embestore 0.2.0

No project description provided

Introduction

Implement the sentence embedding retriever with local cache from the embedding store.

Features

• Embedding store abstraction class

• Support Jina client implementation embedding store

• Support LFU, LRU cache eviction policy for limited cache size, if the eviction policy is not specified then won't apply any eviction policy

• Save the cache to parquet file

• Load the cache from existed parquet file

Quick Start

Option 1. Using Jina flow serve the embedding model

• Installation

pip install embestore"[jina]"

• To start up the Jina flow service with sentence embedding model sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2, you can just clone this github repo directly and serve by the docker container.

git clone https://github.com/ycc789741ycc/sentence-embedding-dataframe-cache.git

cd sentence-embedding-dataframe-cache

make serve-jina-embedding

• Retrieve the embedding

from embestore.store.jina import JinaEmbeddingStore

JINA_EMBESTORE_GRPC = "grpc://0.0.0.0:54321"


query_sentences = ["I want to listen the music.", "Music don't want to listen me."]

jina_embestore = JinaEmbeddingStore(embedding_grpc=JINA_EMBESTORE_GRPC)
results = jina_embestore.retrieve_embeddings(sentences=query_sentences)

• Stop the docker container

make stop-jina-embedding

Option 2. Using local sentence embedding model

• Installation

pip install embestore"[sentence-transformers]"

• Serve the sentence embedding model sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 by in-memory

from embestore.store.torch import TorchEmbeddingStore

query_sentences = ["I want to listen the music.", "Music don't want to listen me."]


torch_embestore = TorchEmbeddingStore()
results = torch_embestore.retrieve_embeddings(sentences=query_sentences)

Option 3. Inherit from the abstraction class

• Installation

pip install embestore

from typing import List, Text

import numpy as np
from sentence_transformers import SentenceTransformer

from embestore.store.base import EmbeddingStore

model = SentenceTransformer("sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2").eval()


class TorchEmbeddingStore(EmbeddingStore):
    def _retrieve_embeddings_from_model(self, sentences: List[Text]) -> np.ndarray:
        return model.encode(sentences)

Save the cache

torch_embestore.save("cache.parquet")

Load from the cache

torch_embestore = TorchEmbeddingStore("cache.parquet")

Apply eviction policy

• LRU

torch_embestore = TorchEmbeddingStore(max_size=100, eviction_policy="lru")

• LFU

torch_embestore = TorchEmbeddingStore(max_size=100, eviction_policy="lfu")

Road Map

[TODO] Documentation

[TODO] Badges