mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
add tools to chat completion request
This commit is contained in:
Hardik Shah
parent
863bb915e1
commit
f3f7af7b8a
26 changed files with 558 additions and 226 deletions
|
|
@ -2,12 +2,14 @@ import textwrap
|
|||
import unittest
|
||||
from datetime import datetime
|
||||
|
||||
from llama_models.llama3_1.api.datatypes import (
|
||||
from llama_models.llama3.api.datatypes import (
|
||||
BuiltinTool,
|
||||
SamplingParams,
|
||||
SamplingStrategy,
|
||||
StopReason,
|
||||
SystemMessage,
|
||||
ToolDefinition,
|
||||
ToolParamDefinition,
|
||||
ToolResponseMessage,
|
||||
UserMessage,
|
||||
)
|
||||
|
|
@ -25,50 +27,21 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
self.api = await get_provider_impl(ollama_config, {})
|
||||
await self.api.initialize()
|
||||
|
||||
current_date = datetime.now()
|
||||
formatted_date = current_date.strftime("%d %B %Y")
|
||||
self.system_prompt = SystemMessage(
|
||||
content=textwrap.dedent(
|
||||
f"""
|
||||
Environment: ipython
|
||||
Tools: brave_search
|
||||
|
||||
Cutting Knowledge Date: December 2023
|
||||
Today Date:{formatted_date}
|
||||
|
||||
"""
|
||||
),
|
||||
)
|
||||
|
||||
self.system_prompt_with_custom_tool = SystemMessage(
|
||||
content=textwrap.dedent(
|
||||
"""
|
||||
Environment: ipython
|
||||
Tools: brave_search, wolfram_alpha, photogen
|
||||
|
||||
Cutting Knowledge Date: December 2023
|
||||
Today Date: 30 July 2024
|
||||
|
||||
|
||||
You have access to the following functions:
|
||||
|
||||
Use the function 'get_boiling_point' to 'Get the boiling point of a imaginary liquids (eg. polyjuice)'
|
||||
{"name": "get_boiling_point", "description": "Get the boiling point of a imaginary liquids (eg. polyjuice)", "parameters": {"liquid_name": {"param_type": "string", "description": "The name of the liquid", "required": true}, "celcius": {"param_type": "boolean", "description": "Whether to return the boiling point in Celcius", "required": false}}}
|
||||
|
||||
|
||||
Think very carefully before calling functions.
|
||||
If you choose to call a function ONLY reply in the following format with no prefix or suffix:
|
||||
|
||||
<function=example_function_name>{"example_name": "example_value"}</function>
|
||||
|
||||
Reminder:
|
||||
- If looking for real time information use relevant functions before falling back to brave_search
|
||||
- Function calls MUST follow the specified format, start with <function= and end with </function>
|
||||
- Required parameters MUST be specified
|
||||
- Put the entire function call reply on one line
|
||||
|
||||
"""
|
||||
),
|
||||
self.custom_tool_defn = ToolDefinition(
|
||||
tool_name="get_boiling_point",
|
||||
description="Get the boiling point of a imaginary liquids (eg. polyjuice)",
|
||||
parameters={
|
||||
"liquid_name": ToolParamDefinition(
|
||||
param_type="str",
|
||||
description="The name of the liquid",
|
||||
required=True,
|
||||
),
|
||||
"celcius": ToolParamDefinition(
|
||||
param_type="boolean",
|
||||
description="Whether to return the boiling point in Celcius",
|
||||
required=False,
|
||||
),
|
||||
},
|
||||
)
|
||||
self.valid_supported_model = "Meta-Llama3.1-8B-Instruct"
|
||||
|
||||
|
|
@ -98,12 +71,12 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
request = ChatCompletionRequest(
|
||||
model=self.valid_supported_model,
|
||||
messages=[
|
||||
self.system_prompt,
|
||||
UserMessage(
|
||||
content="Who is the current US President?",
|
||||
),
|
||||
],
|
||||
stream=False,
|
||||
tools=[ToolDefinition(tool_name=BuiltinTool.brave_search)],
|
||||
)
|
||||
iterator = self.api.chat_completion(request)
|
||||
async for r in iterator:
|
||||
|
|
@ -112,7 +85,7 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
completion_message = response.completion_message
|
||||
|
||||
self.assertEqual(completion_message.content, "")
|
||||
self.assertEqual(completion_message.stop_reason, StopReason.end_of_message)
|
||||
self.assertEqual(completion_message.stop_reason, StopReason.end_of_turn)
|
||||
|
||||
self.assertEqual(
|
||||
len(completion_message.tool_calls), 1, completion_message.tool_calls
|
||||
|
|
@ -128,11 +101,11 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
request = ChatCompletionRequest(
|
||||
