forked from phoenix-oss/llama-stack-mirror
* add tools to chat completion request * use templates for generating system prompts * Moved ToolPromptFormat and jinja templates to llama_models.llama3.api * <WIP> memory changes - inlined AgenticSystemInstanceConfig so API feels more ergonomic - renamed it to AgentConfig, AgentInstance -> Agent - added a MemoryConfig and `memory` parameter - added `attachments` to input and `output_attachments` to the response - some naming changes * InterleavedTextAttachment -> InterleavedTextMedia, introduce memory tool * flesh out memory banks API * agentic loop has a RAG implementation * faiss provider implementation * memory client works * re-work tool definitions, fix FastAPI issues, fix tool regressions * fix agentic_system utils * basic RAG seems to work * small bug fixes for inline attachments * Refactor custom tool execution utilities * Bug fix, show memory retrieval steps in EventLogger * No need for api_key for Remote providers * add special unicode character ↵ to showcase newlines in model prompt templates * remove api.endpoints imports * combine datatypes.py and endpoints.py into api.py * Attachment / add TTL api * split batch_inference from inference * minor import fixes * use a single impl for ChatFormat.decode_assistant_mesage * use interleaved_text_media_as_str() utilityt * Fix api.datatypes imports * Add blobfile for tiktoken * Add ToolPromptFormat to ChatFormat.encode_message so that tools are encoded properly * templates take optional --format={json,function_tag} * Rag Updates * Add `api build` subcommand -- WIP * fix * build + run image seems to work * <WIP> adapters * bunch more work to make adapters work * api build works for conda now * ollama remote adapter works * Several smaller fixes to make adapters work Also, reorganized the pattern of __init__ inside providers so configuration can stay lightweight * llama distribution -> llama stack + containers (WIP) * All the new CLI for api + stack work * Make Fireworks and Together into the Adapter format * Some quick fixes to the CLI behavior to make it consistent * Updated README phew * Update cli_reference.md * llama_toolchain/distribution -> llama_toolchain/core * Add termcolor * update paths * Add a log just for consistency * chmod +x scripts * Fix api dependencies not getting added to configuration * missing import lol * Delete utils.py; move to agentic system * Support downloading of URLs for attachments for code interpreter * Simplify and generalize `llama api build` yay * Update `llama stack configure` to be very simple also * Fix stack start * Allow building an "adhoc" distribution * Remote `llama api []` subcommands * Fixes to llama stack commands and update docs * Update documentation again and add error messages to llama stack start * llama stack start -> llama stack run * Change name of build for less confusion * Add pyopenapi fork to the repository, update RFC assets * Remove conflicting annotation * Added a "--raw" option for model template printing --------- Co-authored-by: Hardik Shah <hjshah@fb.com> Co-authored-by: Ashwin Bharambe <ashwin@meta.com> Co-authored-by: Dalton Flanagan <6599399+dltn@users.noreply.github.com>
120 lines
4.3 KiB
Python
120 lines
4.3 KiB
Python
import unittest
|
|
|
|
from llama_models.llama3.api import * # noqa: F403
|
|
from llama_toolchain.inference.api import * # noqa: F403
|
|
from llama_toolchain.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)
|