An Indexer that works out-of-the-box when you have less than 100K stored Documents

Overview

U100KIndexer

An Indexer that works out-of-the-box when you have less than 100K stored Documents. U100K means under 100K. At 100K stored Documents with 768-dim embeddings, you can expect 300ms for single query or 20~120QPS for batch queries. Results are full Documents.

U100KIndexer leverages jina.DocumenetArrayMemmap as the storage backend and .match() to conduct nearest neighbours search. It returns the full Documents as-is, hence no need to concatenate it with another key-value indexer to retrieve Documents.

Pros & cons

Pros

  • Exhaustive search: highest recall
  • Fast indexing
  • Acceptable query performance under 100K
  • Always return full Documents
  • No extra dependencies

Cons

  • Slow query time

Performance

The indexing and query performance on 768-dim embeddings is as follows (unit is second):

Stored data Indexing time Query size=1 Query size=8 Query size=64
10000 0.256 0.019 0.029 0.086
50000 1.156 0.147 0.177 0.314
100000 2.329 0.297 0.332 0.536
200000 4.704 0.656 0.744 1.050
400000 11.105 1.289 1.536 2.793

Benchmark script can be found in benchmark.py.

Tips

To change workspace,

U100KIndexer(metas={'workspace': './my'})

Or .add(..., uses_metas={'workspace': './my'}) when you use it in a Flow.

Owner
Jina AI
A Neural Search Company. We provide the cloud-native neural search solution powered by state-of-the-art AI technology.
Jina AI
CINECA molecular dynamics tutorial set

High Performance Molecular Dynamics Logging into CINECA's computer systems To logon to the M100 system use the following command from an SSH client ss

J. W. Dell 0 Mar 13, 2022
This creates a ohlc timeseries from downloaded CSV files from NSE India website and makes a SQLite database for your research.

NSE-timeseries-form-CSV-file-creator-and-SQL-appender- This creates a ohlc timeseries from downloaded CSV files from National Stock Exchange India (NS

PILLAI, Amal 1 Oct 02, 2022
Data cleaning tools for Business analysis

Datacleaning datacleaning tools for Business analysis This program is made for Vicky's work. You can use it, too. 数据清洗 该数据清洗工具是为了商业分析 这个程序是为了Vicky的工作而

Lin Jian 3 Nov 16, 2021
Fitting thermodynamic models with pycalphad

ESPEI ESPEI, or Extensible Self-optimizing Phase Equilibria Infrastructure, is a tool for thermodynamic database development within the CALPHAD method

Phases Research Lab 42 Sep 12, 2022
PyStan, a Python interface to Stan, a platform for statistical modeling. Documentation: https://pystan.readthedocs.io

PyStan PyStan is a Python interface to Stan, a package for Bayesian inference. Stan® is a state-of-the-art platform for statistical modeling and high-

Stan 229 Dec 29, 2022
Generate lookml for views from dbt models

dbt2looker Use dbt2looker to generate Looker view files automatically from dbt models. Features Column descriptions synced to looker Dimension for eac

lightdash 126 Dec 28, 2022
Evidence enables analysts to deliver a polished business intelligence system using SQL and markdown.

Evidence enables analysts to deliver a polished business intelligence system using SQL and markdown

915 Dec 26, 2022
Methylation/modified base calling separated from basecalling.

Remora Methylation/modified base calling separated from basecalling. Remora primarily provides an API to call modified bases for basecaller programs s

Oxford Nanopore Technologies 72 Jan 05, 2023
Recommendations from Cramer: On the show Mad-Money (CNBC) Jim Cramer picks stocks which he recommends to buy. We will use this data to build a portfolio

Backtesting the "Cramer Effect" & Recommendations from Cramer Recommendations from Cramer: On the show Mad-Money (CNBC) Jim Cramer picks stocks which

Gábor Vecsei 12 Aug 30, 2022
The OHSDI OMOP Common Data Model allows for the systematic analysis of healthcare observational databases.

The OHSDI OMOP Common Data Model allows for the systematic analysis of healthcare observational databases.

Bell Eapen 14 Jan 02, 2023
High Dimensional Portfolio Selection with Cardinality Constraints

High-Dimensional Portfolio Selecton with Cardinality Constraints This repo contains code for perform proximal gradient descent to solve sample average

Du Jinhong 2 Mar 22, 2022
Port of dplyr and other related R packages in python, using pipda.

Unlike other similar packages in python that just mimic the piping syntax, datar follows the API designs from the original packages as much as possible, and is tested thoroughly with the cases from t

179 Dec 21, 2022
Python Practicum - prepare for your Data Science interview or get a refresher.

Python-Practicum Python Practicum - prepare for your Data Science interview or get a refresher. Data Data visualization using data on births from the

Jovan Trajceski 1 Jul 27, 2021
Single machine, multiple cards training; mix-precision training; DALI data loader.

Template Script Category Description Category script comparison script train.py, loader.py for single-machine-multiple-cards training train_DP.py, tra

2 Jun 27, 2022
The lastest all in one bombing tool coded in python uses tbomb api

BaapG-Attack is a python3 based script which is officially made for linux based distro . It is inbuit mass bomber with sms, mail, calls and many more bombing

59 Dec 25, 2022
Bearsql allows you to query pandas dataframe with sql syntax.

Bearsql adds sql syntax on pandas dataframe. It uses duckdb to speedup the pandas processing and as the sql engine

14 Jun 22, 2022
Tokyo 2020 Paralympics, Analytics

Tokyo 2020 Paralympics, Analytics Thanks for checking out my app! It was built entirely using matplotlib and Tokyo 2020 Paralympics data. This applica

Petro Ivaniuk 1 Nov 18, 2021
Candlestick Pattern Recognition with Python and TA-Lib

Candlestick-Pattern-Recognition-with-Python-and-TA-Lib Goal Look at the S&P500 to try and get a better understanding of these candlestick patterns and

Ganesh Jainarain 11 Oct 07, 2022
.npy, .npz, .mtx converter.

npy-converter Matrix Data Converter. Expand matrix for multi-thread, multi-process Divid matrix for multi-thread, multi-process Support: .mtx, .npy, .

taka 1 Feb 07, 2022
An easy-to-use feature store

A feature store is a data storage system for data science and machine-learning. It can store raw data and also transformed features, which can be fed straight into an ML model or training script.

ByteHub AI 48 Dec 09, 2022