"- args: null\n",
" mcp_endpoint: null\n",
" provider_id: wolfram-alpha\n",
" toolgroup_id: builtin::wolfram_alpha\n",
"vector_dbs: \u001b[1m[\u001b[0m\u001b[1m]\u001b[0m\n",
"version: \u001b[32m'2'\u001b[0m\n",
"\n"
@ -1145,7 +1267,6 @@
}
],
"source": [
"# NBVAL_SKIP\n",
"from pydantic import BaseModel\n",
"\n",
"\n",
@ -1157,7 +1278,7 @@
"\n",
"user_input = \"Michael Jordan was born in 1963. He played basketball for the Chicago Bulls. He retired in 2003. Extract this information into JSON for me. \"\n",
"response = client.inference.completion(\n",
" model_id=model_id,\n",
" model_id=\"meta-llama/Llama-3.1-8B-Instruct\",\n",
" content=user_input,\n",
" stream=False,\n",
" sampling_params={\n",
@ -1513,18 +1634,14 @@
"source": [
"from llama_stack_client.lib.agents.agent import Agent\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types.agent_create_params import AgentConfig\n",
"from termcolor import cprint\n",
"\n",
"agent_config = AgentConfig(\n",
"agent = Agent(\n",
" client, \n",
" model=model_id,\n",
" instructions=\"You are a helpful assistant\",\n",
" toolgroups=[\"builtin::websearch\"],\n",
" input_shields=[],\n",
" output_shields=[],\n",
" enable_session_persistence=False,\n",
" instructions=\"You are a helpful assistant. Use websearch tool to help answer questions.\",\n",
" tools=[\"builtin::websearch\"],\n",
")\n",
"agent = Agent(client, agent_config)\n",
"user_prompts = [\n",
" \"Hello\",\n",
" \"Which teams played in the NBA western conference finals of 2024\",\n",
@ -1693,7 +1810,6 @@
"import uuid\n",
"from llama_stack_client.lib.agents.agent import Agent\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types.agent_create_params import AgentConfig\n",
"from termcolor import cprint\n",
"from llama_stack_client.types import Document\n",
"\n",
@ -1719,11 +1835,11 @@
" vector_db_id=vector_db_id,\n",
" chunk_size_in_tokens=512,\n",
")\n",
"agent_config = AgentConfig(\n",
"rag_agent = Agent(\n",
" client, \n",
" model=model_id,\n",
" instructions=\"You are a helpful assistant\",\n",
" enable_session_persistence=False,\n",
" toolgroups = [\n",
" tools = [\n",
" {\n",
" \"name\": \"builtin::rag/knowledge_search\",\n",
" \"args\" : {\n",
@ -1732,7 +1848,6 @@
" }\n",
" ],\n",
")\n",
"rag_agent = Agent(client, agent_config)\n",
"session_id = rag_agent.create_session(\"test-session\")\n",
"user_prompts = [\n",
" \"What are the top 5 topics that were explained? Only list succinct bullet points.\",\n",
@ -1856,23 +1971,19 @@
"source": [
"from llama_stack_client.types.agents.turn_create_params import Document\n",
"\n",
"agent_config = AgentConfig(\n",
"codex_agent = Agent(\n",
" client, \n",
" model=\"meta-llama/Llama-3.1-8B-Instruct\",\n",
" instructions=\"You are a helpful assistant\",\n",
" tools=[\n",
" \"builtin::code_interpreter\",\n",
" \"builtin::websearch\"\n",
" ],\n",
" sampling_params = {\n",
" \"max_tokens\" : 4096,\n",
" \"temperature\": 0.0\n",
" },\n",
" model=\"meta-llama/Llama-3.1-8B-Instruct\",\n",
" instructions=\"You are a helpful assistant\",\n",
" toolgroups=[\n",
" \"builtin::code_interpreter\",\n",
" \"builtin::websearch\"\n",
" ],\n",
" tool_choice=\"auto\",\n",
" input_shields=[],\n",
" output_shields=[],\n",
" enable_session_persistence=False,\n",
")\n",
"codex_agent = Agent(client, agent_config)\n",
"session_id = codex_agent.create_session(\"test-session\")\n",
"\n",
"\n",
@ -2782,18 +2893,14 @@
"# NBVAL_SKIP\n",
"from llama_stack_client.lib.agents.agent import Agent\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types.agent_create_params import AgentConfig\n",
"from termcolor import cprint\n",
"\n",
"agent_config = AgentConfig(\n",
"agent = Agent(\n",
" client, \n",
" model=model_id,\n",
" instructions=\"You are a helpful assistant\",\n",
" toolgroups=[\"mcp::filesystem\"],\n",
" input_shields=[],\n",
" output_shields=[],\n",
" enable_session_persistence=False,\n",
" tools=[\"mcp::filesystem\"],\n",
")\n",
"agent = Agent(client, agent_config)\n",
"user_prompts = [\n",
" \"Hello\",\n",
" \"list all the files /content\",\n",
@ -2888,17 +2995,13 @@
"source": [
"from llama_stack_client.lib.agents.agent import Agent\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types.agent_create_params import AgentConfig\n",
"\n",
"agent_config = AgentConfig(\n",
"agent = Agent(\n",
" client, \n",
" model=\"meta-llama/Llama-3.3-70B-Instruct\",\n",
" instructions=\"You are a helpful assistant. Use search tool to answer the questions. \",\n",
" toolgroups=[\"builtin::websearch\"],\n",
" input_shields=[],\n",
" output_shields=[],\n",
" enable_session_persistence=False,\n",
" tools=[\"builtin::websearch\"],\n",
")\n",
"agent = Agent(client, agent_config)\n",
"user_prompts = [\n",
" \"Which teams played in the NBA western conference finals of 2024. Search the web for the answer.\",\n",
" \"In which episode and season of South Park does Bill Cosby (BSM-471) first appear? Give me the number and title. Search the web for the answer.\",\n",
@ -4098,7 +4201,7 @@
"source": [
"## 4. Image Understanding with Llama 3.2\n",
"\n",
"Below is a complete example of using Together's Llama Stack 0.1 server at https://llama-stack.together.ai to ask Llama 3.2 questions about an image."
"Below is a complete example of to ask Llama 3.2 questions about an image."
]
},
{
@ -4106,14 +4209,12 @@
"id": "82e381ec",
"metadata": {},
"source": [
"### 4.1 Setup and helpers\n",
"\n",
"Below we install the Llama Stack client 0.1, download the example image, define two image helpers, and set Llama Stack Together server URL and Llama 3.2 model name.\n"
"### 4.1 Setup and helpers\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 1,
"id": "44e05e16",
"metadata": {},
"outputs": [
@ -4123,7 +4224,7 @@
"text": [
" % Total % Received % Xferd Average Speed Time Time Time Current\n",
" Dload Upload Total Spent Left Speed\n",
"100 275k 100 275k 0 0 780k 0 --:--:-- --:--:-- --:--:-- 780k\n"
"100 275k 100 275k 0 0 905k 0 --:--:-- --:--:-- --:--:-- 906k\n"
]
}
],
@ -4133,32 +4234,13 @@
},
{
"cell_type": "code",
"execution_count": null,
"id": "469750f7",
"metadata": {},
"outputs": [],
"source": [
"# NBVAL_SKIP\n",
"from PIL import Image\n",
"import matplotlib.pyplot as plt\n",
"\n",
"def display_image(path):\n",
" img = Image.open(path)\n",
" plt.imshow(img)\n",
" plt.axis('off')\n",
" plt.show()\n",
"\n",
"display_image(\"Llama_Repo.jpeg\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 20,
"id": "a2c1e1c2",
"metadata": {},
"outputs": [],
"source": [
"import base64\n",
"vision_model_id = \"meta-llama/Llama-3.2-11B-Vision-Instruct\"\n",
"\n",
"def encode_image(image_path):\n",
" with open(image_path, \"rb\") as image_file:\n",
@ -4167,19 +4249,6 @@
" return base64_url"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c565f99e",
"metadata": {},
"outputs": [],
"source": [
"from llama_stack_client import LlamaStackClient\n",
"\n",
"LLAMA_STACK_API_TOGETHER_URL=\"https://llama-stack.together.ai\"\n",
"LLAMA32_11B_INSTRUCT = \"meta-llama/Llama-3.2-11B-Vision-Instruct\""
]
},
{
"cell_type": "markdown",
"id": "7737cd41",
@ -4192,55 +4261,44 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 21,
"id": "d7914894",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"There are three llamas in the image. The llama in the middle is purple, the llama on the left is white, and the llama on the right is also white, but it is wearing a blue party hat. Therefore, there are two different colors of llama in the image: purple and white.\n"
]
}
],
"source": [
"from llama_stack_client.lib.inference.event_logger import EventLogger\n",
"\n",
"async def run_main(image_path: str, prompt):\n",
" client = LlamaStackClient(\n",
" base_url=LLAMA_STACK_API_TOGETHER_URL,\n",
" )\n",
"\n",
" message = {\n",
" \"role\": \"user\",\n",
" \"content\": [\n",
" {\n",
" \"type\": \"image\",\n",
" \"image\": {\n",
" \"url\": {\n",
" \"uri\": encode_image(image_path)\n",
" }\n",
"response = client.inference.chat_completion(\n",
" messages=[\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": [\n",
" {\n",
" \"type\": \"image\",\n",
" \"image\": {\n",
" \"url\": {\n",
" \"uri\": encode_image(\"Llama_Repo.jpeg\")\n",
" }\n",
" }\n",
" },\n",
" {\n",
" \"type\": \"text\",\n",
" \"text\": \"How many different colors are those llamas? What are those colors?\",\n",
" }\n",
" },\n",
" {\n",
" \"type\": \"text\",\n",
" \"text\": prompt,\n",
" }\n",
" ]\n",
" }\n",
" ]\n",
" }\n",
" ],\n",
" model_id=vision_model_id,\n",
" stream=False,\n",
")\n",
"\n",
" response = client.inference.chat_completion(\n",
" messages=[message],\n",
" model_id=LLAMA32_11B_INSTRUCT,\n",
" stream=False,\n",
" )\n",
"\n",
" print(response.completion_message.content.lower().strip())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4ee09b97",
"metadata": {},
"outputs": [],
"source": [
"await run_main(\"Llama_Repo.jpeg\",\n",
" \"How many different colors are those llamas?\\\n",
" What are those colors?\")"
"print(response.completion_message.content)"
]
},
{
@ -4255,68 +4313,60 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 19,
"id": "f9a83275",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[33minference> \u001b[0m\u001b[33mThere\u001b[0m\u001b[33m are\u001b[0m\u001b[33m three\u001b[0m\u001b[33m different\u001b[0m\u001b[33m colors\u001b[0m\u001b[33m of\u001b[0m\u001b[33m ll\u001b[0m\u001b[33mamas\u001b[0m\u001b[33m in\u001b[0m\u001b[33m the\u001b[0m\u001b[33m image\u001b[0m\u001b[33m.\u001b[0m\u001b[33m The\u001b[0m\u001b[33m first\u001b[0m\u001b[33m llama\u001b[0m\u001b[33m on\u001b[0m\u001b[33m the\u001b[0m\u001b[33m left\u001b[0m\u001b[33m is\u001b[0m\u001b[33m white\u001b[0m\u001b[33m,\u001b[0m\u001b[33m the\u001b[0m\u001b[33m second\u001b[0m\u001b[33m llama\u001b[0m\u001b[33m in\u001b[0m\u001b[33m the\u001b[0m\u001b[33m middle\u001b[0m\u001b[33m is\u001b[0m\u001b[33m purple\u001b[0m\u001b[33m,\u001b[0m\u001b[33m and\u001b[0m\u001b[33m the\u001b[0m\u001b[33m third\u001b[0m\u001b[33m llama\u001b[0m\u001b[33m on\u001b[0m\u001b[33m the\u001b[0m\u001b[33m right\u001b[0m\u001b[33m is\u001b[0m\u001b[33m white\u001b[0m\u001b[33m with\u001b[0m\u001b[33m a\u001b[0m\u001b[33m blue\u001b[0m\u001b[33m party\u001b[0m\u001b[33m hat\u001b[0m\u001b[33m.\u001b[0m\u001b[97m\u001b[0m\n",
"\u001b[30m\u001b[0m"
]
}
],
"source": [
"from llama_stack_client.lib.agents.agent import Agent\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types.agent_create_params import AgentConfig\n",
"agent = Agent(\n",
" client, \n",
" model=vision_model_id,\n",
" instructions=\"You are a helpful assistant\",\n",
")\n",
"session_id = agent.create_session(\"test-session\")\n",
"\n",
"async def run_main(image_path, prompt):\n",
" base64_image = encode_image(image_path)\n",
"\n",
" client = LlamaStackClient(\n",
" base_url=LLAMA_STACK_API_TOGETHER_URL,\n",
" )\n",
"\n",
" agent_config = AgentConfig(\n",
" model=LLAMA32_11B_INSTRUCT,\n",
" instructions=\"You are a helpful assistant\",\n",
" enable_session_persistence=False,\n",
" toolgroups=[],\n",
" )\n",
"\n",
" agent = Agent(client, agent_config)\n",
" session_id = agent.create_session(\"test-session\")\n",
"\n",
" response = agent.create_turn(\n",
" messages=[{\n",
" \"role\": \"user\",\n",
" \"content\": [\n",
" {\n",
" \"type\": \"image\",\n",
" \"image\": {\n",
" \"url\": {\n",
" \"uri\": encode_image(image_path)\n",
" }\n",
" }\n",
" },\n",
" {\n",
" \"type\": \"text\",\n",
" \"text\": prompt,\n",
"response = agent.create_turn(\n",
" messages=[{\n",
" \"role\": \"user\",\n",
" \"content\": [\n",
" {\n",
" \"type\": \"image\",\n",
" \"image\": {\n",
" \"url\": {\n",
" \"uri\": encode_image(\"Llama_Repo.jpeg\")\n",
" }\n",
" }\n",
" ]\n",
" }],\n",
" session_id=session_id,\n",
" )\n",
" },\n",
" {\n",
" \"type\": \"text\",\n",
" \"text\": \"How many different colors are those llamas? What are those colors?\",\n",
" }\n",
" ]\n",
" }],\n",
" session_id=session_id,\n",
")\n",
"\n",
" for log in EventLogger().log(response):\n",
" log.print()"
"for log in EventLogger().log(response):\n",
" log.print()\n",
" "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "15d0098b",
"id": "f3352379",
"metadata": {},
"outputs": [],
"source": [
"await run_main(\"Llama_Repo.jpeg\",\n",
" \"How many different colors are those llamas?\\\n",
" What are those colors?\")"
]
"source": []
}
],
"metadata": {

