ChatGPT, an AI model developed by OpenAI, has gained popularity for its ability to generate human-like text responses based on the input it receives. Integrating ChatGPT into a React Native application can enhance user interactions by providing intelligent responses to user queries or messages. In this guide, we’ll walk through the process of implementing ChatGPT in a React Native application and handling streaming responses for real-time interactions.
Before we begin, make sure you have the following installed:
If you haven’t already, create a new React Native project using the following command:
npx react-native init ChatGPTAppNavigate to the project directory:
cd ChatGPTAppInstalling required dependencies Next, we need to install the required dependencies. We will use the EventSource library to handle streaming responses. You can install it using the following command:
yarn add react-native-sse @react-native-clipboard/clipboardIntegrating the ChatGPT model To integrate the ChatGPT model, we need to make an API request to the OpenAI API. First, you need to sign up for an API key from the OpenAI website. Once you have the API key, you can use the following code to make an API request:
const handleGetChatGPTResponse = (seletedIndex, list) => {
try {
setCurrentIndex(seletedIndex);
setConversationList([...list]);
const params = JSON.stringify({ model: 'gpt-3.5-turbo',
messages: [...list],
max_tokens: 600,
n: 1,
temperature: 0.8,
stream: true, });
} catch (error) {
console.log('Error', error);
}
};In the above code, we are making an API request to the OpenAI API with the model, messages, max_tokens, n, temperature, and stream parameters. You can also adjust more parameters and configurations as given in OpenAI Doc. We can also send previous responses to chat gpt as history so chatgpt can give replies based on it. We also add an event listener for the open event, triggered when the connection is established. We are also adding an event listener for the message event, which is triggered when a new message is received.
To handle streaming responses, we are using the EventSource API using react-native-sse sdk. The EventSource API allows us to receive real-time updates from the server. In the above code, we are adding an event listener for the message event, which is triggered when a new message is received. We are then parsing the JSON data and updating the conversationList state with the new message. You can follow the below code to request a streaming response.
const handleGetChatGPTResponse = (selectedIndex, list) => {
try {
setCurrentIndex(selectedIndex);
setConversationList([...list]);
const params = JSON.stringify({
model: 'gpt-3.5-turbo',
messages: [...list],
max_tokens: 600,
n: 1,
temperature: 0.8,
stream: true,
});
setShowActionButtons(false);
const es = new EventSource(Endpoints.chatGptUrl, {
headers: {
'Content-Type': 'application/json',
Authorization: `Bearer ${OPENAI_API_KEY}`,
},
method: 'POST',
body: params,
pollingInterval: 0,
});
es.addEventListener('open', () => {
console.log('Open ');
});
es.addEventListener('message', (event) => {
console.log('Test Message', event);
let temp = conversationList;
if (event.data !== '[DONE]') {
const data = JSON.parse(event.data);
console.log('Test Message', data);
if (data?.choices[0]?.delta?.content !== undefined) {
let value = temp[selectedIndex]?.content;
let newValue = value + data.choices[0].delta.content;
temp[selectedIndex].content = newValue;
console.log('temp', temp);
}
} else {
setShowActionButtons(true);
}
setConversationList([...temp]);
setTimeout(() => {
flatListRef?.current?.scrollToEnd();
}, 1000);
setSearch('');
});
return () => {
es.close();
es.removeAllEventListeners();
};
} catch (error) {
console.log('Error', error);
}
};import {
FlatList,
Keyboard,
KeyboardAvoidingView,
SafeAreaView,
StyleSheet,
Text,
TextInput,
TouchableOpacity,
View,
} from "react-native";
import React, { useEffect, useRef, useState } from "react";
import Colors from "../theme/Colors";
import { Header, SvgIcon } from "../components";
