Sequential API Function Calling Using GraphQL Schema

Avirup Saha, Lakshmi Mandal, Balaji Ganesan, Sambit Ghosh, Renuka Sindhgatta, Carlos Eberhardt, Dan Debrunner, Sameep Mehta


Abstract
Function calling using Large Language Models (LLMs) is an active research area that aims to empower LLMs with the ability to execute APIs to perform real-world tasks. However, sequential function calling using LLMs with interdependence between functions is still under-explored. To this end, we introduce GraphQLRestBench, a dataset consisting of natural language utterances paired with function call sequences representing real-world REST API calls with variable mapping between functions. In order to represent the response structure of the functions in the LLM prompt, we use the GraphQL schema of the REST APIs. We also introduce a custom evaluation framework for our dataset consisting of four specially designed metrics. We evaluate various open-source LLMs on our dataset using few-shot Chain-of-Thought and ReAct prompting to establish a reasonable baseline.
Anthology ID:
2024.emnlp-main.1083
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
19452–19458
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1083
DOI:
Bibkey:
Cite (ACL):
Avirup Saha, Lakshmi Mandal, Balaji Ganesan, Sambit Ghosh, Renuka Sindhgatta, Carlos Eberhardt, Dan Debrunner, and Sameep Mehta. 2024. Sequential API Function Calling Using GraphQL Schema. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19452–19458, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Sequential API Function Calling Using GraphQL Schema (Saha et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1083.pdf
Software:
 2024.emnlp-main.1083.software.zip
Data:
 2024.emnlp-main.1083.data.zip