mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
cca9bd6cc3
# What does this PR do? Removed local execution option from the remote Qdrant provider and introduced an explicit inline provider for the embedded execution. Updated the ollama template to include this option: this part can be reverted in case we don't want to have two default `vector_io` providers. (Closes #1082) ## Test Plan Build and run an ollama distro: ```bash llama stack build --template ollama --image-type conda llama stack run --image-type conda ollama ``` Run one of the sample ingestionapplicatinos like [rag_with_vector_db.py](https://github.com/meta-llama/llama-stack-apps/blob/main/examples/agents/rag_with_vector_db.py), but replace this line: ```py selected_vector_provider = vector_providers[0] ``` with the following, to use the `qdrant` provider: ```py selected_vector_provider = vector_providers[1] ``` After running the test code, verify the timestamp of the Qdrant store: ```bash % ls -ltr ~/.llama/distributions/ollama/qdrant.db/collection/test_vector_db_* total 784 -rw-r--r--@ 1 dmartino staff 401408 Feb 26 10:07 storage.sqlite ``` [//]: # (## Documentation) --------- Signed-off-by: Daniele Martinoli <dmartino@redhat.com> Co-authored-by: Francisco Arceo <farceo@redhat.com>
42 lines
1.1 KiB
Python
42 lines
1.1 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
|
|
|
|
import numpy as np
|
|
import pytest
|
|
|
|
from llama_stack.apis.vector_io import Chunk
|
|
|
|
EMBEDDING_DIMENSION = 384
|
|
|
|
|
|
@pytest.fixture
|
|
def vector_db_id() -> str:
|
|
return f"test-vector-db-{random.randint(1, 100)}"
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def embedding_dimension() -> int:
|
|
return EMBEDDING_DIMENSION
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def sample_chunks():
|
|
"""Generates chunks that force multiple batches for a single document to expose ID conflicts."""
|
|
n, k = 10, 3
|
|
sample = [
|
|
Chunk(content=f"Sentence {i} from document {j}", metadata={"document_id": f"document-{j}"})
|
|
for j in range(k)
|
|
for i in range(n)
|
|
]
|
|
return sample
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def sample_embeddings(sample_chunks):
|
|
np.random.seed(42)
|
|
return np.array([np.random.rand(EMBEDDING_DIMENSION).astype(np.float32) for _ in sample_chunks])
|