phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 09:21:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

memory tests fix

Browse source
This commit is contained in:
Xi Yan 2024-12-26 17:27:01 -08:00
parent 3f86c19150
commit 3b1f20ac00
3 changed files with 21 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/distribution/routers/routing_tables.py
View file

@ -13,7 +13,12 @@ from llama_stack.apis.common.content_types import URL
from llama_stack.apis.common.type_system import ParamType from llama_stack.apis.common.type_system import ParamType
from llama_stack.apis.datasets import Dataset, Datasets from llama_stack.apis.datasets import Dataset, Datasets
from llama_stack.apis.eval_tasks import EvalTask, EvalTasks from llama_stack.apis.eval_tasks import EvalTask, EvalTasks
from llama_stack.apis.memory_banks import BankParams, MemoryBank, MemoryBanks from llama_stack.apis.memory_banks import (
BankParams,
MemoryBank,
MemoryBanks,
MemoryBankType,
)
from llama_stack.apis.models import Model, Models, ModelType from llama_stack.apis.models import Model, Models, ModelType
from llama_stack.apis.resource import ResourceType from llama_stack.apis.resource import ResourceType
from llama_stack.apis.scoring_functions import ( from llama_stack.apis.scoring_functions import (

11
llama_stack/providers/inline/memory/faiss/faiss.py
View file

@ -16,11 +16,14 @@ import faiss
import numpy as np import numpy as np
from numpy.typing import NDArray from numpy.typing import NDArray
from llama_models.llama3.api.datatypes import * # noqa: F403
from llama_stack.apis.memory import * # noqa: F403
from llama_stack.apis.inference import InterleavedContent from llama_stack.apis.inference import InterleavedContent
from llama_stack.apis.memory_banks import MemoryBankType, VectorMemoryBank from llama_stack.apis.memory import (
Chunk,
Memory,
MemoryBankDocument,
QueryDocumentsResponse,
)
from llama_stack.apis.memory_banks import MemoryBank, MemoryBankType, VectorMemoryBank
from llama_stack.providers.datatypes import Api, MemoryBanksProtocolPrivate from llama_stack.providers.datatypes import Api, MemoryBanksProtocolPrivate
from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.kvstore import kvstore_impl
from llama_stack.providers.utils.memory.vector_store import ( from llama_stack.providers.utils.memory.vector_store import (

12
llama_stack/providers/tests/memory/test_memory.py
View file

@ -8,14 +8,18 @@ import uuid
import pytest import pytest
from llama_stack.apis.memory import * # noqa: F403 from llama_stack.apis.memory import MemoryBankDocument, QueryDocumentsResponse
from llama_stack.distribution.datatypes import * # noqa: F403
from llama_stack.apis.memory_banks.memory_banks import VectorMemoryBankParams from llama_stack.apis.memory_banks import (
MemoryBank,
MemoryBanks,
VectorMemoryBankParams,
)
# How to run this test: # How to run this test:
# #
# pytest llama_stack/providers/tests/memory/test_memory.py # pytest llama_stack/providers/tests/memory/test_memory.py
# -m "meta_reference" # -m "sentence_transformers" --env EMBEDDING_DIMENSION=384
# -v -s --tb=short --disable-warnings # -v -s --tb=short --disable-warnings