import Strings from "../utils/Strings";
import SvgIcons from "../utils/SvgIcons";
import { FontFamily, FontSize } from "../utils/Fonts";
import { isAndroid, isIos } from "../utils/Metrics";
import stylesCommon from "../utils/stylesCommon";
import Clipboard from "@react-native-clipboard/clipboard";
import { showSuccessToast } from "../components/FlashMessage";
import EventSource from "react-native-sse";
import { Endpoints, OPENAI_API_KEY } from "../networkConfig/Endpoints";
const EditWithChatGpt = () => {
const [search, setSearch] = useState("");
const [keyboardOffset, setKeyboardOffset] = useState(0);
const [conversationList, setConversationList] = useState([]);
const [currentIndex, setCurrentIndex] = useState(0);
const flatListRef = useRef();
const [showActionButtons, setShowActionButtons] = useState(false);
useEffect(() => {
const keyboardDidShowListener = Keyboard.addListener(
isAndroid ? "keyboardDidShow" : "keyboardWillShow",
(e) => {
setKeyboardOffset(e.endCoordinates.height);
}
);
const keyboardDidHideListener = Keyboard.addListener(
isAndroid ? "keyboardDidHide" : "keyboardWillHide",
() => {
setKeyboardOffset(0);
}
);
return () => {
keyboardDidShowListener.remove();
keyboardDidHideListener.remove();
};
}, []);
const onPressRefresh = (item, index) => {
let selectedIndex = index;
let list = conversationList || [];
list[index].content = "";
setCurrentIndex(selectedIndex);
setConversationList([...list]);
handleGetChatGPTResponse(selectedIndex, list);
};
const onPressSend = () => {
try {
let selectedIndex = currentIndex;
let list = conversationList || [];
let queObj = {
role: "user",
content: search?.trim(),
};
let ansObj = {
role: "system",
content: "",
};
list.push(queObj);
list.push(ansObj);
selectedIndex = list.length - 1;
setCurrentIndex(selectedIndex);
setConversationList([...list]);
handleGetChatGPTResponse(selectedIndex, list);
} catch (error) {
console.log("Error", error);
}
};
const handleGetChatGPTResponse = (selectedIndex, list) => {
try {
setCurrentIndex(selectedIndex);
setConversationList([...list]);
const params = JSON.stringify({
model: "gpt-3.5-turbo",
messages: [...list],
max_tokens: 600,
n: 1,
temperature: 0.8,
stream: true,
});
setShowActionButtons(false);
const es = new EventSource(Endpoints.chatGptUrl, {
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${OPENAI_API_KEY}`,
},
method: "POST",
body: params,
pollingInterval: 0,
});
es.addEventListener("open", () => {
console.log("Open ");
});
es.addEventListener("message", (event) => {
console.log("Test Message", event);
let temp = conversationList;
if (event.data !== "[DONE]") {
const data = JSON.parse(event.data);
console.log("Test Message", data);
if (data?.choices[0]?.delta?.content !== undefined) {
let value = temp[selectedIndex]?.content;
let newValue = value + data.choices[0].delta.content;
temp[selectedIndex].content = newValue;
console.log("temp", temp);
} else {
}
} else {
setShowActionButtons(true);
}
setConversationList([...temp]);
setTimeout(() => {
flatListRef?.current?.scrollToEnd();
}, 1000);
});
setSearch("");
return () => {
es.close();
es.removeAllEventListeners();
};
} catch (error) {
console.log("Error", error);
}
};
const renderConversation = ({ item, index }) => {
let isUser = item?.role == "user";
return (
<View style={styles.itemWrap}>
<View style={styles.topNameWrap}>
<Text style={styles.userStyle}>
{isUser ? Strings.you : Strings.bMAIAssistant}
</Text>
</View>
<Text style={styles.content}>{item?.content}</Text>
{showActionButtons ? (
<View style={styles.iconListWrap}>
<TouchableOpacity
style={styles.iconWrap}
onPress={() => onPressClipboard(item)}
>
<SvgIcon name={SvgIcons.copyIcon} height={15} width={15} />
</TouchableOpacity>
{!isUser && index == conversationList.length - 1 ? (
<TouchableOpacity
style={[styles.iconWrap, styles.refreshIcon]}
onPress={() => onPressRefresh(item, index)}
>
<SvgIcon name={SvgIcons.refreshIcon} height={15} width={15} />
</TouchableOpacity>
) : null}
</View>
) : null}
</View>
);
};
const onPressClipboard = (item) => {
let { content } = item;
try {