4
docs/notebooks/Alpha_Llama_Stack_Post_Training.ipynb
View file

@ -3675,7 +3675,7 @@
" benchmark_id=\"llama3.2-3B-instruct:tax_eval\",\n",
" input_rows=eval_rows.rows,\n",
" scoring_functions=[\"braintrust::answer-similarity\"],\n",
" task_config={\n",
" benchmark_config={\n",
" \"type\": \"benchmark\",\n",
" \"eval_candidate\": {\n",
" \"type\": \"model\",\n",
@ -6383,7 +6383,7 @@
" benchmark_id=\"Llama-3.2-3B-Instruct-sft-0:tax_eval\",\n",
" input_rows=eval_rows.rows,\n",
" scoring_functions=[\"braintrust::answer-similarity\"],\n",
" task_config={\n",
" benchmark_config={\n",
" \"type\": \"benchmark\",\n",
" \"eval_candidate\": {\n",
" \"type\": \"model\",\n",

11
docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
View file

@ -781,7 +781,7 @@
" benchmark_id=\"meta-reference::mmmu\",\n",
" input_rows=eval_rows,\n",
" scoring_functions=[\"basic::regex_parser_multiple_choice_answer\"],\n",
" task_config={\n",
" benchmark_config={\n",
" \"type\": \"benchmark\",\n",
" \"eval_candidate\": {\n",
" \"type\": \"model\",\n",
@ -826,10 +826,9 @@
"_ = client.datasets.register(\n",
" dataset_id=simpleqa_dataset_id,\n",
" provider_id=\"huggingface\",\n",
" url={\"uri\": \"https://huggingface.co/datasets/llamastack/evals\"},\n",
" url={\"uri\": \"https://huggingface.co/datasets/llamastack/simpleqa\"},\n",
" metadata={\n",
" \"path\": \"llamastack/evals\",\n",
" \"name\": \"evals__simpleqa\",\n",
" \"path\": \"llamastack/simpleqa\",\n",
" \"split\": \"train\",\n",
" },\n",
" dataset_schema={\n",
@ -960,7 +959,7 @@
" benchmark_id=\"meta-reference::simpleqa\",\n",
" input_rows=eval_rows.rows,\n",
" scoring_functions=[\"llm-as-judge::405b-simpleqa\"],\n",
" task_config={\n",
" benchmark_config={\n",
" \"type\": \"benchmark\",\n",
" \"eval_candidate\": {\n",
" \"type\": \"model\",\n",
@ -1109,7 +1108,7 @@
" benchmark_id=\"meta-reference::simpleqa\",\n",
" input_rows=eval_rows.rows,\n",
" scoring_functions=[\"llm-as-judge::405b-simpleqa\"],\n",
" task_config={\n",
" benchmark_config={\n",
" \"type\": \"benchmark\",\n",
" \"eval_candidate\": {\n",
" \"type\": \"agent\",\n",

8
docs/openapi_generator/README.md
View file

@ -1,9 +1 @@
The RFC Specification (OpenAPI format) is generated from the set of API endpoints located in `llama_stack/distribution/server/endpoints.py` using the `generate.py` utility.
Please install the following packages before running the script:
```
pip install fire PyYAML
```
Then simply run `sh run_openapi_generator.sh`

14
docs/source/building_applications/agent.md
View file

@ -14,18 +14,16 @@ Agents are configured using the `AgentConfig` class, which includes:
- **Safety Shields**: Guardrails to ensure responsible AI behavior
```python
from llama_stack_client.types.agent_create_params import AgentConfig
from llama_stack_client.lib.agents.agent import Agent
# Configure an agent
agent_config = AgentConfig(
model="meta-llama/Llama-3-70b-chat",
instructions="You are a helpful assistant that can use tools to answer questions.",
toolgroups=["builtin::code_interpreter", "builtin::rag/knowledge_search"],
)
# Create the agent
agent = Agent(llama_stack_client, agent_config)
agent = Agent(
llama_stack_client,
model="meta-llama/Llama-3-70b-chat",
instructions="You are a helpful assistant that can use tools to answer questions.",
tools=["builtin::code_interpreter", "builtin::rag/knowledge_search"],
)
```
### 2. Sessions

