phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 15:49:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Vector store inference api (#598)

Browse source 
# What does this PR do?
Moves all the memory providers to use the inference API and improved the
memory tests to setup the inference stack correctly and use the
embedding models


## Test Plan
torchrun $CONDA_PREFIX/bin/pytest -v -s -k "meta_reference"
--inference-model="Llama3.2-3B-Instruct"
--embedding-model="sentence-transformers/all-MiniLM-L6-v2"
llama_stack/providers/tests/inference/test_embeddings.py --env
EMBEDDING_DIMENSION=384


pytest -v -s llama_stack/providers/tests/memory/test_memory.py
--providers="inference=together,memory=weaviate"
--embedding-model="togethercomputer/m2-bert-80M-2k-retrieval" --env
EMBEDDING_DIMENSION=768 --env TOGETHER_API_KEY=<API-KEY> --env
WEAVIATE_API_KEY=foo --env WEAVIATE_CLUSTER_URL=bar
 
pytest -v -s llama_stack/providers/tests/memory/test_memory.py
--providers="inference=together,memory=chroma"
--embedding-model="togethercomputer/m2-bert-80M-2k-retrieval" --env
EMBEDDING_DIMENSION=768 --env TOGETHER_API_KEY=<API-KEY>--env
CHROMA_HOST=localhost --env CHROMA_PORT=8000

pytest -v -s llama_stack/providers/tests/memory/test_memory.py
--providers="inference=together,memory=pgvector"
--embedding-model="togethercomputer/m2-bert-80M-2k-retrieval" --env
PGVECTOR_DB=postgres --env PGVECTOR_USER=postgres --env
PGVECTOR_PASSWORD=mysecretpassword --env PGVECTOR_HOST=0.0.0.0 --env
EMBEDDING_DIMENSION=768 --env TOGETHER_API_KEY=<API-KEY>

pytest -v -s llama_stack/providers/tests/memory/test_memory.py
--providers="inference=together,memory=faiss"
--embedding-model="togethercomputer/m2-bert-80M-2k-retrieval" --env
EMBEDDING_DIMENSION=768 --env TOGETHER_API_KEY=<API-KEY>
This commit is contained in:
Dinesh Yeduguru 2024-12-12 11:16:54 -08:00 • committed by GitHub
parent db7b26a8c9
commit 4f8b73b9e1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 235 additions and 118 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/remote/memory/qdrant/__init__.py
View file

@ -4,12 +4,16 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Dict
from llama_stack.providers.datatypes import Api, ProviderSpec
from .config import QdrantConfig
async def get_adapter_impl(config: QdrantConfig, _deps):
async def get_adapter_impl(config: QdrantConfig, deps: Dict[Api, ProviderSpec]):
from .qdrant import QdrantVectorMemoryAdapter
impl = QdrantVectorMemoryAdapter(config)
impl = QdrantVectorMemoryAdapter(config, deps[Api.inference])
await impl.initialize()
return impl

5
llama_stack/providers/remote/memory/qdrant/qdrant.py
View file

@ -101,10 +101,11 @@ class QdrantIndex(EmbeddingIndex):
class QdrantVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
def __init__(self, config: QdrantConfig) -> None:
def __init__(self, config: QdrantConfig, inference_api: Api.inference) -> None:
self.config = config
self.client = AsyncQdrantClient(**self.config.model_dump(exclude_none=True))
self.cache = {}
self.inference_api = inference_api
async def initialize(self) -> None:
pass
@ -123,6 +124,7 @@ class QdrantVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
index = BankWithIndex(
bank=memory_bank,
index=QdrantIndex(self.client, memory_bank.identifier),
inference_api=self.inference_api,
)
self.cache[memory_bank.identifier] = index
@ -143,6 +145,7 @@ class QdrantVectorMemoryAdapter(Memory, MemoryBanksProtocolPrivate):
index = BankWithIndex(
bank=bank,
index=QdrantIndex(client=self.client, collection_name=bank_id),
inference_api=self.inference_api,
)
self.cache[bank_id] = index
return index