model=self.valid_supported_model,
|
||||
messages=[
|
||||
self.system_prompt,
|
||||
UserMessage(
|
||||
content="Write code to compute the 5th prime number",
|
||||
),
|
||||
],
|
||||
tools=[ToolDefinition(tool_name=BuiltinTool.code_interpreter)],
|
||||
stream=False,
|
||||
)
|
||||
iterator = self.api.chat_completion(request)
|
||||
|
|
@ -142,7 +115,7 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
completion_message = response.completion_message
|
||||
|
||||
self.assertEqual(completion_message.content, "")
|
||||
self.assertEqual(completion_message.stop_reason, StopReason.end_of_message)
|
||||
self.assertEqual(completion_message.stop_reason, StopReason.end_of_turn)
|
||||
|
||||
self.assertEqual(
|
||||
len(completion_message.tool_calls), 1, completion_message.tool_calls
|
||||
|
|
@ -157,12 +130,12 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
request = ChatCompletionRequest(
|
||||
model=self.valid_supported_model,
|
||||
messages=[
|
||||
self.system_prompt_with_custom_tool,
|
||||
UserMessage(
|
||||
content="Use provided function to find the boiling point of polyjuice?",
|
||||
),
|
||||
],
|
||||
stream=False,
|
||||
tools=[self.custom_tool_defn],
|
||||
)
|
||||
iterator = self.api.chat_completion(request)
|
||||
async for r in iterator:
|
||||
|
|
@ -229,12 +202,12 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
request = ChatCompletionRequest(
|
||||
model=self.valid_supported_model,
|
||||
messages=[
|
||||
self.system_prompt,
|
||||
UserMessage(
|
||||
content="Who is the current US President?",
|
||||
content="Using web search tell me who is the current US President?",
|
||||
),
|
||||
],
|
||||
stream=True,
|
||||
tools=[ToolDefinition(tool_name=BuiltinTool.brave_search)],
|
||||
)
|
||||
iterator = self.api.chat_completion(request)
|
||||
events = []
|
||||
|
|
@ -250,19 +223,19 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
self.assertEqual(
|
||||
events[-2].event_type, ChatCompletionResponseEventType.progress
|
||||
)
|
||||
self.assertEqual(events[-2].stop_reason, StopReason.end_of_message)
|
||||
self.assertEqual(events[-2].stop_reason, StopReason.end_of_turn)
|
||||
self.assertEqual(events[-2].delta.content.tool_name, BuiltinTool.brave_search)
|
||||
|
||||
async def test_custom_tool_call_streaming(self):
|
||||
request = ChatCompletionRequest(
|
||||
model=self.valid_supported_model,
|
||||
messages=[
|
||||
self.system_prompt_with_custom_tool,
|
||||
UserMessage(
|
||||
content="Use provided function to find the boiling point of polyjuice?",
|
||||
),
|
||||
],
|
||||
stream=True,
|
||||
tools=[self.custom_tool_defn],
|
||||
)
|
||||
iterator = self.api.chat_completion(request)
|
||||
events = []
|
||||
|
|
@ -321,7 +294,6 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
request = ChatCompletionRequest(
|
||||
model=self.valid_supported_model,
|
||||
messages=[
|
||||
self.system_prompt,
|
||||
UserMessage(
|
||||
content="Search the web and tell me who the "
|
||||
"44th president of the United States was",
|
||||
|
|
@ -333,6 +305,7 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
),
|
||||
],
|
||||
stream=True,
|
||||
tools=[ToolDefinition(tool_name=BuiltinTool.brave_search)],
|
||||
)
|
||||
iterator = self.api.chat_completion(request)
|
||||
|
||||
|
|
@ -350,12 +323,12 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
request = ChatCompletionRequest(
|
||||
model=self.valid_supported_model,
|
||||
messages=[
|
||||
self.system_prompt,
|
||||
UserMessage(
|
||||
content="Write code to answer this question: What is the 100th prime number?",
|
||||
),
|
||||
],
|
||||
stream=True,
|
||||
tools=[ToolDefinition(tool_name=BuiltinTool.code_interpreter)],
|
||||
)
|
||||
iterator = self.api.chat_completion(request)
|
||||
events = []
|
||||
|
|
@ -371,7 +344,7 @@ class OllamaInferenceTests(unittest.IsolatedAsyncioTestCase):
|
|||
self.assertEqual(
|
||||
events[-2].event_type, ChatCompletionResponseEventType.progress
|
||||
)
|
||||
self.assertEqual(events[-2].stop_reason, StopReason.end_of_message)
|
||||
self.assertEqual(events[-2].stop_reason, StopReason.end_of_turn)
|
||||
self.assertEqual(
|
||||
events[-2].delta.content.tool_name, BuiltinTool.code_interpreter
|
||||
)
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue