@inproceedings{bang-2023-gptcache,
title = "{GPTC}ache: An Open-Source Semantic Cache for {LLM} Applications Enabling Faster Answers and Cost Savings",
author = "Bang, Fu",
editor = "Tan, Liling and
Milajevs, Dmitrijs and
Chauhan, Geeticka and
Gwinnup, Jeremy and
Rippeth, Elijah",
booktitle = "Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.nlposs-1.24",
doi = "10.18653/v1/2023.nlposs-1.24",
pages = "212--218",
abstract = "The rise of ChatGPT1 has led to the development of artificial intelligence (AI) applications, particularly those that rely on large language models (LLMs). However, recalling LLM APIs can be expensive, and the response speed may slow down during LLMs{'} peak times, causing frustration among developers. Potential solutions to this problem include using better LLM models or investing in more computing resources. However, these options may increase product development costs and decrease development speed. GPTCache2 is an open-source semantic cache that stores LLM responses to address this issue. When integrating an AI application with GPTCache, user queries are first sent to GPTCache for a response before being sent to LLMs like ChatGPT. If GPTCache has the answer to a query, it quickly returns the answer to the user without having to query the LLM. This approach saves costs on API recalls and makes response times much faster. For instance, integrating GPTCache with the GPT service offered by OpenAI can increase response speed 2-10 times when the cache is hit. Moreover, network fluctuations will not affect GPTCache{'}s response time, making it highly stable. This paper presents GPTCache and its architecture, how it functions and performs, and the use cases for which it is most advantageous.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bang-2023-gptcache">
<titleInfo>
<title>GPTCache: An Open-Source Semantic Cache for LLM Applications Enabling Faster Answers and Cost Savings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fu</namePart>
<namePart type="family">Bang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liling</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrijs</namePart>
<namePart type="family">Milajevs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geeticka</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Gwinnup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elijah</namePart>
<namePart type="family">Rippeth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rise of ChatGPT1 has led to the development of artificial intelligence (AI) applications, particularly those that rely on large language models (LLMs). However, recalling LLM APIs can be expensive, and the response speed may slow down during LLMs’ peak times, causing frustration among developers. Potential solutions to this problem include using better LLM models or investing in more computing resources. However, these options may increase product development costs and decrease development speed. GPTCache2 is an open-source semantic cache that stores LLM responses to address this issue. When integrating an AI application with GPTCache, user queries are first sent to GPTCache for a response before being sent to LLMs like ChatGPT. If GPTCache has the answer to a query, it quickly returns the answer to the user without having to query the LLM. This approach saves costs on API recalls and makes response times much faster. For instance, integrating GPTCache with the GPT service offered by OpenAI can increase response speed 2-10 times when the cache is hit. Moreover, network fluctuations will not affect GPTCache’s response time, making it highly stable. This paper presents GPTCache and its architecture, how it functions and performs, and the use cases for which it is most advantageous.</abstract>
<identifier type="citekey">bang-2023-gptcache</identifier>
<identifier type="doi">10.18653/v1/2023.nlposs-1.24</identifier>
<location>
<url>https://aclanthology.org/2023.nlposs-1.24</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>212</start>
<end>218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GPTCache: An Open-Source Semantic Cache for LLM Applications Enabling Faster Answers and Cost Savings
%A Bang, Fu
%Y Tan, Liling
%Y Milajevs, Dmitrijs
%Y Chauhan, Geeticka
%Y Gwinnup, Jeremy
%Y Rippeth, Elijah
%S Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F bang-2023-gptcache
%X The rise of ChatGPT1 has led to the development of artificial intelligence (AI) applications, particularly those that rely on large language models (LLMs). However, recalling LLM APIs can be expensive, and the response speed may slow down during LLMs’ peak times, causing frustration among developers. Potential solutions to this problem include using better LLM models or investing in more computing resources. However, these options may increase product development costs and decrease development speed. GPTCache2 is an open-source semantic cache that stores LLM responses to address this issue. When integrating an AI application with GPTCache, user queries are first sent to GPTCache for a response before being sent to LLMs like ChatGPT. If GPTCache has the answer to a query, it quickly returns the answer to the user without having to query the LLM. This approach saves costs on API recalls and makes response times much faster. For instance, integrating GPTCache with the GPT service offered by OpenAI can increase response speed 2-10 times when the cache is hit. Moreover, network fluctuations will not affect GPTCache’s response time, making it highly stable. This paper presents GPTCache and its architecture, how it functions and performs, and the use cases for which it is most advantageous.
%R 10.18653/v1/2023.nlposs-1.24
%U https://aclanthology.org/2023.nlposs-1.24
%U https://doi.org/10.18653/v1/2023.nlposs-1.24
%P 212-218
Markdown (Informal)
[GPTCache: An Open-Source Semantic Cache for LLM Applications Enabling Faster Answers and Cost Savings](https://aclanthology.org/2023.nlposs-1.24) (Bang, NLPOSS-WS 2023)
ACL