gorilla-llm/APIBench

---
license: apache-2.0
language:
- en
tags:
- api
---
# Gorilla: Large Language Model Connected with Massive APIs
By Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez ([Project Website](https://shishirpatil.github.io/gorilla/))

[](https://arxiv.org/abs/2305.15334) [](https://discord.gg/3apqwwME) [](https://colab.research.google.com/drive/1DEBPsccVLF_aUnmD0FwPeHFrtdC0QIUP?usp=sharing)

`Gorilla` enables LLMs to use tools by invoking APIs. Given a natural language query, Gorilla can write a semantically- and syntactically- correct API to invoke. With Gorilla, we are the first to demonstrate how to use LLMs to invoke 1,600+ (and growing) API calls accurately while reducing hallucination. We also release APIBench, the largest collection of APIs, curated and easy to be trained on! Join us, as we try to expand the largest API store and teach LLMs how to write them! Hop on our Discord, or open a PR, or email us if you would like to have your API incorporated as well.

### Dataset Date

05/28/2023

### Organization

Gorilla LLM (UC Berkeley)

---
license: apache-2.0
---

原始信息汇总

数据集概述

数据集名称

Gorilla: Large Language Model Connected with Massive APIs

作者

Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez

数据集描述

Gorilla 是一个能够使大型语言模型（LLMs）通过调用API来使用工具的数据集。它能够根据自然语言查询生成语义和语法正确的API调用。该数据集首次展示了如何使用LLMs准确调用超过1600个（且数量在增长）的API，同时减少了幻觉现象。此外，还发布了APIBench，这是目前最大的API集合，便于训练。

数据集日期

2023年05月28日

组织机构

Gorilla LLM (UC Berkeley)

许可证

Apache-2.0