Viewing profile — lqhl

Oh, we missed this new standard. Our first version must have been implemented before its release. We should definitely consider it now.

LLM applications can benefit from Retrieval-Augmented Generation (RAG) in a similar way that humans benefit from search engines like Google. Therefore, I believe RAG cannot be repl…

MyScaleDB utilizes approximate nearest neighbors (ANN) algorithms such as ScaNN, HNSW, and IVF. As a result, it may not achieve a 100% recall rate. However, depending on the search…

Since we developed our internal version before the release of usearch, we integrated hnswlib with faiss's PQ/SQ algorithms. Search performance is typically not a concern in real-wo…

I have subscribed to ChatGPT Plus for asking development questions and requesting code writing assistance, especially in unfamiliar languages. I have a few complaints about ChatGPT…

I'm not familiar with it. maybe you can submit a PR?

A comparison matrix of some vector databases. Feel free to submit PRs on https://github.com/lqhl/vectordb-comparison/ to contribute!

I work on MyScale ( https://myscale.com ), a fully-managed vector database based on ClickHouse. Some unique features of MyScale: 1. This solution is built on ClickHouse and offers …

We conducted a benchmark to evaluate the precision, throughput (QPS), insert speed, build speed, and cost-effectiveness of Pinecone, Qdrant, MyScale, Weaviate, and Zilliz (Milvus).…

Compilance is also important. Like SOC 2

As jwells89 mentioned, LLMs can extract the intention from questions and generate better queries for a search engine or database.

This idea is a simplified version of Retrieval-Augmented Generation (RAG), and RAG has been studied in various research papers, such as the one available at https://arxiv.org/abs/2…

This article suggests that LLMs should use a database as a reference for factual information. Rather than asking LLMs to provide their own answers, it is recommended that they summ…

That's true and we have tried different configurations for systems that use HNSW. But for the ease of presentation, we only choose the configuration with the highest throughput at …