mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-18 15:09:48 +00:00
adding logo and favicon
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chore: Enable keyword search for Milvus inline (#3073) With https://github.com/milvus-io/milvus-lite/pull/294 - Milvus Lite supports keyword search using BM25. While introducing keyword search we had explicitly disabled it for inline milvus. This PR removes the need for the check, and enables `inline::milvus` for tests. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Run llama stack with `inline::milvus` enabled: ``` pytest tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes --stack-config=http://localhost:8321 --embedding-model=all-MiniLM-L6-v2 -v ``` ``` INFO 2025-08-07 17:06:20,932 tests.integration.conftest:64 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS =========================================================================================== test session starts ============================================================================================ platform darwin -- Python 3.12.11, pytest-7.4.4, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-14.7.6-arm64-arm-64bit', 'Packages': {'pytest': '7.4.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.23.8', 'cov': '6.0.0', 'timeout': '2.2.0', 'socket': '0.7.0', 'html': '3.1.1', 'langsmith': '0.3.39', 'anyio': '4.8.0', 'metadata': '3.0.0'}} rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack configfile: pyproject.toml plugins: asyncio-0.23.8, cov-6.0.0, timeout-2.2.0, socket-0.7.0, html-3.1.1, langsmith-0.3.39, anyio-4.8.0, metadata-3.0.0 asyncio: mode=Mode.AUTO collected 3 items tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-vector] PASSED [ 33%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-keyword] PASSED [ 66%] tests/integration/vector_io/test_openai_vector_stores.py::test_openai_vector_store_search_modes[None-None-all-MiniLM-L6-v2-None-384-hybrid] PASSED [100%] ============================================================================================ 3 passed in 4.75s ============================================================================================= ``` Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> chore: Fixup main pre commit (#3204) build: Bump version to 0.2.18 chore: Faster npm pre-commit (#3206) Adds npm to pre-commit.yml installation and caches ui Removes node installation during pre-commit. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> chiecking in for tonight, wip moving to agents api Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> remove log Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updated Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix: disable ui-prettier & ui-eslint (#3207) chore(pre-commit): add pre-commit hook to enforce llama_stack logger usage (#3061) This PR adds a step in pre-commit to enforce using `llama_stack` logger. Currently, various parts of the code base uses different loggers. As a custom `llama_stack` logger exist and used in the codebase, it is better to standardize its utilization. Signed-off-by: Mustafa Elbehery <melbeher@redhat.com> Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu> fix: fix ```openai_embeddings``` for asymmetric embedding NIMs (#3205) NVIDIA asymmetric embedding models (e.g., `nvidia/llama-3.2-nv-embedqa-1b-v2`) require an `input_type` parameter not present in the standard OpenAI embeddings API. This PR adds the `input_type="query"` as default and updates the documentation to suggest using the `embedding` API for passage embeddings. <!-- If resolving an issue, uncomment and update the line below --> Resolves #2892 ``` pytest -s -v tests/integration/inference/test_openai_embeddings.py --stack-config="inference=nvidia" --embedding-model="nvidia/llama-3.2-nv-embedqa-1b-v2" --env NVIDIA_API_KEY={nvidia_api_key} --env NVIDIA_BASE_URL="https://integrate.api.nvidia.com" ``` cleaning up Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> updating session manager to cache messages locally Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> fix linter Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> more cleanup Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo
parent
e7be568d7e
commit
6620b625f1
76 changed files with 2343 additions and 1187 deletions
|
|
@ -4,7 +4,6 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import logging
|
||||
import sys
|
||||
import time
|
||||
import uuid
|
||||
|
|
@ -19,10 +18,10 @@ from llama_stack.apis.post_training import (
|
|||
LoraFinetuningConfig,
|
||||
TrainingConfig,
|
||||
)
|
||||
from llama_stack.log import get_logger
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s", force=True)
|
||||
logger = logging.getLogger(__name__)
|
||||
logger = get_logger(name=__name__, category="post_training")
|
||||
|
||||
|
||||
skip_because_resource_intensive = pytest.mark.skip(
|
||||
|
|
|
|||
|
|
@ -4,7 +4,6 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import logging
|
||||
import time
|
||||
from io import BytesIO
|
||||
|
||||
|
|
@ -14,8 +13,9 @@ from openai import BadRequestError as OpenAIBadRequestError
|
|||
|
||||
from llama_stack.apis.vector_io import Chunk
|
||||
from llama_stack.core.library_client import LlamaStackAsLibraryClient
|
||||
from llama_stack.log import get_logger
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
logger = get_logger(name=__name__, category="vector_io")
|
||||
|
||||
|
||||
def skip_if_provider_doesnt_support_openai_vector_stores(client_with_models):
|
||||
|
|
@ -56,6 +56,7 @@ def skip_if_provider_doesnt_support_openai_vector_stores_search(client_with_mode
|
|||
"keyword": [
|
||||
"inline::sqlite-vec",
|
||||
"remote::milvus",
|
||||
"inline::milvus",
|
||||
],
|
||||
"hybrid": [
|
||||
"inline::sqlite-vec",
|
||||
|
|
|
|||
|
|
@ -45,7 +45,6 @@ from llama_stack.providers.inline.agents.meta_reference.responses.utils import (
|
|||
|
||||
|
||||
class TestConvertChatChoiceToResponseMessage:
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_string_content(self):
|
||||
choice = OpenAIChoice(
|
||||
message=OpenAIAssistantMessageParam(content="Test message"),
|
||||
|
|
@ -61,7 +60,6 @@ class TestConvertChatChoiceToResponseMessage:
|
|||
assert isinstance(result.content[0], OpenAIResponseOutputMessageContentOutputText)
|
||||
assert result.content[0].text == "Test message"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_text_param_content(self):
|
||||
choice = OpenAIChoice(
|
||||
message=OpenAIAssistantMessageParam(
|
||||
|
|
@ -78,12 +76,10 @@ class TestConvertChatChoiceToResponseMessage:
|
|||
|
||||
|
||||
class TestConvertResponseContentToChatContent:
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_string_content(self):
|
||||
result = await convert_response_content_to_chat_content("Simple string")
|
||||
assert result == "Simple string"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_text_content_parts(self):
|
||||
content = [
|
||||
OpenAIResponseInputMessageContentText(text="First part"),
|
||||
|
|
@ -98,7 +94,6 @@ class TestConvertResponseContentToChatContent:
|
|||
assert isinstance(result[1], OpenAIChatCompletionContentPartTextParam)
|
||||
assert result[1].text == "Second part"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_image_content(self):
|
||||
content = [OpenAIResponseInputMessageContentImage(image_url="https://example.com/image.jpg", detail="high")]
|
||||
|
||||
|
|
@ -111,7 +106,6 @@ class TestConvertResponseContentToChatContent:
|
|||
|
||||
|
||||
class TestConvertResponseInputToChatMessages:
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_string_input(self):
|
||||
result = await convert_response_input_to_chat_messages("User message")
|
||||
|
||||
|
|
@ -119,7 +113,6 @@ class TestConvertResponseInputToChatMessages:
|
|||
assert isinstance(result[0], OpenAIUserMessageParam)
|
||||
assert result[0].content == "User message"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_function_tool_call_output(self):
|
||||
input_items = [
|
||||
OpenAIResponseInputFunctionToolCallOutput(
|
||||
|
|
@ -135,7 +128,6 @@ class TestConvertResponseInputToChatMessages:
|
|||
assert result[0].content == "Tool output"
|
||||
assert result[0].tool_call_id == "call_123"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_function_tool_call(self):
|
||||
input_items = [
|
||||
OpenAIResponseOutputMessageFunctionToolCall(
|
||||
|
|
@ -154,7 +146,6 @@ class TestConvertResponseInputToChatMessages:
|
|||
assert result[0].tool_calls[0].function.name == "test_function"
|
||||
assert result[0].tool_calls[0].function.arguments == '{"param": "value"}'
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_response_message(self):
|
||||
input_items = [
|
||||
OpenAIResponseMessage(
|
||||
|
|
@ -173,7 +164,6 @@ class TestConvertResponseInputToChatMessages:
|
|||
|
||||
|
||||
class TestConvertResponseTextToChatResponseFormat:
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_text_format(self):
|
||||
text = OpenAIResponseText(format=OpenAIResponseTextFormat(type="text"))
|
||||
result = await convert_response_text_to_chat_response_format(text)
|
||||
|
|
@ -181,14 +171,12 @@ class TestConvertResponseTextToChatResponseFormat:
|
|||
assert isinstance(result, OpenAIResponseFormatText)
|
||||
assert result.type == "text"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_json_object_format(self):
|
||||
text = OpenAIResponseText(format={"type": "json_object"})
|
||||
result = await convert_response_text_to_chat_response_format(text)
|
||||
|
||||
assert isinstance(result, OpenAIResponseFormatJSONObject)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_convert_json_schema_format(self):
|
||||
schema_def = {"type": "object", "properties": {"test": {"type": "string"}}}
|
||||
text = OpenAIResponseText(
|
||||
|
|
@ -204,7 +192,6 @@ class TestConvertResponseTextToChatResponseFormat:
|
|||
assert result.json_schema["name"] == "test_schema"
|
||||
assert result.json_schema["schema"] == schema_def
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_default_text_format(self):
|
||||
text = OpenAIResponseText()
|
||||
result = await convert_response_text_to_chat_response_format(text)
|
||||
|
|
@ -214,27 +201,22 @@ class TestConvertResponseTextToChatResponseFormat:
|
|||
|
||||
|
||||
class TestGetMessageTypeByRole:
|
||||
@pytest.mark.asyncio
|
||||
async def test_user_role(self):
|
||||
result = await get_message_type_by_role("user")
|
||||
assert result == OpenAIUserMessageParam
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_system_role(self):
|
||||
result = await get_message_type_by_role("system")
|
||||
assert result == OpenAISystemMessageParam
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_assistant_role(self):
|
||||
result = await get_message_type_by_role("assistant")
|
||||
assert result == OpenAIAssistantMessageParam
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_developer_role(self):
|
||||
result = await get_message_type_by_role("developer")
|
||||
assert result == OpenAIDeveloperMessageParam
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_unknown_role(self):
|
||||
result = await get_message_type_by_role("unknown")
|
||||
assert result is None
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import logging # allow-direct-logging
|
||||
import threading
|
||||
import time
|
||||
from http.server import BaseHTTPRequestHandler, HTTPServer
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue