phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Convert SamplingParams.strategy to a union (#767)

Browse source 
# What does this PR do?

Cleans up how we provide sampling params. Earlier, strategy was an enum
and all params (top_p, temperature, top_k) across all strategies were
grouped. We now have a strategy union object with each strategy (greedy,
top_p, top_k) having its corresponding params.
Earlier, 
```
class SamplingParams: 
    strategy: enum ()
    top_p, temperature, top_k and other params
```
However, the `strategy` field was not being used in any providers making
it confusing to know the exact sampling behavior purely based on the
params since you could pass temperature, top_p, top_k and how the
provider would interpret those would not be clear.

Hence we introduced -- a union where the strategy and relevant params
are all clubbed together to avoid this confusion.

Have updated all providers, tests, notebooks, readme and otehr places
where sampling params was being used to use the new format.
   

## Test Plan
`pytest llama_stack/providers/tests/inference/groq/test_groq_utils.py`
// inference on ollama, fireworks and together 
`with-proxy pytest -v -s -k "ollama"
--inference-model="meta-llama/Llama-3.1-8B-Instruct"
llama_stack/providers/tests/inference/test_text_inference.py `
// agents on fireworks 
`pytest -v -s -k 'fireworks and create_agent'
--inference-model="meta-llama/Llama-3.1-8B-Instruct"
llama_stack/providers/tests/agents/test_agents.py
--safety-shield="meta-llama/Llama-Guard-3-8B"`

## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [X] Ran pre-commit to handle lint / formatting issues.
- [X] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [X] Updated relevant documentation.
- [X] Wrote necessary unit or integration tests.

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
This commit is contained in:
Hardik Shah 2025-01-15 05:38:51 -08:00 • committed by GitHub
parent 300e6e2702
commit a51c8b4efc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
29 changed files with 611 additions and 388 deletions
Download patch file Download diff file Expand all files Collapse all files