Clipboard.setString(content);
showSuccessToast(Strings.copiedSuccessMsg);
} catch (error) {}
};
return (
<View style={styles.container}>
<Header backButton middleText={Strings.editWithAiAssistant} />
<View style={styles.mainWrap}>
<View style={stylesCommon.flex}>
{conversationList.length ? (
<FlatList
data={conversationList}
extraData={conversationList}
renderItem={renderConversation}
ref={flatListRef}
showsVerticalScrollIndicator={false}
bounces={false}
contentContainerStyle={styles.contentContainerStyle}
/>
) : (
<View style={styles.topWrap}>
<Text style={styles.howCanIHelpYou}>
{Strings.howCanIHelpYou}
</Text>
</View>
)}
</View>
<KeyboardAvoidingView
behavior={isIos ? "padding" : null}
enabled
contentContainerStyle={[
stylesCommon.flexGrow,
{ paddingBottom: keyboardOffset },
]}
keyboardVerticalOffset={100}
>
<View style={styles.bottomWrapper}>
<Text>{Strings.content}</Text>
<View style={styles.inputBackground}>
<View style={styles.inputWrapper}>
<TextInput
placeholder={Strings.sendMessage}
autoCorrect={false}
placeholderTextColor={Colors.disable}
blurOnSubmit={false}
cursorColor={Colors.tabActive}
selectionColor={Colors.tabActive}
underlineColorAndroid={Colors.transparent}
value={search}
onChangeText={(text) => setSearch(text)}
multiline
style={styles.inputStyle}
/>
</View>
<View style={styles.lastWrap}>
<TouchableOpacity
style={[
styles.sendWrap,
{
backgroundColor: search?.trim()?.length
? Colors.green2
: Colors.disable,
},
]}
onPress={onPressSend}
>
<SvgIcon name={SvgIcons.sendIcon} height={20} width={20} />
</TouchableOpacity>
</View>
</View>
</View>
</KeyboardAvoidingView>
</View>
<SafeAreaView />
</View>
);
};
export default EditWithChatGpt;
const styles = StyleSheet.create({
container: {
flex: 1,
backgroundColor: Colors.white,
},
mainWrap: {
flex: 1,
paddingTop: 15,
paddingHorizontal: 20,
},
topWrap: {
alignItems: "center",
paddingTop: 20,
flex: 1,
},
howCanIHelpYou: {
color: Colors.primaryText,
marginTop: 15,
},
inputBackground: {
backgroundColor: Colors.background,
borderWidth: 1,
borderColor: Colors.divider,
marginTop: 10,
paddingVertical: 10,
borderRadius: 8,
paddingHorizontal: 10,
maxHeight: 300,
alignItems: "center",
justifyContent: "space-between",
flexDirection: "row",
},
inputStyle: {
fontSize: FontSize.F14,
padding: 0,
fontFamily: FontFamily.regular,
color: Colors.primaryText,
maxHeight: 250,
paddingBottom: isIos ? 5 : 3,
},
bottomWrapper: {
paddingBottom: 20,
paddingHorizontal: 2,
paddingTop: 10,
},
sendWrap: {
height: 35,
width: 35,
borderRadius: 5,
alignItems: "center",
justifyContent: "center",
},
lastWrap: {
justifyContent: "flex-end",
paddingLeft: 5,
alignSelf: "flex-end",
},
topNameWrap: {
flexDirection: "row",
alignItems: "center",
},
nameInitialWrap: {
height: 25,
width: 25,
backgroundColor: Colors.tabActive,
borderRadius: 50,
alignItems: "center",
justifyContent: "center",
marginRight: 10,
},
itemWrap: {
paddingVertical: 10,
},
iconListWrap: {
flexDirection: "row",
alignItems: "center",
marginTop: 20,
},
iconWrap: {
height: 30,
width: 30,
backgroundColor: Colors.lightGray,
borderRadius: 60,
alignItems: "center",
justifyContent: "center",
},
refreshIcon: {
marginLeft: 10,
},
disabledButtonContainerStyle: {
backgroundColor: Colors.white,
borderWidth: 1,
borderColor: Colors.border,
flex: 0.5,
marginLeft: 10,
},
inputWrapper: {
maxHeight: 250,
flex: 0.99,
width: "90%",
},
contentContainerStyle: {
flexGrow: 1,
paddingBottom: 20,
},
content: {
fontSize: 14,
fontWeight: "600",
color: "gray",
},
userStyle: {
fontSize: 16,
color: "Black",
fontWeight: "bold",
},
});
This blog post explains how to implement the ChatGPT model in a React Native application and handle streaming responses using the EventSource API. It covers project setup, model integration, and streaming response handling to create an interactive chat experience. By leveraging ChatGPT, you can enhance user engagement and provide valuable assistance in various applications. Experiment with different configurations to customize the chat interface to your needs.
!! Enjoy, Keep, and Do Delicious Coding !!
