- Recipes
- OpenAI prompt to Amazon S3 NDJSON file
Connect OpenAI prompt and Amazon S3 NDJSON file in our serverless environment
Use this template to Get OpenAI prompt responses using them to create NDJSON file entries in Amazon S3 Bucket.
Share
Get OpenAI prompt responses
Used integrations:
JavaScript
Python
class OpenaiSourceGetPromptResponse {
async init() {
// TODO: Create your OpenAI credential
// More info at https://yepcode.io/docs/integrations/openai/#credential-configuration
this.openai = yepcode.integration.openai("your-openai-credential-name");
}
async fetch(publish, done) {
// TODO: Configure your prompt
const funnyPrompts = [
"What do you think of humans?",
"Do you prefer tabs or spaces?",
"What's the meaning of life, the universe, and everything?",
"What's your favorite programming joke?",
"What's the worst code you've ever seen?"
];
// More info at: https://platform.openai.com/docs/api-reference/completions/create
const completion = await this.openai.createCompletion({
model: "text-davinci-003",
prompt: funnyPrompts,
max_tokens: 7,
temperature: 0,
});
for (const choice of completion.data.choices) {
await publish(choice);
}
done();
}
async close() {}
}
class OpenaiSourceGetPromptResponse:
def setup(self):
# TODO: Create your OpenAI credential
# More info at https://yepcode.io/docs/integrations/openai/#credential-configuration
self.openai = yepcode.integration.openai("your-openai-credential-name")
def generator(self):
# TODO: Configure your prompt
# More info at: https://platform.openai.com/docs/api-reference/completions/create
prompts = [
"What do you think of humans?",
"Do you prefer tabs or spaces?",
"What's the meaning of life, the universe, and everything?",
"What's your favorite programming joke?",
"What's the worst code you've ever seen?"
]
completion = self.openai.Completion.create(
model="text-davinci-003",
prompt=prompts,
max_tokens=7,
temperature=0
)
for choice in completion.choices:
yield choice
def close(self):
pass
Do you need help solving this integration with YepCode?
Let's talkCreate NDJSON file entries in Amazon S3 Bucket
Used integrations:
JavaScript
Python
class AwsS3TargetUploadNdjson {
async init() {
// TODO: Create your aws-s3 credential
// More info at https://yepcode.io/docs/integrations/aws-s3/#credential-configuration
const awsS3 = yepcode.integration.awsS3("your-aws-s3-credential-name");
// Transforms the items into a ndjson format
this.stringifier = ndjson.stringify();
const targetStream = new PassThrough();
this.stringifier.pipe(targetStream);
// TODO: customize the Upload content
// More info at: https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/interfaces/_aws_sdk_lib_storage.options-1.html
const upload = new Upload({
client: awsS3,
params: {
Bucket: "your-bucket-name",
Key: "your-file-name.ndjson",
Body: targetStream,
},
});
upload.on("httpUploadProgress", (progress) => {
console.log(`Upload progress`, progress);
});
this.uploadPromise = upload.done();
}
async consume(item) {
this.stringifier.write(item);
}
async close() {
try {
this.stringifier.end();
} catch (error) {
console.error(`Error ending stringifier`, error);
}
try {
await this.uploadPromise;
} catch (error) {
console.error(`Error ending upload`, error);
}
}
}
import ndjson
import io
class AccumulatingStream:
def __init__(self):
self.data = io.BytesIO()
def write(self, item):
self.data.write(item.encode("utf-8"))
def get_stream(self):
self.data.seek(0)
return self.data
class AwsS3TargetUploadNdjson:
def setup(self):
# TODO: Create your S3 credential:
# More info at https://yepcode.io/docs/integrations/aws-s3/#credential-configuration
self.aws_s3_client = yepcode.integration.awsS3("your-s3-credential-name")
self.acc_stream = AccumulatingStream()
self.stringifier = ndjson.writer(self.acc_stream, ensure_ascii=False)
def consume(self, generator, done):
for item in generator:
self.stringifier.writerow(item)
done()
def close(self):
# TODO: customize the bucket name and object key
try:
self.aws_s3_client.upload_fileobj(
self.acc_stream.get_stream(),
"bucket-name",
"path/to/object.ndjson",
)
except Exception as error:
print(f"Error uploading object: {error}")
FAQs
YepCode is a SaaS platform that allows to create, execute and monitor integrations and automations using source code in a serverless environment.
We like to call it the Zapier for developers, since we bring all the agility and benefits of NoCode tools (avoid server provisioning, environment configuration, deployments,...), but with all the power of being able to use a programming language like JavaScript or Python.
These recipes are a good starting point for you to build your own YepCode processes and solve your integration and automation problems.
You only have to fill the sign up form and your account will be created with our FREE plan (no credit card required).
YepCode has been created with a clear enterprise approach (multi-tenant environment, team management, high security and auditing standards, IdP integrations, on-premise options,...) so we can be the Swiss army knife of any team of engineering, especially those that need to extract or send information to external systems, and where a certain dynamism or adaptation to change is necessary in that process.
Sure! You just need to do some configuration to allow YepCode servers to connect to that service. Check our docs page to get more information.