78
docs/zero_to_hero_guide/04_Tool_Calling101.ipynb
View file

@ -26,27 +26,28 @@
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import requests\n",
"import json\n",
"import asyncio\n",
"import nest_asyncio\n",
"import json\n",
"import os\n",
"from typing import Dict, List\n",
"\n",
"import nest_asyncio\n",
"import requests\n",
"from dotenv import load_dotenv\n",
"from llama_stack_client import LlamaStackClient\n",
"from llama_stack_client.lib.agents.custom_tool import CustomTool\n",
"from llama_stack_client.types.shared.tool_response_message import ToolResponseMessage\n",
"from llama_stack_client.types import CompletionMessage\n",
"from llama_stack_client.lib.agents.agent import Agent\n",
"from llama_stack_client.lib.agents.custom_tool import CustomTool\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types import CompletionMessage\n",
"from llama_stack_client.types.agent_create_params import AgentConfig\n",
"from llama_stack_client.types.shared.tool_response_message import ToolResponseMessage\n",
"\n",
"# Allow asyncio to run in Jupyter Notebook\n",
"nest_asyncio.apply()\n",
"\n",
"HOST='localhost'\n",
"PORT=5001\n",
"MODEL_NAME='meta-llama/Llama-3.2-3B-Instruct'"
"HOST = \"localhost\"\n",
"PORT = 5001\n",
"MODEL_NAME = \"meta-llama/Llama-3.2-3B-Instruct\"\n"
]
},
{
@ -69,7 +70,7 @@
"outputs": [],
"source": [
"load_dotenv()\n",
"BRAVE_SEARCH_API_KEY = os.environ['BRAVE_SEARCH_API_KEY']"
"BRAVE_SEARCH_API_KEY = os.environ[\"BRAVE_SEARCH_API_KEY\"]\n"
]
},
{
@ -118,7 +119,7 @@
" cleaned = {k: v for k, v in results[idx].items() if k in selected_keys}\n",
" clean_response.append(cleaned)\n",
"\n",
" return {\"query\": query, \"top_k\": clean_response}"
" return {\"query\": query, \"top_k\": clean_response}\n"
]
},
{
@ -157,25 +158,29 @@
" for message in messages:\n",
" if isinstance(message, CompletionMessage) and message.tool_calls:\n",
" for tool_call in message.tool_calls:\n",
" if 'query' in tool_call.arguments:\n",
" query = tool_call.arguments['query']\n",
" if \"query\" in tool_call.arguments:\n",
" query = tool_call.arguments[\"query\"]\n",
" call_id = tool_call.call_id\n",
"\n",
" if query:\n",
" search_result = await self.run_impl(query)\n",
" return [ToolResponseMessage(\n",
" call_id=call_id,\n",
" role=\"ipython\",\n",
" content=self._format_response_for_agent(search_result),\n",
" tool_name=\"brave_search\"\n",
" )]\n",
" return [\n",
" ToolResponseMessage(\n",
" call_id=call_id,\n",
" role=\"ipython\",\n",
" content=self._format_response_for_agent(search_result),\n",
" tool_name=\"brave_search\",\n",
" )\n",
" ]\n",
"\n",
" return [ToolResponseMessage(\n",
" call_id=\"no_call_id\",\n",
" role=\"ipython\",\n",
" content=\"No query provided.\",\n",
" tool_name=\"brave_search\"\n",
" )]\n",
" return [\n",
" ToolResponseMessage(\n",
" call_id=\"no_call_id\",\n",
" role=\"ipython\",\n",
" content=\"No query provided.\",\n",
" tool_name=\"brave_search\",\n",
" )\n",
" ]\n",
"\n",
" def _format_response_for_agent(self, search_result):\n",
" parsed_result = json.loads(search_result)\n",
@ -186,7 +191,7 @@
" f\" URL: {result.get('url', 'No URL')}\\n\"\n",
" f\" Description: {result.get('description', 'No Description')}\\n\\n\"\n",
" )\n",
" return formatted_result"
" return formatted_result\n"
]
},
{
@ -209,7 +214,7 @@
"async def execute_search(query: str):\n",
" web_search_tool = WebSearchTool(api_key=BRAVE_SEARCH_API_KEY)\n",
" result = await web_search_tool.run_impl(query)\n",
" print(\"Search Results:\", result)"
" print(\"Search Results:\", result)\n"
]
},
{
@ -236,7 +241,7 @@
],
"source": [
"query = \"Latest developments in quantum computing\"\n",
"asyncio.run(execute_search(query))"
"asyncio.run(execute_search(query))\n"
]
},
{
@ -288,19 +293,17 @@
"\n",
" # Initialize custom tool (ensure `WebSearchTool` is defined earlier in the notebook)\n",
" webSearchTool = WebSearchTool(api_key=BRAVE_SEARCH_API_KEY)\n",
" \n",
"\n",
" # Define the agent configuration, including the model and tool setup\n",
" agent_config = AgentConfig(\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",
" \"strategy\": \"greedy\",\n",
" \"temperature\": 1.0,\n",
" \"top_p\": 0.9,\n",
" \"strategy\": {\n",
" \"type\": \"greedy\",\n",
" },\n",
" },\n",
" tools=[\n",
" webSearchTool.get_tool_definition()\n",
" ],\n",
" tools=[webSearchTool.get_tool_definition()],\n",
" tool_choice=\"auto\",\n",
" tool_prompt_format=\"python_list\",\n",
" input_shields=input_shields,\n",
@ -329,8 +332,9 @@
" async for log in EventLogger().log(response):\n",
" log.print()\n",
"\n",
"\n",
"# Run the function asynchronously in a Jupyter Notebook cell\n",
"await run_main(disable_safety=True)"
"await run_main(disable_safety=True)\n"
]
}
],

20
docs/zero_to_hero_guide/07_Agents101.ipynb
View file

@ -50,8 +50,8 @@
"outputs": [],
"source": [
"HOST = \"localhost\" # Replace with your host\n",
"PORT = 5001 # Replace with your port\n",
"MODEL_NAME='meta-llama/Llama-3.2-3B-Instruct'"
"PORT = 5001 # Replace with your port\n",
"MODEL_NAME = \"meta-llama/Llama-3.2-3B-Instruct\"\n"
]
},
{
@ -60,10 +60,12 @@
"metadata": {},
"outputs": [],
"source": [
"from dotenv import load_dotenv\n",
"import os\n",
"\n",
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()\n",
"BRAVE_SEARCH_API_KEY = os.environ['BRAVE_SEARCH_API_KEY']"
"BRAVE_SEARCH_API_KEY = os.environ[\"BRAVE_SEARCH_API_KEY\"]\n"
]
},
{
@ -104,20 +106,22 @@
],
"source": [
"import os\n",
"\n",
"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",
" 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",
" \"strategy\": \"greedy\",\n",
" \"temperature\": 1.0,\n",
" \"top_p\": 0.9,\n",
" \"strategy\": {\n",
" \"type\": \"greedy\",\n",
" },\n",
" },\n",
" tools=[\n",
" {\n",
@ -157,7 +161,7 @@
" log.print()\n",
"\n",
"\n",
"await agent_example()"
"await agent_example()\n"
]
},
{