8
docs/source/building_applications/agent_execution_loop.md
View file

@ -70,18 +70,18 @@ Each step in this process can be monitored and controlled through configurations
from llama_stack_client import LlamaStackClient
from llama_stack_client.lib.agents.agent import Agent
from llama_stack_client.lib.agents.event_logger import EventLogger
from llama_stack_client.types.agent_create_params import AgentConfig
from rich.pretty import pprint
# Replace host and port
client = LlamaStackClient(base_url=f"http://{HOST}:{PORT}")
agent_config = AgentConfig(
agent = Agent(
client,
# Check with `llama-stack-client models list`
model="Llama3.2-3B-Instruct",
instructions="You are a helpful assistant",
# Enable both RAG and tool usage
toolgroups=[
tools=[
{
"name": "builtin::rag/knowledge_search",
"args": {"vector_db_ids": ["my_docs"]},
@ -98,8 +98,6 @@ agent_config = AgentConfig(
"max_tokens": 2048,
},
)
agent = Agent(client, agent_config)
session_id = agent.create_session("monitored_session")
# Stream the agent's execution steps

250
docs/source/building_applications/evals.md
View file

@ -1,169 +1,127 @@
# Evals
# Evaluations
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/10CHyykee9j2OigaIcRv47BKG9mrNm0tJ?usp=sharing)
The Llama Stack provides a set of APIs in Llama Stack for supporting running evaluations of LLM applications.
- `/datasetio` + `/datasets` API
- `/scoring` + `/scoring_functions` API
- `/eval` + `/benchmarks` API
Llama Stack provides the building blocks needed to run benchmark and application evaluations. This guide will walk you through how to use these components to run open benchmark evaluations. Visit our [Evaluation Concepts](../concepts/evaluation_concepts.md) guide for more details on how evaluations work in Llama Stack, and our [Evaluation Reference](../references/evals_reference/index.md) guide for a comprehensive reference on the APIs.
### 1. Open Benchmark Model Evaluation
This first example walks you through how to evaluate a model candidate served by Llama Stack on open benchmarks. We will use the following benchmark:
- [MMMU](https://arxiv.org/abs/2311.16502) (A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI): Benchmark designed to evaluate multimodal models.
- [SimpleQA](https://openai.com/index/introducing-simpleqa/): Benchmark designed to access models to answer short, fact-seeking questions.
This guides walks you through the process of evaluating an LLM application built using Llama Stack. Checkout the [Evaluation Reference](../references/evals_reference/index.md) guide goes over the sets of APIs and developer experience flow of using Llama Stack to run evaluations for benchmark and application use cases. Checkout our Colab notebook on working examples with evaluations [here](https://colab.research.google.com/drive/10CHyykee9j2OigaIcRv47BKG9mrNm0tJ?usp=sharing).
#### 1.1 Running MMMU
- We will use a pre-processed MMMU dataset from [llamastack/mmmu](https://huggingface.co/datasets/llamastack/mmmu). The preprocessing code is shown in in this [Github Gist](https://gist.github.com/yanxi0830/118e9c560227d27132a7fd10e2c92840). The dataset is obtained by transforming the original [MMMU/MMMU](https://huggingface.co/datasets/MMMU/MMMU) dataset into correct format by `inference/chat-completion` API.
## Application Evaluation
[![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)
Llama Stack offers a library of scoring functions and the `/scoring` API, allowing you to run evaluations on your pre-annotated AI application datasets.
In this example, we will show you how to:
1. Build an Agent with Llama Stack
2. Query the agent's sessions, turns, and steps
3. Evaluate the results.
##### Building a Search Agent
```python
import datasets
from llama_stack_client import LlamaStackClient
from llama_stack_client.lib.agents.agent import Agent
from llama_stack_client.lib.agents.event_logger import EventLogger
ds = datasets.load_dataset(path="llamastack/mmmu", name="Agriculture", split="dev")
ds = ds.select_columns(["chat_completion_input", "input_query", "expected_answer"])
eval_rows = ds.to_pandas().to_dict(orient="records")
```
client = LlamaStackClient(base_url=f"http://{HOST}:{PORT}")
- Next, we will run evaluation on an model candidate, we will need to:
- Define a system prompt
- Define an EvalCandidate
- Run evaluate on the dataset
```python
SYSTEM_PROMPT_TEMPLATE = """
You are an expert in Agriculture whose job is to answer questions from the user using images.
First, reason about the correct answer.
Then write the answer in the following format where X is exactly one of A,B,C,D:
Answer: X
Make sure X is one of A,B,C,D.
If you are uncertain of the correct answer, guess the most likely one.
"""
system_message = {
"role": "system",
"content": SYSTEM_PROMPT_TEMPLATE,
}
client.benchmarks.register(
benchmark_id="meta-reference::mmmu",
dataset_id=f"mmmu-{subset}-{split}",
scoring_functions=["basic::regex_parser_multiple_choice_answer"],
agent = Agent(
client,
model="meta-llama/Llama-3.3-70B-Instruct",
instructions="You are a helpful assistant. Use search tool to answer the questions. ",
tools=["builtin::websearch"],
)
user_prompts = [
"Which teams played in the NBA Western Conference Finals of 2024. Search the web for the answer.",
"In which episode and season of South Park does Bill Cosby (BSM-471) first appear? Give me the number and title. Search the web for the answer.",
"What is the British-American kickboxer Andrew Tate's kickboxing name? Search the web for the answer.",
]
response = client.eval.evaluate_rows(
benchmark_id="meta-reference::mmmu",
input_rows=eval_rows,
scoring_functions=["basic::regex_parser_multiple_choice_answer"],
task_config={
"type": "benchmark",
"eval_candidate": {
"type": "model",
"model": "meta-llama/Llama-3.2-90B-Vision-Instruct",
"sampling_params": {
"strategy": {
"type": "greedy",
},
"max_tokens": 4096,
"repeat_penalty": 1.0,
},
"system_message": system_message,
},
},
)
```
session_id = agent.create_session("test-session")
#### 1.2. Running SimpleQA
- We will use a pre-processed SimpleQA dataset from [llamastack/evals](https://huggingface.co/datasets/llamastack/evals/viewer/evals__simpleqa) which is obtained by transforming the input query into correct format accepted by `inference/chat-completion` API.
- Since we will be using this same dataset in our next example for Agentic evaluation, we will register it using the `/datasets` API, and interact with it through `/datasetio` API.
for prompt in user_prompts:
response = agent.create_turn(
messages=[
{
"role": "user",
"content": prompt,
}
],
session_id=session_id,
)
```python
simpleqa_dataset_id = "huggingface::simpleqa"
_ = client.datasets.register(
dataset_id=simpleqa_dataset_id,
provider_id="huggingface",
url={"uri": "https://huggingface.co/datasets/llamastack/evals"},
metadata={
"path": "llamastack/evals",
"name": "evals__simpleqa",
"split": "train",
},
dataset_schema={
"input_query": {"type": "string"},
"expected_answer": {"type": "string"},
"chat_completion_input": {"type": "chat_completion_input"},
},
)
eval_rows = client.datasetio.get_rows_paginated(
dataset_id=simpleqa_dataset_id,
rows_in_page=5,
)
```
```python
client.benchmarks.register(
benchmark_id="meta-reference::simpleqa",
dataset_id=simpleqa_dataset_id,
scoring_functions=["llm-as-judge::405b-simpleqa"],
)
response = client.eval.evaluate_rows(
benchmark_id="meta-reference::simpleqa",
input_rows=eval_rows.rows,
scoring_functions=["llm-as-judge::405b-simpleqa"],
task_config={
"type": "benchmark",
"eval_candidate": {
"type": "model",
"model": "meta-llama/Llama-3.2-90B-Vision-Instruct",
"sampling_params": {
"strategy": {
"type": "greedy",
},
"max_tokens": 4096,
"repeat_penalty": 1.0,
},
},
},
)
for log in EventLogger().log(response):
log.print()
```
### 2. Agentic Evaluation
- In this example, we will demonstrate how to evaluate a agent candidate served by Llama Stack via `/agent` API.
- We will continue to use the SimpleQA dataset we used in previous example.
- Instead of running evaluation on model, we will run the evaluation on a Search Agent with access to search tool. We will define our agent evaluation candidate through `AgentConfig`.
##### Query Agent Execution Steps
Now, let's look deeper into the agent's execution steps and see if how well our agent performs.
```python
# query the agents session
from rich.pretty import pprint
session_response = client.agents.session.retrieve(
session_id=session_id,
agent_id=agent.agent_id,
)
pprint(session_response)
```
As a sanity check, we will first check if all user prompts is followed by a tool call to `brave_search`.
```python
num_tool_call = 0
for turn in session_response.turns:
for step in turn.steps:
if (
step.step_type == "tool_execution"
and step.tool_calls[0].tool_name == "brave_search"
):
num_tool_call += 1
print(
f"{num_tool_call}/{len(session_response.turns)} user prompts are followed by a tool call to `brave_search`"
)
```
##### Evaluate Agent Responses
Now, we want to evaluate the agent's responses to the user prompts.
1. First, we will process the agent's execution history into a list of rows that can be used for evaluation.
2. Next, we will label the rows with the expected answer.
3. Finally, we will use the `/scoring` API to score the agent's responses.
```python
agent_config = {
"model": "meta-llama/Llama-3.1-405B-Instruct",
"instructions": "You are a helpful assistant",
"sampling_params": {
"strategy": {
"type": "greedy",
},
},
"tools": [
eval_rows = []
expected_answers = [
"Dallas Mavericks and the Minnesota Timberwolves",
"Season 4, Episode 12",
"King Cobra",
]
for i, turn in enumerate(session_response.turns):
eval_rows.append(
{
"type": "brave_search",
"engine": "tavily",
"api_key": userdata.get("TAVILY_SEARCH_API_KEY"),
"input_query": turn.input_messages[0].content,
"generated_answer": turn.output_message.content,
"expected_answer": expected_answers[i],
}
],
"tool_choice": "auto",
"input_shields": [],
"output_shields": [],
"enable_session_persistence": False,
}
)
response = client.eval.evaluate_rows(
benchmark_id="meta-reference::simpleqa",
input_rows=eval_rows.rows,
scoring_functions=["llm-as-judge::405b-simpleqa"],
task_config={
"type": "benchmark",
"eval_candidate": {
"type": "agent",
"config": agent_config,
},
},
pprint(eval_rows)
scoring_params = {
"basic::subset_of": None,
}
scoring_response = client.scoring.score(
input_rows=eval_rows, scoring_functions=scoring_params
)
pprint(scoring_response)
```

30
docs/source/building_applications/evaluation.md
View file

@ -1,30 +0,0 @@
## Testing & Evaluation
Llama Stack provides built-in tools for evaluating your applications:
1. **Benchmarking**: Test against standard datasets
2. **Application Evaluation**: Score your application's outputs
3. **Custom Metrics**: Define your own evaluation criteria
Here's how to set up basic evaluation:
```python
# Create an evaluation task
response = client.benchmarks.register(
benchmark_id="my_eval",
dataset_id="my_dataset",
scoring_functions=["accuracy", "relevance"],
)
# Run evaluation
job = client.eval.run_eval(
benchmark_id="my_eval",
task_config={
"type": "app",
"eval_candidate": {"type": "agent", "config": agent_config},
},
)
# Get results
result = client.eval.job_result(benchmark_id="my_eval", job_id=job.job_id)
```

26
docs/source/building_applications/rag.md
View file

@ -20,6 +20,11 @@ We may add more storage types like Graph IO in the future.
Here's how to set up a vector database for RAG:
```python
# Create http client
from llama_stack_client import LlamaStackClient
client = LlamaStackClient(base_url=f"http://localhost:{os.environ['LLAMA_STACK_PORT']}")
# Register a vector db
vector_db_id = "my_documents"
response = client.vector_dbs.register(
@ -81,15 +86,14 @@ results = client.tool_runtime.rag_tool.query(
One of the most powerful patterns is combining agents with RAG capabilities. Here's a complete example:
```python
from llama_stack_client.types.agent_create_params import AgentConfig
from llama_stack_client.lib.agents.agent import Agent
# Configure agent with memory
agent_config = AgentConfig(
# Create agent with memory
agent = Agent(
client,
model="meta-llama/Llama-3.3-70B-Instruct",
instructions="You are a helpful assistant",
enable_session_persistence=False,
toolgroups=[
tools=[
{
"name": "builtin::rag/knowledge_search",
"args": {
@ -98,8 +102,6 @@ agent_config = AgentConfig(
}
],
)
agent = Agent(client, agent_config)
session_id = agent.create_session("rag_session")
@ -122,7 +124,7 @@ response = agent.create_turn(
],
documents=[
{
"content": "https://raw.githubusercontent.com/example/doc.rst",
"content": "https://raw.githubusercontent.com/pytorch/torchtune/main/docs/source/tutorials/memory_optimizations.rst",
"mime_type": "text/plain",
}
],
@ -136,6 +138,14 @@ response = agent.create_turn(
)
```
You can print the response with below.
```python
from llama_stack_client.lib.agents.event_logger import EventLogger
for log in EventLogger().log(response):
log.print()
```
### Unregistering Vector DBs
If you need to clean up and unregister vector databases, you can do so as follows:

34
docs/source/building_applications/tools.md
View file

@ -5,7 +5,7 @@ An example of this would be a "db_access" tool group that contains tools for int
Tools are treated as any other resource in llama stack like models. You can register them, have providers for them etc.
When instatiating an agent, you can provide it a list of tool groups that it has access to. Agent gets the corresponding tool definitions for the specified tool groups and passes them along to the model.
When instantiating an agent, you can provide it a list of tool groups that it has access to. Agent gets the corresponding tool definitions for the specified tool groups and passes them along to the model.
Refer to the [Building AI Applications](https://github.com/meta-llama/llama-stack/blob/main/docs/getting_started.ipynb) notebook for more examples on how to use tools.
@ -60,7 +60,7 @@ Features:
- Disabled dangerous system operations
- Configurable execution timeouts
> ⚠️ Important: The code interpreter tool can operate in a controlled enviroment locally or on Podman containers. To ensure proper functionality in containerised environments:
> ⚠️ Important: The code interpreter tool can operate in a controlled environment locally or on Podman containers. To ensure proper functionality in containerized environments:
> - The container requires privileged access (e.g., --privileged).
> - Users without sufficient permissions may encounter permission errors. (`bwrap: Can't mount devpts on /newroot/dev/pts: Permission denied`)
> - 🔒 Security Warning: Privileged mode grants elevated access and bypasses security restrictions. Use only in local, isolated, or controlled environments.
@ -127,15 +127,11 @@ MCP tools require:
## Adding Custom Tools
When you want to use tools other than the built-in tools, you can implement a python function and decorate it with `@client_tool`.
When you want to use tools other than the built-in tools, you just need to implement a python function with a docstring. The content of the docstring will be used to describe the tool and the parameters and passed
along to the generative model.
To define a custom tool, you need to use the `@client_tool` decorator.
```python
from llama_stack_client.lib.agents.client_tool import client_tool
# Example tool definition
@client_tool
def my_tool(input: int) -> int:
"""
Runs my awesome tool.
@ -149,15 +145,7 @@ def my_tool(input: int) -> int:
Once defined, simply pass the tool to the agent config. `Agent` will take care of the rest (calling the model with the tool definition, executing the tool, and returning the result to the model for the next iteration).
```python
# Example agent config with client provided tools
client_tools = [
my_tool,
]
agent_config = AgentConfig(
...,
client_tools=[client_tool.get_tool_definition() for client_tool in client_tools],
)
agent = Agent(client, agent_config, client_tools)
agent = Agent(client, ..., tools=[my_tool])
```
Refer to [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/blob/main/examples/agents/e2e_loop_with_client_tools.py) for an example of how to use client provided tools.
@ -194,10 +182,10 @@ group_tools = client.tools.list_tools(toolgroup_id="search_tools")
```python
from llama_stack_client.lib.agents.agent import Agent
from llama_stack_client.types.agent_create_params import AgentConfig
# Configure the AI agent with necessary parameters
agent_config = AgentConfig(
# Instantiate the AI agent with the given configuration
agent = Agent(
client,
name="code-interpreter",
description="A code interpreter agent for executing Python code snippets",
instructions="""
@ -205,14 +193,10 @@ agent_config = AgentConfig(
Always show the generated code, never generate your own code, and never anticipate results.
""",
model="meta-llama/Llama-3.2-3B-Instruct",
toolgroups=["builtin::code_interpreter"],
tools=["builtin::code_interpreter"],
max_infer_iters=5,
enable_session_persistence=False,
)
# Instantiate the AI agent with the given configuration
agent = Agent(client, agent_config)
# Start a session
session_id = agent.create_session("tool_session")

55
docs/source/concepts/evaluation_concepts.md
View file

@ -24,17 +24,58 @@ The Evaluation APIs are associated with a set of Resources as shown in the follo
- Associated with `Benchmark` resource.
Use the following decision tree to decide how to use LlamaStack Evaluation flow.
![Eval Flow](../references/evals_reference/resources/eval-flow.png)
## Open-benchmark Eval
### List of open-benchmarks Llama Stack support
Llama stack pre-registers several popular open-benchmarks to easily evaluate model perfomance via CLI.
The list of open-benchmarks we currently support:
- [MMLU-COT](https://arxiv.org/abs/2009.03300) (Measuring Massive Multitask Language Understanding): Benchmark designed to comprehensively evaluate the breadth and depth of a model's academic and professional understanding
- [GPQA-COT](https://arxiv.org/abs/2311.12022) (A Graduate-Level Google-Proof Q&A Benchmark): A challenging benchmark of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry.
- [SimpleQA](https://openai.com/index/introducing-simpleqa/): Benchmark designed to access models to answer short, fact-seeking questions.
- [MMMU](https://arxiv.org/abs/2311.16502) (A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI)]: Benchmark designed to evaluate multimodal models.
```{admonition} Note on Benchmark v.s. Application Evaluation
:class: tip
- **Benchmark Evaluation** is a well-defined eval-task consisting of `dataset` and `scoring_function`. The generation (inference or agent) will be done as part of evaluation.
- **Application Evaluation** assumes users already have app inputs & generated outputs. Evaluation will purely focus on scoring the generated outputs via scoring functions (e.g. LLM-as-judge).
You can follow this [contributing guide](https://llama-stack.readthedocs.io/en/latest/references/evals_reference/index.html#open-benchmark-contributing-guide) to add more open-benchmarks to Llama Stack
### Run evaluation on open-benchmarks via CLI
We have built-in functionality to run the supported open-benckmarks using llama-stack-client CLI
#### Spin up Llama Stack server
Spin up llama stack server with 'open-benchmark' template
```
llama stack run llama_stack/templates/open-benchmark/run.yaml
```
#### Run eval CLI
There are 3 necessary inputs to run a benchmark eval
- `list of benchmark_ids`: The list of benchmark ids to run evaluation on
- `model-id`: The model id to evaluate on
- `utput_dir`: Path to store the evaluate results
```
llama-stack-client eval run-benchmark <benchmark_id_1> <benchmark_id_2> ... \
--model_id <model id to evaluate on> \
--output_dir <directory to store the evaluate results> \
```
You can run
```
llama-stack-client eval run-benchmark help
```
to see the description of all the flags that eval run-benchmark has
In the output log, you can find the file path that has your evaluation results. Open that file and you can see you aggrgate
evaluation results over there.
## What's Next?
- Check out our Colab notebook on working examples with evaluations [here](https://colab.research.google.com/drive/10CHyykee9j2OigaIcRv47BKG9mrNm0tJ?usp=sharing).
- Check out our Colab notebook on working examples with running benchmark evaluations [here](https://colab.research.google.com/github/meta-llama/llama-stack/blob/main/docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb#scrollTo=mxLCsP4MvFqP).
- Check out our [Building Applications - Evaluation](../building_applications/evals.md) guide for more details on how to use the Evaluation APIs to evaluate your applications.
- Check out our [Evaluation Reference](../references/evals_reference/index.md) for more details on the APIs.

