forked from phoenix-oss/llama-stack-mirror
f4f47970e5
# What does this PR do? Default inference_model for testing: "meta-llama/Llama-3.1-8B-Instruct" Default vision inference_model for testing: "meta-llama/Llama-3.2-11B-Vision-Instruct" ## Test Plan `/opt/miniconda3/envs/stack/bin/pytest -s -v --inference-model=meta-llama/Llama-3.2-3B-Instruct tests/client-sdk/agents` `/opt/miniconda3/envs/stack/bin/pytest -s -v --embedding-model=all-MiniLM-L6-v2 tests/client-sdk/vector_io` `/opt/miniconda3/envs/stack/bin/pytest -s -v --safety-shield=meta-llama/Llama-Guard-3-1B tests/client-sdk/safety` ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
63 lines
2.1 KiB
Python
63 lines
2.1 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 random
|
|
|
|
|
|
def test_vector_db_retrieve(llama_stack_client, embedding_model):
|
|
# Register a memory bank first
|
|
vector_db_id = f"test_vector_db_{random.randint(1000, 9999)}"
|
|
llama_stack_client.vector_dbs.register(
|
|
vector_db_id=vector_db_id,
|
|
embedding_model=embedding_model,
|
|
embedding_dimension=384,
|
|
provider_id="faiss",
|
|
)
|
|
|
|
# Retrieve the memory bank and validate its properties
|
|
response = llama_stack_client.vector_dbs.retrieve(vector_db_id=vector_db_id)
|
|
assert response is not None
|
|
assert response.identifier == vector_db_id
|
|
assert response.embedding_model == embedding_model
|
|
assert response.provider_id == "faiss"
|
|
assert response.provider_resource_id == vector_db_id
|
|
|
|
|
|
def test_vector_db_list(llama_stack_client):
|
|
vector_dbs_after_register = [
|
|
vector_db.identifier for vector_db in llama_stack_client.vector_dbs.list()
|
|
]
|
|
assert len(vector_dbs_after_register) == 0
|
|
|
|
|
|
def test_vector_db_register(llama_stack_client, embedding_model):
|
|
vector_db_id = f"test_vector_db_{random.randint(1000, 9999)}"
|
|
llama_stack_client.vector_dbs.register(
|
|
vector_db_id=vector_db_id,
|
|
embedding_model=embedding_model,
|
|
embedding_dimension=384,
|
|
provider_id="faiss",
|
|
)
|
|
|
|
vector_dbs_after_register = [
|
|
vector_db.identifier for vector_db in llama_stack_client.vector_dbs.list()
|
|
]
|
|
assert vector_dbs_after_register == [vector_db_id]
|
|
|
|
|
|
def test_vector_db_unregister(llama_stack_client):
|
|
vector_dbs = [
|
|
vector_db.identifier for vector_db in llama_stack_client.vector_dbs.list()
|
|
]
|
|
assert len(vector_dbs) == 1
|
|
|
|
vector_db_id = vector_dbs[0]
|
|
llama_stack_client.vector_dbs.unregister(vector_db_id=vector_db_id)
|
|
|
|
vector_dbs = [
|
|
vector_db.identifier for vector_db in llama_stack_client.vector_dbs.list()
|
|
]
|
|
assert len(vector_dbs) == 0
|