CodexDB: Generating Code for Processing SQL Queries using GPT-3 Codex

2022-04-19 · Immanuel Trummer

CodexDB is an SQL processing engine whose internals can be customized via natural language instructions. CodexDB is based on OpenAI's GPT-3 Codex model which translates text into code. It is a framework on top of GPT-3 Codex that decomposes complex SQL queries into a series of simple processing steps, described in natural language. Processing steps are enriched with user-provided instructions and descriptions of database properties. Codex translates the resulting text into query processing code. An early prototype of CodexDB is able to generate correct code for a majority of queries of the WikiSQL benchmark and can be customized in various ways.

📄 PDF Abstract BibTeX arXiv:2204.08941

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…

Adam 설명 없음

Multi-Head Attention 설명 없음

Residual Connection 설명 없음

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…

Execution-Based Evaluation for Open-Domain Code Generation

2022-12-20 · Zhiruo Wang, Shuyan Zhou, Daniel Fried, Graham Neubig

To extend the scope of coding queries to more realistic settings, we propose ODEX, the first Open-Domain EXecution-based natural language (NL) to Python code generation dataset. ODEX has 945 NL-Code pairs spanning 79 div…

Code Generation Memorization

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

2024-08-07 · Xiangyan Liu, Bo Lan, Zhiyuan Hu, Yang Liu 외

Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a r…

HumanEval mbpp Retrieval

Codex Hacks HackerRank: Memorization Issues and a Framework for Code Synthesis Evaluation

2022-12-06 · Anjan Karmakar, Julian Aron Prenner, Marco D'Ambros, Romain Robbes

The Codex model has demonstrated extraordinary competence in synthesizing code from natural language problem descriptions. However, in order to reveal unknown failure modes and hidden biases, such large-scale models must…

Memorization

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis

2024-02-25 · Yao Mu, Junting Chen, Qinglong Zhang, Shoufa Chen 외

Robotic behavior synthesis, the problem of understanding multimodal inputs and generating precise physical control for robots, is an important part of Embodied AI. Despite successes in applying multimodal large language …

Code Generation Multimodal Reasoning Visual Question Answering

CoSQA: 20,000+ Web Queries for Code Search and Question Answering

2021-05-27 · ACL 2021 5 · JunJie Huang, Duyu Tang, Linjun Shou, Ming Gong 외

Finding codes given natural language query isb eneficial to the productivity of software developers. Future progress towards better semantic matching between query and code requires richer supervised training resources. …

Code Search Contrastive Learning Natural Language Queries Question Answering