itrummer
My name is Immanuel, I'm assistant professor at Cornell University. I mostly publish code that relates to my research which is about database and data analysis.
Cornell University
Pinned Repositories
CiceroDBoldVersion
CodexDB
CodexDB generates code for SQL query processing via OpenAI's GPT-3 Codex model.
DataCorrelationPredictionWithNLP
This project aims at predicting correlated column pairs in data tables by analyzing column names via large language models.
DataScienceWithGPT
Resources to learn data processing with GPT and other language models
dbbert
DB-BERT tunes database systems for optimal performance, using tuning hints mined from text.
ExactCardinalityQueryOptimization
This repository contains tools for finding query plans that produce the least number of join result tuples (the so-called "Cout" metric). Those tools are not suitable for query optimization at run time - instead, they can be used for offline analysis to assess the quality of query optimizers.
itrummer.github.io
Personal page of Immanuel Trummer.
lm4db
Material for my VLDB'22 and BTW'23 tutorials on application for language models in data management
query-optimizer-lib
Contains implementations of various algorithms for database query optimization. The algorithms cover multiple problem variants (e.g., traditional and multi-objective query optimization) and offer different tradeoffs between optimality guarantees and optimization time (e.g., fast randomized algorithms, approximation schemes, exhaustive algorithms, parallel algorithms, ...).
schemacompression
Compress database schemata to reduce cost for LLM processing
itrummer's Repositories
itrummer/CodexDB
CodexDB generates code for SQL query processing via OpenAI's GPT-3 Codex model.
itrummer/dbbert
DB-BERT tunes database systems for optimal performance, using tuning hints mined from text.
itrummer/query-optimizer-lib
Contains implementations of various algorithms for database query optimization. The algorithms cover multiple problem variants (e.g., traditional and multi-objective query optimization) and offer different tradeoffs between optimality guarantees and optimization time (e.g., fast randomized algorithms, approximation schemes, exhaustive algorithms, parallel algorithms, ...).
itrummer/DataCorrelationPredictionWithNLP
This project aims at predicting correlated column pairs in data tables by analyzing column names via large language models.
itrummer/DataScienceWithGPT
Resources to learn data processing with GPT and other language models
itrummer/lm4db
Material for my VLDB'22 and BTW'23 tutorials on application for language models in data management
itrummer/CiceroDBoldVersion
itrummer/schemacompression
Compress database schemata to reduce cost for LLM processing
itrummer/ExactCardinalityQueryOptimization
This repository contains tools for finding query plans that produce the least number of join result tuples (the so-called "Cout" metric). Those tools are not suitable for query optimization at run time - instead, they can be used for offline analysis to assess the quality of query optimizers.
itrummer/itrummer.github.io
Personal page of Immanuel Trummer.
itrummer/NaturalMiner
Mine data for patterns described in natural language
itrummer/BABOONS
itrummer/vta
Frontend for virtual TA
itrummer/awesome-codex
A list dedicated to products, demos and articles related to 🤖 OpenAI's Codex.
itrummer/qdata
itrummer/awesome-gpt3
itrummer/balm
BALM - A framework for Batch Analysis with Language Models
itrummer/cornelldbseminar
Website of the Cornell Database Seminar
itrummer/databyvoice
Web site summarizing our work on voice query interfaces
itrummer/dbz
itrummer/llmjoins
Implements theta-joins with free-text join predicates using large language models.
itrummer/naru
Neural Relation Understanding: neural cardinality estimators for tabular data
itrummer/quantumdb
Algorithms for mapping database optimization problems to quantum hardware (D-Wave).
itrummer/sigmod2019voice
itrummer/skinnerdb-1
itrummer/SkinnerPG
itrummer/slate
Slate is a Jekyll theme for GitHub Pages
itrummer/testingstreamlit
itrummer/tupac
TUPAC: Tuning with Partial Configurations
itrummer/WebChecker