10
docs/zero_to_hero_guide/README.md
View file

@ -157,7 +157,15 @@ curl http://localhost:$LLAMA_STACK_PORT/alpha/inference/chat-completion
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Write me a 2-sentence poem about the moon"}
],
"sampling_params": {"temperature": 0.7, "seed": 42, "max_tokens": 512}
"sampling_params": {
"strategy": {
"type": "top_p",
"temperatrue": 0.7,
"top_p": 0.95,
},
"seed": 42,
"max_tokens": 512
}
}
EOF
```

94
docs/zero_to_hero_guide/Tool_Calling101_Using_Together's_Llama_Stack_Server.ipynb
View file

@ -83,8 +83,8 @@
},
"outputs": [],
"source": [
"LLAMA_STACK_API_TOGETHER_URL=\"https://llama-stack.together.ai\"\n",
"LLAMA31_8B_INSTRUCT = \"Llama3.1-8B-Instruct\""
"LLAMA_STACK_API_TOGETHER_URL = \"https://llama-stack.together.ai\"\n",
"LLAMA31_8B_INSTRUCT = \"Llama3.1-8B-Instruct\"\n"
]
},
{
@ -107,12 +107,13 @@
" AgentConfigToolSearchToolDefinition,\n",
")\n",
"\n",
"\n",
"# Helper function to create an agent with tools\n",
"async def create_tool_agent(\n",
" client: LlamaStackClient,\n",
" tools: List[Dict],\n",
" instructions: str = \"You are a helpful assistant\",\n",
" model: str = LLAMA31_8B_INSTRUCT\n",
" model: str = LLAMA31_8B_INSTRUCT,\n",
") -> Agent:\n",
" \"\"\"Create an agent with specified tools.\"\"\"\n",
" print(\"Using the following model: \", model)\n",
@ -120,9 +121,9 @@
" model=model,\n",
" instructions=instructions,\n",
" sampling_params={\n",
" \"strategy\": \"greedy\",\n",
" \"temperature\": 1.0,\n",
" \"top_p\": 0.9,\n",
" \"strategy\": {\n",
" \"type\": \"greedy\",\n",
" },\n",
" },\n",
" tools=tools,\n",
" tool_choice=\"auto\",\n",
@ -130,7 +131,7 @@
" enable_session_persistence=True,\n",
" )\n",
"\n",
" return Agent(client, agent_config)"
" return Agent(client, agent_config)\n"
]
},
{
@ -172,7 +173,8 @@
],
"source": [
"# comment this if you don't have a BRAVE_SEARCH_API_KEY\n",
"os.environ[\"BRAVE_SEARCH_API_KEY\"] = 'YOUR_BRAVE_SEARCH_API_KEY'\n",
"os.environ[\"BRAVE_SEARCH_API_KEY\"] = \"YOUR_BRAVE_SEARCH_API_KEY\"\n",
"\n",
"\n",
"async def create_search_agent(client: LlamaStackClient) -> Agent:\n",
" \"\"\"Create an agent with Brave Search capability.\"\"\"\n",
@ -186,8 +188,8 @@
"\n",
" return await create_tool_agent(\n",
" client=client,\n",
" tools=[search_tool], # set this to [] if you don't have a BRAVE_SEARCH_API_KEY\n",
" model = LLAMA31_8B_INSTRUCT,\n",
" tools=[search_tool], # set this to [] if you don't have a BRAVE_SEARCH_API_KEY\n",
" model=LLAMA31_8B_INSTRUCT,\n",
" instructions=\"\"\"\n",
" You are a research assistant that can search the web.\n",
" Always cite your sources with URLs when providing information.\n",
@ -198,9 +200,10 @@
"\n",
" SOURCES:\n",
" - [Source title](URL)\n",
" \"\"\"\n",
" \"\"\",\n",
" )\n",
"\n",
"\n",
"# Example usage\n",
"async def search_example():\n",
" client = LlamaStackClient(base_url=LLAMA_STACK_API_TOGETHER_URL)\n",
@ -212,7 +215,7 @@
" # Example queries\n",
" queries = [\n",
" \"What are the latest developments in quantum computing?\",\n",
" #\"Who won the most recent Super Bowl?\",\n",
" # \"Who won the most recent Super Bowl?\",\n",
" ]\n",
"\n",
" for query in queries:\n",
@ -227,8 +230,9 @@
" async for log in EventLogger().log(response):\n",
" log.print()\n",
"\n",
"\n",
"# Run the example (in Jupyter, use asyncio.run())\n",
"await search_example()"
"await search_example()\n"
]
},
{
@ -286,12 +290,16 @@
}
],
"source": [
"from typing import TypedDict, Optional, Dict, Any\n",
"from datetime import datetime\n",
"import json\n",
"from llama_stack_client.types.tool_param_definition_param import ToolParamDefinitionParam\n",
"from llama_stack_client.types import CompletionMessage,ToolResponseMessage\n",
"from datetime import datetime\n",
"from typing import Any, Dict, Optional, TypedDict\n",
"\n",
"from llama_stack_client.lib.agents.custom_tool import CustomTool\n",
"from llama_stack_client.types import CompletionMessage, ToolResponseMessage\n",
"from llama_stack_client.types.tool_param_definition_param import (\n",
" ToolParamDefinitionParam,\n",
")\n",
"\n",
"\n",
"class WeatherTool(CustomTool):\n",
" \"\"\"Example custom tool for weather information.\"\"\"\n",
@ -305,16 +313,15 @@
" def get_params_definition(self) -> Dict[str, ToolParamDefinitionParam]:\n",
" return {\n",
" \"location\": ToolParamDefinitionParam(\n",
" param_type=\"str\",\n",
" description=\"City or location name\",\n",
" required=True\n",
" param_type=\"str\", description=\"City or location name\", required=True\n",
" ),\n",
" \"date\": ToolParamDefinitionParam(\n",
" param_type=\"str\",\n",
" description=\"Optional date (YYYY-MM-DD)\",\n",
" required=False\n",
" )\n",
" required=False,\n",
" ),\n",
" }\n",
"\n",
" async def run(self, messages: List[CompletionMessage]) -> List[ToolResponseMessage]:\n",
" assert len(messages) == 1, \"Expected single message\"\n",
"\n",
@ -337,20 +344,14 @@
" )\n",
" return [message]\n",
"\n",
" async def run_impl(self, location: str, date: Optional[str] = None) -> Dict[str, Any]:\n",
" async def run_impl(\n",
" self, location: str, date: Optional[str] = None\n",
" ) -> Dict[str, Any]:\n",
" \"\"\"Simulate getting weather data (replace with actual API call).\"\"\"\n",
" # Mock implementation\n",
" if date:\n",
" return {\n",
" \"temperature\": 90.1,\n",
" \"conditions\": \"sunny\",\n",
" \"humidity\": 40.0\n",
" }\n",
" return {\n",
" \"temperature\": 72.5,\n",
" \"conditions\": \"partly cloudy\",\n",
" \"humidity\": 65.0\n",
" }\n",
" return {\"temperature\": 90.1, \"conditions\": \"sunny\", \"humidity\": 40.0}\n",
" return {\"temperature\": 72.5, \"conditions\": \"partly cloudy\", \"humidity\": 65.0}\n",
"\n",
"\n",
"async def create_weather_agent(client: LlamaStackClient) -> Agent:\n",
@ -358,38 +359,33 @@
"\n",
" # Create the agent with the tool\n",
" weather_tool = WeatherTool()\n",
" \n",
"\n",
" agent_config = AgentConfig(\n",
" model=LLAMA31_8B_INSTRUCT,\n",
" #model=model_name,\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",
" Include both temperature and conditions in your summaries.\n",
" \"\"\",\n",
" sampling_params={\n",
" \"strategy\": \"greedy\",\n",
" \"temperature\": 1.0,\n",
" \"top_p\": 0.9,\n",
" \"strategy\": {\n",
" \"type\": \"greedy\",\n",
" },\n",
" },\n",
" tools=[\n",
" weather_tool.get_tool_definition()\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",
" enable_session_persistence=True,\n",
" )\n",
"\n",
" agent = Agent(\n",
" client=client,\n",
" agent_config=agent_config,\n",
" custom_tools=[weather_tool]\n",
" )\n",
" agent = Agent(client=client, agent_config=agent_config, custom_tools=[weather_tool])\n",
"\n",
" return agent\n",
"\n",
"\n",
"# Example usage\n",
"async def weather_example():\n",
" client = LlamaStackClient(base_url=LLAMA_STACK_API_TOGETHER_URL)\n",
@ -413,12 +409,14 @@
" async for log in EventLogger().log(response):\n",
" log.print()\n",
"\n",
"\n",
"# For Jupyter notebooks\n",
"import nest_asyncio\n",
"\n",
"nest_asyncio.apply()\n",
"\n",
"# Run the example\n",
"await weather_example()"
"await weather_example()\n"
]
},
{