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

API Updates: fleshing out RAG APIs, introduce "llama stack" CLI command (#51)

Browse source 
* 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>
This commit is contained in:
Ashwin Bharambe 2024-09-03 22:39:39 -07:00 • committed by GitHub
parent 35093c0b6f
commit 7bc7785b0d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
141 changed files with 8252 additions and 4032 deletions
Download patch file Download diff file Expand all files Collapse all files

86
tests/test_inference.py
View file

@ -8,16 +8,21 @@ import unittest
from datetime import datetime
from llama_models.llama3_1.api.datatypes import (
from llama_models.llama3.api.datatypes import (
BuiltinTool,
StopReason,
SystemMessage,
ToolDefinition,
ToolParamDefinition,
ToolPromptFormat,
ToolResponseMessage,
UserMessage,
)
from llama_toolchain.inference.api.datatypes import ChatCompletionResponseEventType
from llama_toolchain.inference.api.endpoints import ChatCompletionRequest
from llama_toolchain.inference.api import (
ChatCompletionRequest,
ChatCompletionResponseEventType,
)
from llama_toolchain.inference.meta_reference.config import MetaReferenceImplConfig
from llama_toolchain.inference.meta_reference.inference import get_provider_impl
@ -54,52 +59,6 @@ class InferenceTests(unittest.IsolatedAsyncioTestCase):
cls.api = await get_provider_impl(config, {})
await cls.api.initialize()
current_date = datetime.now()
formatted_date = current_date.strftime("%d %B %Y")
cls.system_prompt = SystemMessage(
content=textwrap.dedent(
f"""
Environment: ipython
Tools: brave_search
Cutting Knowledge Date: December 2023
Today Date:{formatted_date}
"""
),
)
cls.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
- Only call one function at a time
- Put the entire function call reply on one line
"""
),
)
@classmethod
def tearDownClass(cls):
# This runs the async teardown function
@ -111,6 +70,22 @@ class InferenceTests(unittest.IsolatedAsyncioTestCase):
async def asyncSetUp(self):
self.valid_supported_model = MODEL
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,
),
},
)
async def test_text(self):
request = ChatCompletionRequest(
@ -162,12 +137,12 @@ class InferenceTests(unittest.IsolatedAsyncioTestCase):
request = ChatCompletionRequest(
model=self.valid_supported_model,
messages=[
InferenceTests.system_prompt_with_custom_tool,
UserMessage(
content="Use provided function to find the boiling point of polyjuice in fahrenheit?",
),
],
stream=False,
tools=[self.custom_tool_defn],
)
iterator = InferenceTests.api.chat_completion(request)
async for r in iterator:
@ -197,11 +172,11 @@ class InferenceTests(unittest.IsolatedAsyncioTestCase):
request = ChatCompletionRequest(
model=self.valid_supported_model,
messages=[
self.system_prompt,
UserMessage(
content="Who is the current US President?",
),
],
tools=[ToolDefinition(tool_name=BuiltinTool.brave_search)],
stream=True,
)
iterator = InferenceTests.api.chat_completion(request)
@ -227,17 +202,20 @@ class InferenceTests(unittest.IsolatedAsyncioTestCase):
request = ChatCompletionRequest(
model=self.valid_supported_model,
messages=[
InferenceTests.system_prompt_with_custom_tool,
UserMessage(
content="Use provided function to find the boiling point of polyjuice?",
),
],
stream=True,
tools=[self.custom_tool_defn],
tool_prompt_format=ToolPromptFormat.function_tag,
)
iterator = InferenceTests.api.chat_completion(request)
events = []
async for chunk in iterator:
# print(f"{chunk.event.event_type:<40} | {str(chunk.event.stop_reason):<26} | {chunk.event.delta} ")
# print(
# f"{chunk.event.event_type:<40} | {str(chunk.event.stop_reason):<26} | {chunk.event.delta} "
# )
events.append(chunk.event)
self.assertEqual(events[0].event_type, ChatCompletionResponseEventType.start)
@ -257,7 +235,6 @@ class InferenceTests(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",
@ -270,6 +247,7 @@ class InferenceTests(unittest.IsolatedAsyncioTestCase):
),
],
stream=True,
tools=[ToolDefinition(tool_name=BuiltinTool.brave_search)],
)
iterator = self.api.chat_completion(request)