10
docs/source/concepts/index.md
View file

@ -1,5 +1,13 @@
# Core Concepts
```{toctree}
:maxdepth: 1
:hidden:
evaluation_concepts
```
Given Llama Stack's service-oriented philosophy, a few concepts and workflows arise which may not feel completely natural in the LLM landscape, especially if you are coming with a background in other frameworks.
@ -26,7 +34,7 @@ We are working on adding a few more APIs to complete the application lifecycle.
The goal of Llama Stack is to build an ecosystem where users can easily swap out different implementations for the same API. Examples for these include:
- LLM inference providers (e.g., Fireworks, Together, AWS Bedrock, Groq, Cerebras, SambaNova, vLLM, etc.),
- Vector databases (e.g., ChromaDB, Weaviate, Qdrant, FAISS, PGVector, etc.),
- Vector databases (e.g., ChromaDB, Weaviate, Qdrant, Milvus, FAISS, PGVector, etc.),
- Safety providers (e.g., Meta's Llama Guard, AWS Bedrock Guardrails, etc.)
Providers come in two flavors:

12
docs/source/conf.py
View file

@ -13,16 +13,18 @@
# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
from docutils import nodes
import tomli # Import tomli for TOML parsing
from pathlib import Path
import requests
import json
# Read version from pyproject.toml
with Path(__file__).parent.parent.parent.joinpath("pyproject.toml").open("rb") as f:
pyproject = tomli.load(f)
llama_stack_version = pyproject["project"]["version"]
pypi_url = "https://pypi.org/pypi/llama-stack/json"
version_tag = json.loads(requests.get(pypi_url).text)["info"]["version"]
print(f"{version_tag=}")
# generate the full link including text and url here
llama_stack_version_url = f"https://github.com/meta-llama/llama-stack/releases/tag/v{llama_stack_version}"
llama_stack_version_url = f"https://github.com/meta-llama/llama-stack/releases/tag/v{version_tag}"
llama_stack_version_link = f"<a href='{llama_stack_version_url}'>release notes</a>"
project = "llama-stack"
@ -77,7 +79,7 @@ myst_enable_extensions = [
myst_substitutions = {
"docker_hub": "https://hub.docker.com/repository/docker/llamastack",
"llama_stack_version": llama_stack_version,
"llama_stack_version": version_tag,
"llama_stack_version_link": llama_stack_version_link,
}

30
docs/source/contributing/new_api_provider.md
View file

@ -17,25 +17,31 @@ Here are some example PRs to help you get started:
## Testing the Provider
Before running tests, you must have required dependencies installed. This depends on the providers or distributions you are testing. For example, if you are testing the `together` distribution, you should install dependencies via `llama stack build --template together`.
### 1. Integration Testing
- Create integration tests that use real provider instances and configurations
- For remote services, test actual API interactions
- Avoid mocking at the provider level since adapter layers tend to be thin
- Reference examples in {repopath}`tests/api`
### 2. Unit Testing (Optional)
- Add unit tests for provider-specific functionality
- See examples in {repopath}`llama_stack/providers/tests/inference/test_text_inference.py`
Integration tests are located in {repopath}`tests/integration`. These tests use the python client-SDK APIs (from the `llama_stack_client` package) to test functionality. Since these tests use client APIs, they can be run either by pointing to an instance of the Llama Stack server or "inline" by using `LlamaStackAsLibraryClient`.
Consult {repopath}`tests/integration/README.md` for more details on how to run the tests.
Note that each provider's `sample_run_config()` method (in the configuration class for that provider)
typically references some environment variables for specifying API keys and the like. You can set these in the environment or pass these via the `--env` flag to the test command.
### 2. Unit Testing
Unit tests are located in {repopath}`tests/unit`. Provider-specific unit tests are located in {repopath}`tests/unit/providers`. These tests are all run automatically as part of the CI process.
### 3. Additional end-to-end testing
### 3. End-to-End Testing
1. Start a Llama Stack server with your new provider
2. Test using client requests
3. Verify compatibility with existing client scripts in the [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main) repository
4. Document which scripts are compatible with your provider
2. Verify compatibility with existing client scripts in the [llama-stack-apps](https://github.com/meta-llama/llama-stack-apps/tree/main) repository
3. Document which scripts are compatible with your provider
## Submitting Your PR
1. Ensure all tests pass
2. Include a comprehensive test plan in your PR summary
3. Document any known limitations or considerations
4. Submit your pull request for review

73
docs/source/distributions/building_distro.md
View file

@ -4,6 +4,37 @@
This guide will walk you through the steps to get started with building a Llama Stack distribution from scratch with your choice of API providers.
### Setting your log level
In order to specify the proper logging level users can apply the following environment variable `LLAMA_STACK_LOGGING` with the following format:
`LLAMA_STACK_LOGGING=server=debug;core=info`
Where each category in the following list:
- all
- core
- server
- router
- inference
- agents
- safety
- eval
- tools
- client
Can be set to any of the following log levels:
- debug
- info
- warning
- error
- critical
The default global log level is `info`. `all` sets the log level for all components.
A user can also set `LLAMA_STACK_LOG_FILE` which will pipe the logs to the specified path as well as to the terminal. An example would be: `export LLAMA_STACK_LOG_FILE=server.log`
### Llama Stack Build
In order to build your own distribution, we recommend you clone the `llama-stack` repository.
@ -22,25 +53,25 @@ The main points to consider are:
```
llama stack build -h
usage: llama stack build [-h] [--config CONFIG] [--template TEMPLATE] [--list-templates]
[--image-type {conda,container,venv}] [--image-name IMAGE_NAME] [--print-deps-only]
usage: llama stack build [-h] [--config CONFIG] [--template TEMPLATE] [--list-templates] [--image-type {conda,container,venv}] [--image-name IMAGE_NAME] [--print-deps-only] [--run]
Build a Llama stack container
options:
-h, --help show this help message and exit
--config CONFIG Path to a config file to use for the build. You can find example configs in llama_stack/distributions/**/build.yaml.
If this argument is not provided, you will be prompted to enter information interactively
--template TEMPLATE Name of the example template config to use for build. You may use `llama stack build --list-templates` to check out the available templates
--list-templates Show the available templates for building a Llama Stack distribution
--config CONFIG Path to a config file to use for the build. You can find example configs in llama_stack/distributions/**/build.yaml. If this argument is not provided, you will
be prompted to enter information interactively (default: None)
--template TEMPLATE Name of the example template config to use for build. You may use `llama stack build --list-templates` to check out the available templates (default: None)
--list-templates Show the available templates for building a Llama Stack distribution (default: False)
--image-type {conda,container,venv}
Image Type to use for the build. This can be either conda or container or venv. If not specified, will use the image type from the template config.
Image Type to use for the build. This can be either conda or container or venv. If not specified, will use the image type from the template config. (default:
conda)
--image-name IMAGE_NAME
[for image-type=conda] Name of the conda environment to use for the build. If
not specified, currently active Conda environment will be used. If no Conda
environment is active, you must specify a name.
--print-deps-only Print the dependencies for the stack only, without building the stack
[for image-type=conda|venv] Name of the conda or virtual environment to use for the build. If not specified, currently active Conda environment will be used if
found. (default: None)
--print-deps-only Print the dependencies for the stack only, without building the stack (default: False)
--run Run the stack after building using the same image type, name, and other applicable arguments (default: False)
```
After this step is complete, a file named `<name>-build.yaml` and template file `<name>-run.yaml` will be generated and saved at the output file path specified at the end of the command.
@ -183,8 +214,8 @@ Now, let's start the Llama Stack Distribution Server. You will need the YAML con
```
llama stack run -h
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] [--disable-ipv6] [--env KEY=VALUE] [--tls-keyfile TLS_KEYFILE]
[--tls-certfile TLS_CERTFILE] [--image-type {conda,container,venv}]
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] [--disable-ipv6] [--env KEY=VALUE] [--tls-keyfile TLS_KEYFILE] [--tls-certfile TLS_CERTFILE]
[--image-type {conda,container,venv}]
config
Start the server for a Llama Stack Distribution. You should have already built (or downloaded) and configured the distribution.
@ -194,17 +225,17 @@ positional arguments:
options:
-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. Defaults to 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
Name of the image to run. Defaults to the current conda environment
--disable-ipv6 Disable IPv6 support
--env KEY=VALUE Environment variables to pass to the server in KEY=VALUE format. Can be specified multiple times.
Name of the image to run. Defaults to the current conda environment (default: None)
--disable-ipv6 Disable IPv6 support (default: False)
--env KEY=VALUE Environment variables to pass to the server in KEY=VALUE format. Can be specified multiple times. (default: [])
--tls-keyfile TLS_KEYFILE
Path to TLS key file for HTTPS
Path to TLS key file for HTTPS (default: None)
--tls-certfile TLS_CERTFILE
Path to TLS certificate file for HTTPS
Path to TLS certificate file for HTTPS (default: None)
--image-type {conda,container,venv}
Image Type used during the build. This can be either conda or container or venv.
Image Type used during the build. This can be either conda or container or venv. (default: conda)
```

