HackerTrans
トップ新着トレンドコメント過去質問紹介求人

Fendyfd

no profile record

投稿

Milvus 2.5: full-text search and semantic search

milvus.io
2 ポイント·投稿者 Fendyfd·2 年前·0 コメント

Databricks is raising $10B Series J Investment at $62B Valuation

databricks.com
1 ポイント·投稿者 Fendyfd·2 年前·2 コメント

Matryoshka Embeddings

milvus.io
1 ポイント·投稿者 Fendyfd·2 年前·0 コメント

[untitled]

1 ポイント·投稿者 Fendyfd·2 年前·0 コメント

Top Keywords about Milvus

milvus.io
2 ポイント·投稿者 Fendyfd·2 年前·0 コメント

Benchmarking VectorDB

zilliz.com
1 ポイント·投稿者 Fendyfd·2 年前·0 コメント

How to Evaluate RAG Apps

zilliz.com
1 ポイント·投稿者 Fendyfd·2 年前·0 コメント

[untitled]

1 ポイント·投稿者 Fendyfd·3 年前·0 コメント

Milvus Vector Database in 2023

milvus.io
7 ポイント·投稿者 Fendyfd·3 年前·0 コメント

Open Source Benchmarking Tool for Vector Databases

zilliz.com
1 ポイント·投稿者 Fendyfd·3 年前·0 コメント

[untitled]

1 ポイント·投稿者 Fendyfd·3 年前·0 コメント

Yet Another Cache, but for ChatGPT

zilliz.com
1 ポイント·投稿者 Fendyfd·3 年前·1 コメント

コメント

Fendyfd
·2 年前·議論
thanks
Fendyfd
·2 年前·議論
It is open-sourced, and you can find its source code on GitHub. The leaderboard is just something easy for readers to have a quick look at. You're welcome to use this tool to generate your results.

I won't argue with you about whether "vector database" should be a product category. You are not the first or even the last person who has doubts about it. Maybe many years later, we'll have the answer.
Fendyfd
·2 年前·議論
trying to answer your questions since you asked.
Fendyfd
·2 年前·議論
FYI the VectorDBBench leaderboard: https://zilliz.com/vector-database-benchmark-tool?database=Z...
Fendyfd
·2 年前·議論
Good question. 1. VectorDBBench is an open-source benchmark that is pretty vendor-neutral. If you've used it or checked its leaderboard, you'll find that almost every database is ranked first or in the top place on specific metrics.

2. The key to using a benchmark is not to find which vector database is the "best" but which one is most suitable for your use cases and applications. Actually, there is no "universally best" vector database for any situation. So I don't think anyone should be able to cheat on this.
Fendyfd
·2 年前·議論
There are multiple vectordb available in the market, open source ones include Milvus, Qdrant, Weaviate etc. Cloud services include Zilliz Cloud (managed milvus), Qdrant Cloud, Weaviate Cloud etc. Try using a benchmark tool to evaluate them. Here is an open-source option for your reference: VectorDBBench (https://github.com/zilliztech/VectorDBBench)
Fendyfd
·3 年前·議論
[dead]
Fendyfd
·3 年前·議論
With GPTCache, you can cache your LLM responses with just a few lines of code changes, boosting your LLM applications 100 times faster.