The team at Mindbowser was highly professional, patient, and collaborative throughout our engagement. They struck the right balance between offering guidance and taking direction, which made the development process smooth. Although our project wasn’t related to healthcare, we clearly benefited...
Founder, Texas Ranch Security
Mindbowser played a crucial role in helping us bring everything together into a unified, cohesive product. Their commitment to industry-standard coding practices made an enormous difference, allowing developers to seamlessly transition in and out of the project without any confusion....
CEO, MarketsAI
I'm thrilled to be partnering with Mindbowser on our journey with TravelRite. The collaboration has been exceptional, and I’m truly grateful for the dedication and expertise the team has brought to the development process. Their commitment to our mission is...
Founder & CEO, TravelRite
The Mindbowser team's professionalism consistently impressed me. Their commitment to quality shone through in every aspect of the project. They truly went the extra mile, ensuring they understood our needs perfectly and were always willing to invest the time to...
CTO, New Day Therapeutics
I collaborated with Mindbowser for several years on a complex SaaS platform project. They took over a partially completed project and successfully transformed it into a fully functional and robust platform. Throughout the entire process, the quality of their work...
President, E.B. Carlson
Mindbowser and team are professional, talented and very responsive. They got us through a challenging situation with our IOT product successfully. They will be our go to dev team going forward.
Founder, Cascada
Amazing team to work with. Very responsive and very skilled in both front and backend engineering. Looking forward to our next project together.
Co-Founder, Emerge
The team is great to work with. Very professional, on task, and efficient.
Founder, PeriopMD
I can not express enough how pleased we are with the whole team. From the first call and meeting, they took our vision and ran with it. Communication was easy and everyone was flexible to our schedule. I’m excited to...
Founder, Seeke
We had very close go live timeline and Mindbowser team got us live a month before.
CEO, BuyNow WorldWide
If you want a team of great developers, I recommend them for the next project.
Founder, Teach Reach
Mindbowser built both iOS and Android apps for Mindworks, that have stood the test of time. 5 years later they still function quite beautifully. Their team always met their objectives and I'm very happy with the end result. Thank you!
Founder, Mindworks
Mindbowser has delivered a much better quality product than our previous tech vendors. Our product is stable and passed Well Architected Framework Review from AWS.
CEO, PurpleAnt
I am happy to share that we got USD 10k in cloud credits courtesy of our friends at Mindbowser. Thank you Pravin and Ayush, this means a lot to us.
CTO, Shortlist
Mindbowser is one of the reasons that our app is successful. These guys have been a great team.
Founder & CEO, MangoMirror
Kudos for all your hard work and diligence on the Telehealth platform project. You made it possible.
CEO, ThriveHealth
Mindbowser helped us build an awesome iOS app to bring balance to people’s lives.
CEO, SMILINGMIND
They were a very responsive team! Extremely easy to communicate and work with!
Founder & CEO, TotTech
We’ve had very little-to-no hiccups at all—it’s been a really pleasurable experience.
Co-Founder, TEAM8s
Mindbowser was very helpful with explaining the development process and started quickly on the project.
Executive Director of Product Development, Innovation Lab
The greatest benefit we got from Mindbowser is the expertise. Their team has developed apps in all different industries with all types of social proofs.
Co-Founder, Vesica
Mindbowser is professional, efficient and thorough.
Consultant, XPRIZE
Very committed, they create beautiful apps and are very benevolent. They have brilliant Ideas.
Founder, S.T.A.R.S of Wellness
Mindbowser was great; they listened to us a lot and helped us hone in on the actual idea of the app. They had put together fantastic wireframes for us.
Co-Founder, Flat Earth
Ayush was responsive and paired me with the best team member possible, to complete my complex vision and project. Could not be happier.
Founder, Child Life On Call
The team from Mindbowser stayed on task, asked the right questions, and completed the required tasks in a timely fashion! Strong work team!
CEO, SDOH2Health LLC
Mindbowser was easy to work with and hit the ground running, immediately feeling like part of our team.
CEO, Stealth Startup
Mindbowser was an excellent partner in developing my fitness app. They were patient, attentive, & understood my business needs. The end product exceeded my expectations. Thrilled to share it globally.
Owner, Phalanx
Mindbowser's expertise in tech, process & mobile development made them our choice for our app. The team was dedicated to the process & delivered high-quality features on time. They also gave valuable industry advice. Highly recommend them for app development...
Co-Founder, Fox&Fork