22
docs/source/distributions/remote_hosted_distro/index.md
View file

@ -17,26 +17,4 @@ $ llama-stack-client configure --endpoint https://llamastack-preview.fireworks.a
$ llama-stack-client models list
```
You will see outputs:
```
$ llama-stack-client models list
+------------------------------+------------------------------+---------------+------------+
| identifier | llama_model | provider_id | metadata |
+==============================+==============================+===============+============+
| Llama3.1-8B-Instruct | Llama3.1-8B-Instruct | fireworks0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.1-70B-Instruct | Llama3.1-70B-Instruct | fireworks0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.1-405B-Instruct | Llama3.1-405B-Instruct | fireworks0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.2-1B-Instruct | Llama3.2-1B-Instruct | fireworks0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.2-3B-Instruct | Llama3.2-3B-Instruct | fireworks0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.2-11B-Vision-Instruct | Llama3.2-11B-Vision-Instruct | fireworks0 | {} |
+------------------------------+------------------------------+---------------+------------+
| Llama3.2-90B-Vision-Instruct | Llama3.2-90B-Vision-Instruct | fireworks0 | {} |
+------------------------------+------------------------------+---------------+------------+
```
Checkout the [llama-stack-client-python](https://github.com/meta-llama/llama-stack-client-python/blob/main/docs/cli_reference.md) repo for more details on how to use the `llama-stack-client` CLI. Checkout [llama-stack-app](https://github.com/meta-llama/llama-stack-apps/tree/main) for examples applications built on top of Llama Stack.

3
docs/source/distributions/self_hosted_distro/fireworks.md
View file

@ -22,7 +22,7 @@ The `llamastack/distribution-fireworks` distribution consists of the following p
| 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::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `remote::wolfram-alpha`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
@ -40,7 +40,6 @@ The following models are available by default:
- `accounts/fireworks/models/llama-v3p1-8b-instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)`
- `accounts/fireworks/models/llama-v3p1-70b-instruct (aliases: meta-llama/Llama-3.1-70B-Instruct)`
- `accounts/fireworks/models/llama-v3p1-405b-instruct (aliases: meta-llama/Llama-3.1-405B-Instruct-FP8)`
- `accounts/fireworks/models/llama-v3p2-1b-instruct (aliases: meta-llama/Llama-3.2-1B-Instruct)`
- `accounts/fireworks/models/llama-v3p2-3b-instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
- `accounts/fireworks/models/llama-v3p2-11b-vision-instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
- `accounts/fireworks/models/llama-v3p2-90b-vision-instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`

6
docs/source/distributions/self_hosted_distro/ollama.md
View file

@ -22,8 +22,8 @@ The `llamastack/distribution-ollama` distribution consists of the following prov
| 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::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
| vector_io | `inline::sqlite-vec`, `remote::chromadb`, `remote::pgvector` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol`, `remote::wolfram-alpha` |
| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
You should use this distribution if you have a regular desktop machine without very powerful GPUs. Of course, if you have powerful GPUs, you can still continue using this distribution since Ollama supports GPU acceleration.
@ -130,7 +130,7 @@ llama stack run ./run-with-safety.yaml \
### (Optional) Update Model Serving Configuration
```{note}
Please check the [model_entries](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/ollama/ollama.py#L45) for the supported Ollama models.
Please check the [model_entries](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/ollama/models.py) for the supported Ollama models.
```
To serve a new model with `ollama`

2
docs/source/distributions/self_hosted_distro/remote-vllm.md
View file

@ -21,7 +21,7 @@ The `llamastack/distribution-remote-vllm` distribution consists of the following
| 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::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol`, `remote::wolfram-alpha` |
| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |

2
docs/source/distributions/self_hosted_distro/tgi.md
View file

@ -35,7 +35,7 @@ The following environment variables can be configured:
- `LLAMA_STACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
- `INFERENCE_MODEL`: Inference model loaded into the TGI server (default: `meta-llama/Llama-3.2-3B-Instruct`)
- `TGI_URL`: URL of the TGI server with the main inference model (default: `http://127.0.0.1:8080}/v1`)
- `TGI_URL`: URL of the TGI server with the main inference model (default: `http://127.0.0.1:8080/v1`)
- `TGI_SAFETY_URL`: URL of the TGI server with the safety model (default: `http://127.0.0.1:8081/v1`)
- `SAFETY_MODEL`: Name of the safety (Llama-Guard) model to use (default: `meta-llama/Llama-Guard-3-1B`)

2
docs/source/distributions/self_hosted_distro/together.md
View file

@ -22,7 +22,7 @@ The `llamastack/distribution-together` distribution consists of the following pr
| 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::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol` |
| tool_runtime | `remote::brave-search`, `remote::tavily-search`, `inline::code-interpreter`, `inline::rag-runtime`, `remote::model-context-protocol`, `remote::wolfram-alpha` |
| vector_io | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |

8
docs/source/getting_started/index.md
View file

@ -184,7 +184,6 @@ from termcolor import cprint
from llama_stack_client.lib.agents.agent import Agent
from llama_stack_client.lib.agents.event_logger import EventLogger
from llama_stack_client.types.agent_create_params import AgentConfig
from llama_stack_client.types import Document
@ -241,13 +240,14 @@ client.tool_runtime.rag_tool.insert(
chunk_size_in_tokens=512,
)
agent_config = AgentConfig(
rag_agent = Agent(
client,
model=os.environ["INFERENCE_MODEL"],
# Define instructions for the agent ( aka system prompt)
instructions="You are a helpful assistant",
enable_session_persistence=False,
# Define tools available to the agent
toolgroups=[
tools=[
{
"name": "builtin::rag/knowledge_search",
"args": {
@ -256,8 +256,6 @@ agent_config = AgentConfig(
}
],
)
rag_agent = Agent(client, agent_config)
session_id = rag_agent.create_session("test-session")
user_prompts = [

1
docs/source/index.md
View file

@ -68,6 +68,7 @@ A number of "adapters" are available for some popular Inference and Vector Store
| FAISS | Single Node |
| SQLite-Vec| Single Node |
| Chroma | Hosted and Single Node |
| Milvus | Hosted and Single Node |
| Postgres (PGVector) | Hosted and Single Node |
| Weaviate | Hosted |

3
docs/source/providers/index.md
View file

@ -2,7 +2,7 @@
The goal of Llama Stack is to build an ecosystem where users can easily swap out different implementations for the same API. Examples for these include:
- LLM inference providers (e.g., Fireworks, Together, AWS Bedrock, Groq, Cerebras, SambaNova, vLLM, etc.),
- Vector databases (e.g., ChromaDB, Weaviate, Qdrant, FAISS, PGVector, etc.),
- Vector databases (e.g., ChromaDB, Weaviate, Qdrant, Milvus, FAISS, PGVector, etc.),
- Safety providers (e.g., Meta's Llama Guard, AWS Bedrock Guardrails, etc.)
Providers come in two flavors:
@ -55,5 +55,6 @@ vector_io/sqlite-vec
vector_io/chromadb
vector_io/pgvector
vector_io/qdrant
vector_io/milvus
vector_io/weaviate
```

