llama-stack-mirror/tests/test_prepare_messages.py
Ashwin Bharambe 9487ad8294
API Updates (#73)
* API Keys passed from Client instead of distro configuration

* delete distribution registry

* Rename the "package" word away

* Introduce a "Router" layer for providers

Some providers need to be factorized and considered as thin routing
layers on top of other providers. Consider two examples:

- The inference API should be a routing layer over inference providers,
  routed using the "model" key
- The memory banks API is another instance where various memory bank
  types will be provided by independent providers (e.g., a vector store
  is served by Chroma while a keyvalue memory can be served by Redis or
  PGVector)

This commit introduces a generalized routing layer for this purpose.

* update `apis_to_serve`

* llama_toolchain -> llama_stack

* Codemod from llama_toolchain -> llama_stack

- added providers/registry
- cleaned up api/ subdirectories and moved impls away
- restructured api/api.py
- from llama_stack.apis.<api> import foo should work now
- update imports to do llama_stack.apis.<api>
- update many other imports
- added __init__, fixed some registry imports
- updated registry imports
- create_agentic_system -> create_agent
- AgenticSystem -> Agent

* Moved some stuff out of common/; re-generated OpenAPI spec

* llama-toolchain -> llama-stack (hyphens)

* add control plane API

* add redis adapter + sqlite provider

* move core -> distribution

* Some more toolchain -> stack changes

* small naming shenanigans

* Removing custom tool and agent utilities and moving them client side

* Move control plane to distribution server for now

* Remove control plane from API list

* no codeshield dependency randomly plzzzzz

* Add "fire" as a dependency

* add back event loggers

* stack configure fixes

* use brave instead of bing in the example client

* add init file so it gets packaged

* add init files so it gets packaged

* Update MANIFEST

* bug fix

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Xi Yan <xiyan@meta.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
2024-09-17 19:51:35 -07:00

126 lines
4.5 KiB
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import unittest
from llama_models.llama3.api import * # noqa: F403
from llama_stack.inference.api import * # noqa: F403
from llama_stack.inference.prepare_messages import prepare_messages
MODEL = "Meta-Llama3.1-8B-Instruct"
class PrepareMessagesTests(unittest.IsolatedAsyncioTestCase):
async def test_system_default(self):
content = "Hello !"
request = ChatCompletionRequest(
model=MODEL,
messages=[
UserMessage(content=content),
],
)
messages = prepare_messages(request)
self.assertEqual(len(messages), 2)
self.assertEqual(messages[-1].content, content)
self.assertTrue("Cutting Knowledge Date: December 2023" in messages[0].content)
async def test_system_builtin_only(self):
content = "Hello !"
request = ChatCompletionRequest(
model=MODEL,
messages=[
UserMessage(content=content),
],
tools=[
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
ToolDefinition(tool_name=BuiltinTool.brave_search),
],
)
messages = prepare_messages(request)
self.assertEqual(len(messages), 2)
self.assertEqual(messages[-1].content, content)
self.assertTrue("Cutting Knowledge Date: December 2023" in messages[0].content)
self.assertTrue("Tools: brave_search" in messages[0].content)
async def test_system_custom_only(self):
content = "Hello !"
request = ChatCompletionRequest(
model=MODEL,
messages=[
UserMessage(content=content),
],
tools=[
ToolDefinition(
tool_name="custom1",
description="custom1 tool",
parameters={
"param1": ToolParamDefinition(
param_type="str",
description="param1 description",
required=True,
),
},
)
],
tool_prompt_format=ToolPromptFormat.json,
)
messages = prepare_messages(request)
self.assertEqual(len(messages), 3)
self.assertTrue("Environment: ipython" in messages[0].content)
self.assertTrue("Return function calls in JSON format" in messages[1].content)
self.assertEqual(messages[-1].content, content)
async def test_system_custom_and_builtin(self):
content = "Hello !"
request = ChatCompletionRequest(
model=MODEL,
messages=[
UserMessage(content=content),
],
tools=[
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
ToolDefinition(tool_name=BuiltinTool.brave_search),
ToolDefinition(
tool_name="custom1",
description="custom1 tool",
parameters={
"param1": ToolParamDefinition(
param_type="str",
description="param1 description",
required=True,
),
},
),
],
)
messages = prepare_messages(request)
self.assertEqual(len(messages), 3)
self.assertTrue("Environment: ipython" in messages[0].content)
self.assertTrue("Tools: brave_search" in messages[0].content)
self.assertTrue("Return function calls in JSON format" in messages[1].content)
self.assertEqual(messages[-1].content, content)
async def test_user_provided_system_message(self):
content = "Hello !"
system_prompt = "You are a pirate"
request = ChatCompletionRequest(
model=MODEL,
messages=[
SystemMessage(content=system_prompt),
UserMessage(content=content),
],
tools=[
ToolDefinition(tool_name=BuiltinTool.code_interpreter),
],
)
messages = prepare_messages(request)
self.assertEqual(len(messages), 2, messages)
self.assertTrue(messages[0].content.endswith(system_prompt))
self.assertEqual(messages[-1].content, content)