phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 20:41:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: Enabling Milvus for VectorIO CI

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-06-27 21:25:57 -04:00
parent 709eb7da33
commit c8d41d45ec
115 changed files with 2919 additions and 184 deletions
Download patch file Download diff file Expand all files Collapse all files

9
tests/integration/agents/test_openai_responses.py
View file

@ -4,7 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import pytest
from openai import OpenAI
from openai import BadRequestError, OpenAI
from llama_stack.distribution.library_client import LlamaStackAsLibraryClient
@ -92,6 +92,13 @@ def test_responses_store(openai_client, client_with_models, text_model_id, strea
if output_type == "message":
assert retrieved_response.output[0].content[0].text == content
# Delete the response
delete_response = client.responses.delete(response_id)
assert delete_response is None
with pytest.raises(BadRequestError):
client.responses.retrieve(response_id)
def test_list_response_input_items(openai_client, client_with_models, text_model_id):
"""Test the new list_openai_response_input_items endpoint."""

19
tests/integration/vector_io/test_vector_io.py
View file

@ -123,6 +123,9 @@ def test_insert_chunks(client_with_empty_registry, embedding_model_id, embedding
def test_insert_chunks_with_precomputed_embeddings(client_with_empty_registry, embedding_model_id, embedding_dimension):
vector_io_provider_params_dict = {
"inline::milvus": {"score_threshold": -1.0},
}
vector_db_id = "test_precomputed_embeddings_db"
client_with_empty_registry.vector_dbs.register(
vector_db_id=vector_db_id,
@ -133,7 +136,7 @@ def test_insert_chunks_with_precomputed_embeddings(client_with_empty_registry, e
chunks_with_embeddings = [
Chunk(
content="This is a test chunk with precomputed embedding.",
metadata={"document_id": "doc1", "source": "precomputed"},
metadata={"document_id": "doc1", "source": "precomputed", "chunk_id": "chunk1"},
embedding=[0.1] * int(embedding_dimension),
),
]
@ -143,22 +146,30 @@ def test_insert_chunks_with_precomputed_embeddings(client_with_empty_registry, e
chunks=chunks_with_embeddings,
)
# Query for the first document
provider = [p.provider_id for p in client_with_empty_registry.providers.list() if p.api == "vector_io"][0]
response = client_with_empty_registry.vector_io.query(
vector_db_id=vector_db_id,
query="precomputed embedding test",
params=vector_io_provider_params_dict.get(provider, None),
)
# Verify the top result is the expected document
assert response is not None
assert len(response.chunks) > 0
assert len(response.chunks) > 0, (
f"provider params for {provider} = {vector_io_provider_params_dict.get(provider, None)}"
)
assert response.chunks[0].metadata["document_id"] == "doc1"
assert response.chunks[0].metadata["source"] == "precomputed"
# expect this test to fail
@pytest.mark.xfail(reason="This test is expected to fail.")
def test_query_returns_valid_object_when_identical_to_embedding_in_vdb(
client_with_empty_registry, embedding_model_id, embedding_dimension
):
vector_io_provider_params_dict = {
"inline::milvus": {"score_threshold": 3.0},
}
vector_db_id = "test_precomputed_embeddings_db"
client_with_empty_registry.vector_dbs.register(
vector_db_id=vector_db_id,
@ -179,9 +190,11 @@ def test_query_returns_valid_object_when_identical_to_embedding_in_vdb(
chunks=chunks_with_embeddings,
)
provider = [p.provider_id for p in client_with_empty_registry.providers.list() if p.api == "vector_io"][0]
response = client_with_empty_registry.vector_io.query(
vector_db_id=vector_db_id,
query="duplicate",
params=vector_io_provider_params_dict.get(provider, None),
)
# Verify the top result is the expected document