170
docs/source/references/evals_reference/index.md
View file

@ -24,19 +24,9 @@ The Evaluation APIs are associated with a set of Resources as shown in the follo
- Associated with `Benchmark` resource.
Use the following decision tree to decide how to use LlamaStack Evaluation flow.
![Eval Flow](./resources/eval-flow.png)
```{admonition} Note on Benchmark v.s. Application Evaluation
:class: tip
- **Benchmark Evaluation** is a well-defined eval-task consisting of `dataset` and `scoring_function`. The generation (inference or agent) will be done as part of evaluation.
- **Application Evaluation** assumes users already have app inputs & generated outputs. Evaluation will purely focus on scoring the generated outputs via scoring functions (e.g. LLM-as-judge).
```
## Evaluation Examples Walkthrough
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/10CHyykee9j2OigaIcRv47BKG9mrNm0tJ?usp=sharing)
[![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/notebooks/Llama_Stack_Benchmark_Evals.ipynb)
It is best to open this notebook in Colab to follow along with the examples.
@ -63,20 +53,29 @@ eval_rows = ds.to_pandas().to_dict(orient="records")
- Run evaluate on the dataset
```python
from rich.pretty import pprint
from tqdm import tqdm
SYSTEM_PROMPT_TEMPLATE = """
You are an expert in Agriculture whose job is to answer questions from the user using images.
You are an expert in {subject} whose job is to answer questions from the user using images.
First, reason about the correct answer.
Then write the answer in the following format where X is exactly one of A,B,C,D:
Answer: X
Make sure X is one of A,B,C,D.
If you are uncertain of the correct answer, guess the most likely one.
"""
system_message = {
"role": "system",
"content": SYSTEM_PROMPT_TEMPLATE,
"content": SYSTEM_PROMPT_TEMPLATE.format(subject=subset),
}
# register the evaluation benchmark task with the dataset and scoring function
client.benchmarks.register(
benchmark_id="meta-reference::mmmu",
dataset_id=f"mmmu-{subset}-{split}",
@ -87,14 +86,15 @@ response = client.eval.evaluate_rows(
benchmark_id="meta-reference::mmmu",
input_rows=eval_rows,
scoring_functions=["basic::regex_parser_multiple_choice_answer"],
task_config={
"type": "benchmark",
benchmark_config={
"eval_candidate": {
"type": "model",
"model": "meta-llama/Llama-3.2-90B-Vision-Instruct",
"sampling_params": {
"strategy": {
"type": "greedy",
"type": "top_p",
"temperature": 1.0,
"top_p": 0.95,
},
"max_tokens": 4096,
"repeat_penalty": 1.0,
@ -103,6 +103,7 @@ response = client.eval.evaluate_rows(
},
},
)
pprint(response)
```
#### 1.2. Running SimpleQA
@ -115,10 +116,9 @@ simpleqa_dataset_id = "huggingface::simpleqa"
_ = client.datasets.register(
dataset_id=simpleqa_dataset_id,
provider_id="huggingface",
url={"uri": "https://huggingface.co/datasets/llamastack/evals"},
url={"uri": "https://huggingface.co/datasets/llamastack/simpleqa"},
metadata={
"path": "llamastack/evals",
"name": "evals__simpleqa",
"path": "llamastack/simpleqa",
"split": "train",
},
dataset_schema={
@ -145,8 +145,7 @@ response = client.eval.evaluate_rows(
benchmark_id="meta-reference::simpleqa",
input_rows=eval_rows.rows,
scoring_functions=["llm-as-judge::405b-simpleqa"],
task_config={
"type": "benchmark",
benchmark_config={
"eval_candidate": {
"type": "model",
"model": "meta-llama/Llama-3.2-90B-Vision-Instruct",
@ -160,6 +159,7 @@ response = client.eval.evaluate_rows(
},
},
)
pprint(response)
```
@ -170,19 +170,17 @@ response = client.eval.evaluate_rows(
```python
agent_config = {
"model": "meta-llama/Llama-3.1-405B-Instruct",
"instructions": "You are a helpful assistant",
"model": "meta-llama/Llama-3.3-70B-Instruct",
"instructions": "You are a helpful assistant that have access to tool to search the web. ",
"sampling_params": {
"strategy": {
"type": "greedy",
},
},
"tools": [
{
"type": "brave_search",
"engine": "tavily",
"api_key": userdata.get("TAVILY_SEARCH_API_KEY"),
"type": "top_p",
"temperature": 0.5,
"top_p": 0.9,
}
},
"toolgroups": [
"builtin::websearch",
],
"tool_choice": "auto",
"tool_prompt_format": "json",
@ -195,25 +193,22 @@ response = client.eval.evaluate_rows(
benchmark_id="meta-reference::simpleqa",
input_rows=eval_rows.rows,
scoring_functions=["llm-as-judge::405b-simpleqa"],
task_config={
"type": "benchmark",
benchmark_config={
"eval_candidate": {
"type": "agent",
"config": agent_config,
},
},
)
pprint(response)
```
### 3. Agentic Application Dataset Scoring
- Llama Stack offers a library of scoring functions and the `/scoring` API, allowing you to run evaluations on your pre-annotated AI application datasets.
[![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)
- In this example, we will work with an example RAG dataset and couple of scoring functions for evaluation.
- `llm-as-judge::base`: LLM-As-Judge with custom judge prompt & model.
- `braintrust::factuality`: Factuality scorer from [braintrust](https://github.com/braintrustdata/autoevals).
- `basic::subset_of`: Basic checking if generated answer is a subset of expected answer.
Llama Stack offers a library of scoring functions and the `/scoring` API, allowing you to run evaluations on your pre-annotated AI application datasets.
- Please checkout our [Llama Stack Playground](https://llama-stack.readthedocs.io/en/latest/playground/index.html) for an interactive interface to upload datasets and run scorings.
In this example, we will work with an example RAG dataset you have built previously, label with an annotation, and use LLM-As-Judge with custom judge prompt for scoring. Please checkout our [Llama Stack Playground](https://llama-stack.readthedocs.io/en/latest/playground/index.html) for an interactive interface to upload datasets and run scorings.
```python
judge_model_id = "meta-llama/Llama-3.1-405B-Instruct-FP8"
@ -280,18 +275,25 @@ response = client.scoring.score(
The following examples give the quick steps to start running evaluations using the llama-stack-client CLI.
#### Benchmark Evaluation CLI
Usage: There are 2 inputs necessary for running a benchmark eval
- `eval-task-id`: the identifier associated with the eval task. Each `Benchmark` is parametrized by
- `dataset_id`: the identifier associated with the dataset.
- `List[scoring_function_id]`: list of scoring function identifiers.
- `eval-task-config`: specifies the configuration of the model / agent to evaluate on.
There are 3 necessary input for running a benchmark eval
- `list of benchmark_ids`: The list of benchmark ids to run evaluation on
- `model-id`: The model id to evaluate on
- `utput_dir`: Path to store the evaluate results
```
llama-stack-client eval run-benchmark <benchmark_id_1> <benchmark_id_2> ... \
--model_id <model id to evaluate on> \
--output_dir <directory to store the evaluate results> \
```
You can run
```
llama-stack-client eval run-benchmark help
```
to see the description of all the flags to run benckmark eval
```
llama-stack-client eval run_benchmark <eval-task-id> \
--eval-task-config ~/benchmark_config.json \
--visualize
```
In the output log, you can find the path to the file that has your evaluation results. Open that file and you can see you aggrgate
evaluation results over there.
#### Application Evaluation CLI
@ -317,28 +319,9 @@ The `BenchmarkConfig` are user specified config to define:
2. Optionally scoring function params to allow customization of scoring function behaviour. This is useful to parameterize generic scoring functions such as LLMAsJudge with custom `judge_model` / `judge_prompt`.
**Example Benchmark BenchmarkConfig**
**Example BenchmarkConfig**
```json
{
"type": "benchmark",
"eval_candidate": {
"type": "model",
"model": "Llama3.2-3B-Instruct",
"sampling_params": {
"strategy": {
"type": "greedy",
},
"max_tokens": 0,
"repetition_penalty": 1.0
}
}
}
```
**Example Application BenchmarkConfig**
```json
{
"type": "app",
"eval_candidate": {
"type": "model",
"model": "Llama3.1-405B-Instruct",
@ -362,3 +345,52 @@ The `BenchmarkConfig` are user specified config to define:
}
}
```
## Open-benchmark Contributing Guide
### Create the new dataset for your new benchmark
An eval open-benchmark essentially contains 2 parts:
- `raw data`: The raw dataset associated with the benchmark. You typically need to search the original paper that introduces the benchmark and find the canonical dataset (usually hosted on huggingface)
- `prompt template`: How to ask the candidate model to generate the answer (prompt template plays a critical role to the evaluation results). Tyically, you can find the reference prompt template associated with the benchmark in benchmarks author's repo ([exmaple](https://github.com/idavidrein/gpqa/blob/main/prompts/chain_of_thought.txt)) or some other popular open source repos ([example](https://github.com/openai/simple-evals/blob/0a6e8f62e52bc5ae915f752466be3af596caf392/common.py#L14))
To create new open-benmark in llama stack, you need to combine the prompt template and the raw data into the `chat_completion_input` column in the evaluation dataset.
Llama stack enforeces the evaluate dataset schema to contain at least 3 columns:
- `chat_completion_input`: The actual input to the model to run the generation for eval
- `input_query`: The raw input from the raw dataset without the prompt template
- `expected_answer`: The ground truth for scoring functions to calcalate the score from.
You need to write a script [example convert script](https://gist.github.com/yanxi0830/118e9c560227d27132a7fd10e2c92840) to convert the benchmark raw dataset to llama stack format eval dataset and update the dataset to huggingface [example benchmark dataset](https://huggingface.co/datasets/llamastack/mmmu)
### Find scoring function for your new benchmark
The purpose of scoring function is to calculate the score for each example based on candidate model generation result and expected_answer. It also aggregates the scores from all the examples and generate the final evaluate results.
Firstly, you can see if the existing [llama stack scoring functions](https://github.com/meta-llama/llama-stack/tree/main/llama_stack/providers/inline/scoring) can fulfill your need. If not, you need to write a new scoring function based on what benchmark author / other open source repo describe.
### Add new benchmark into template
Firstly, you need to add the evaluation dataset associated with your benchmark under `datasets` resource in the [open-benchmark](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/templates/open-benchmark/run.yaml)
Secondly, you need to add the new benchmark you just created under the `benchmarks` resource in the same template. To add the new benchmark, you need to have
- `benchmark_id`: identifier of the benchmark
- `dataset_id`: identifier of the dataset associated with your benchmark
- `scoring_functions`: scoring function to calculate the score based on generation results and expected_answer
### Test the new benchmark
Spin up llama stack server with 'open-benchmark' templates
```
llama stack run llama_stack/templates/open-benchmark/run.yaml
```
Run eval benchmark CLI with your new benchmark id
```
llama-stack-client eval run-benchmark <new_benchmark_id> \
--model_id <model id to evaluate on> \
--output_dir <directory to store the evaluate results> \
```

15
docs/source/references/llama_cli_reference/index.md
View file

@ -1,6 +1,6 @@
# llama (server-side) CLI Reference
The `llama` CLI tool helps you setup and use the Llama Stack. It should be available on your path after installing the `llama-stack` package.
The `llama` CLI tool helps you set up and use the Llama Stack. The CLI is available on your path after installing the `llama-stack` package.
## Installation
@ -27,9 +27,9 @@ You have two ways to install Llama Stack:
## `llama` subcommands
1. `download`: `llama` cli tools supports downloading the model from Meta or Hugging Face.
2. `model`: Lists available models and their properties.
3. `stack`: Allows you to build and run a Llama Stack server. You can read more about this [here](../../distributions/building_distro).
1. `download`: Supports downloading models from Meta or Hugging Face. [Downloading models](#downloading-models)
2. `model`: Lists available models and their properties. [Understanding models](#understand-the-models)
3. `stack`: Allows you to build a stack using the `llama stack` distribution and run a Llama Stack server. You can read more about how to build a Llama Stack distribution in the [Build your own Distribution](../../distributions/building_distro) documentation.
### Sample Usage
@ -117,7 +117,7 @@ You should see a table like this:
+----------------------------------+------------------------------------------+----------------+
```
To download models, you can use the llama download command.
To download models, you can use the `llama download` command.
### Downloading from [Meta](https://llama.meta.com/llama-downloads/)
@ -191,7 +191,7 @@ You should see a table like this:
The `llama model` command helps you explore the model’s interface.
1. `download`: Download the model from different sources. (meta, huggingface)
2. `list`: Lists all the models available for download with hardware requirements to deploy the models.
2. `list`: Lists all the models available for download with hardware requirements for deploying the models.
3. `prompt-format`: Show llama model message formats.
4. `describe`: Describes all the properties of the model.
@ -262,13 +262,12 @@ llama model prompt-format -m Llama3.2-3B-Instruct
![alt text](../../../resources/prompt-format.png)
You will be shown a Markdown formatted description of the model interface and how prompts / messages are formatted for various scenarios.
**NOTE**: Outputs in terminal are color printed to show special tokens.
### Remove model
You can run `llama model remove` to remove unecessary model:
You can run `llama model remove` to remove an unnecessary model:
```
llama model remove -m Llama-Guard-3-8B-int8

12
docs/zero_to_hero_guide/04_Tool_Calling101.ipynb
View file

@ -294,8 +294,9 @@
" # Initialize custom tool (ensure `WebSearchTool` is defined earlier in the notebook)\n",
" webSearchTool = WebSearchTool(api_key=BRAVE_SEARCH_API_KEY)\n",
"\n",
" # Define the agent configuration, including the model and tool setup\n",
" agent_config = AgentConfig(\n",
" # Create an agent instance with the client and configuration\n",
" agent = Agent(\n",
" client, \n",
" model=MODEL_NAME,\n",
" instructions=\"\"\"You are a helpful assistant that responds to user queries with relevant information and cites sources when available.\"\"\",\n",
" sampling_params={\n",
@ -303,17 +304,12 @@
" \"type\": \"greedy\",\n",
" },\n",
" },\n",
" tools=[webSearchTool.get_tool_definition()],\n",
" tool_choice=\"auto\",\n",
" tool_prompt_format=\"python_list\",\n",
" tools=[webSearchTool],\n",
" input_shields=input_shields,\n",
" output_shields=output_shields,\n",
" enable_session_persistence=False,\n",
" )\n",
"\n",
" # Create an agent instance with the client and configuration\n",
" agent = Agent(client, agent_config, [webSearchTool])\n",
"\n",
" # Create a session for interaction and print the session ID\n",
" session_id = agent.create_session(\"test-session\")\n",
" print(f\"Created session_id={session_id} for Agent({agent.agent_id})\")\n",

11
docs/zero_to_hero_guide/07_Agents101.ipynb
View file

@ -110,12 +110,12 @@
"from llama_stack_client import LlamaStackClient\n",
"from llama_stack_client.lib.agents.agent import Agent\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types.agent_create_params import AgentConfig\n",
"\n",
"\n",
"async def agent_example():\n",
" client = LlamaStackClient(base_url=f\"http://{HOST}:{PORT}\")\n",
" agent_config = AgentConfig(\n",
" agent = Agent(\n",
" client, \n",
" model=MODEL_NAME,\n",
" instructions=\"You are a helpful assistant! If you call builtin tools like brave search, follow the syntax brave_search.call(…)\",\n",
" sampling_params={\n",
@ -130,14 +130,7 @@
" \"api_key\": BRAVE_SEARCH_API_KEY,\n",
" }\n",
" ],\n",
" tool_choice=\"auto\",\n",
" tool_prompt_format=\"function_tag\",\n",
" input_shields=[],\n",
" output_shields=[],\n",
" enable_session_persistence=False,\n",
" )\n",
"\n",
" agent = Agent(client, agent_config)\n",
" session_id = agent.create_session(\"test-session\")\n",
" print(f\"Created session_id={session_id} for Agent({agent.agent_id})\")\n",
"\n",

2
docs/zero_to_hero_guide/README.md
View file

@ -40,7 +40,7 @@ If you're looking for more specific topics, we have a [Zero to Hero Guide](#next
ollama run llama3.2:3b-instruct-fp16 --keepalive -1m
```
**Note**:
- The supported models for llama stack for now is listed in [here](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/ollama/ollama.py#L43)
- The supported models for llama stack for now is listed in [here](https://github.com/meta-llama/llama-stack/blob/main/llama_stack/providers/remote/inference/ollama/models.py)
- `keepalive -1m` is used so that ollama continues to keep the model in memory indefinitely. Otherwise, ollama frees up memory and you would have to run `ollama run` again.
---

24
docs/zero_to_hero_guide/Tool_Calling101_Using_Together_Llama_Stack_Server.ipynb
View file

@ -103,7 +103,6 @@
"from llama_stack_client.lib.agents.agent import Agent\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types.agent_create_params import (\n",
" AgentConfig,\n",
" AgentConfigToolSearchToolDefinition,\n",
")\n",
"\n",
@ -117,7 +116,8 @@
") -> Agent:\n",
" \"\"\"Create an agent with specified tools.\"\"\"\n",
" print(\"Using the following model: \", model)\n",
" agent_config = AgentConfig(\n",
" return Agent(\n",
" client, \n",
" model=model,\n",
" instructions=instructions,\n",
" sampling_params={\n",
@ -126,12 +126,7 @@
" },\n",
" },\n",
" tools=tools,\n",
" tool_choice=\"auto\",\n",
" tool_prompt_format=\"json\",\n",
" enable_session_persistence=True,\n",
" )\n",
"\n",
" return Agent(client, agent_config)\n"
" )\n"
]
},
{
@ -360,9 +355,9 @@
" # Create the agent with the tool\n",
" weather_tool = WeatherTool()\n",
"\n",
" agent_config = AgentConfig(\n",
" agent = Agent(\n",
" client=client, \n",
" model=LLAMA31_8B_INSTRUCT,\n",
" # model=model_name,\n",
" instructions=\"\"\"\n",
" You are a weather assistant that can provide weather information.\n",
" Always specify the location clearly in your responses.\n",
@ -373,16 +368,9 @@
" \"type\": \"greedy\",\n",
" },\n",
" },\n",
" tools=[weather_tool.get_tool_definition()],\n",
" tool_choice=\"auto\",\n",
" tool_prompt_format=\"json\",\n",
" input_shields=[],\n",
" output_shields=[],\n",
" enable_session_persistence=True,\n",
" tools=[weather_tool],\n",
" )\n",
"\n",
" agent = Agent(client=client, agent_config=agent_config, custom_tools=[weather_tool])\n",
"\n",
" return agent\n",
"\n",
"\n",