sentence-transformers How to use suhwan3/e5-step1 with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("suhwan3/e5-step1")
sentences = [
"The Merlyn.AI SectorSurfer Momentum ETF is designed to dynamically shift its investment strategy based on market conditions, tracking an index that utilizes an algorithmic Bull/Bear indicator assessing U.S. equity markets for advancing trends or elevated decline risk using factors like price-trend, momentum, value sentiment, and volatility. In Bull markets, it targets approximately a 70/30 domestic/foreign aggressive equity allocation by selecting six thematic ETFs (four sectors, two geopolitical), while in Bear markets, it seeks safety by choosing at least four momentum-leading bond, treasury, and gold safe-harbor ETFs, explicitly avoiding inverse and leveraged funds. The index is typically evaluated monthly, though the indicator can trigger strategy changes anytime during excessive market volatility. Under normal circumstances, at least 80% of the fund's assets are invested in the index's component securities; the fund is non-diversified. Please be aware this fund is closing, with its last day of trading scheduled for November 10, 2023.",
"The BlackRock Future Climate and Sustainable Economy ETF (BECO) is an actively managed equity fund focused on the transition to a lower carbon economy and future climate themes. It seeks a relatively concentrated, non-diversified portfolio of globally-listed companies of any market capitalization, investing across multiple subthemes such as sustainable energy, resource efficiency, future transport, sustainable nutrition, and biodiversity. The fund utilizes proprietary environmental criteria, including carbon metrics, and aims to align with the Paris Climate Agreement goals for net-zero emissions by 2050, while excluding certain high-emission industries and companies violating the UN Global Compact. It also attempts to achieve a better aggregate environmental and ESG score than its benchmark, the MSCI ACWI Multiple Industries Select Index. Note that BECO is being delisted, with its last day of trading on an exchange scheduled for August 12, 2024.",
"The Direxion Daily Semiconductor Bull 3X Shares (SOXL) seeks daily investment results, before fees and expenses, of 300% of the daily performance of the ICE Semiconductor Index. To achieve this bullish, leveraged exposure, the fund invests at least 80% of its net assets in financial instruments, such as swap agreements, securities of the index, and ETFs that track the index. The underlying ICE Semiconductor Index is a rules-based, modified float-adjusted market capitalization-weighted index that tracks the performance of the thirty largest U.S. listed semiconductor companies. As a daily leveraged fund, SOXL rebalances daily, meaning results over periods longer than one day can differ significantly from 300% of the index's performance due to the effects of compounding; the fund is also non-diversified.",
"The KraneShares Trust ETF seeks investment results corresponding generally to the price and yield performance of the Solactive Global Luxury Index. Under normal circumstances, the fund invests at least 80% of its net assets in instruments in the underlying index or those with similar economic characteristics. This index is a modified, free float adjusted market capitalization weighted index designed to measure the equity performance of companies from global luxury-related sectors, such as travel & leisure, premium ware, and apparel, located in developed markets. The index selects the top 25 companies based on criteria including size, trading volume, and country of listing, applying a modified weighting approach where the top 5 securities receive higher allocations (with the largest capped at 10%) while others are capped at 4.5%. The index is rebalanced semi-annually. The fund is non-diversified and while targeting US investments, it maintains at least 40% of its assets in foreign entities or those with significant business activities outside the United States."
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [4, 4] 
