Greetings,
I'm currently using a demo account to test how this service works before deploying on a larger scale. My problem: I have deployed a text-bison@001 endpoint to figure out how to create and access endpoints. It is deployed on us-central1.
When trying to access the endpoint using the PredictionServiceClient from the node pkg Google-cloud/aiplatform I am receiving this error in the console:
```
Error: 13 INTERNAL: Received RST_STREAM with code 0
at callErrorFromStatus ([...]/node_modules/@grpc/grpc-js/build/src/call.js:31:19)
at Object.onReceiveStatus ([...]/node_modules/@grpc/grpc-js/build/src/client.js:192:76)
at Object.onReceiveStatus ([...]/node_modules/@grpc/grpc-js/build/src/client-interceptors.js:360:141)
at Object.onReceiveStatus ([...]/node_modules/@grpc/grpc-js/build/src/client-interceptors.js:323:181)
at [...]/node_modules/@grpc/grpc-js/build/src/resolving-call.js:99:78
at process.processTicksAndRejections (node:internal/process/task_queues:77:11)
for call at
at ServiceClientImpl.makeUnaryRequest ([...]/node_modules/@grpc/grpc-js/build/src/client.js:160:32)
at ServiceClientImpl.<anonymous> ([...]/node_modules/@grpc/grpc-js/build/src/make-client.js:105:19)
at [...]/node_modules/@google-cloud/aiplatform/build/src/v1/prediction_service_client.js:237:29
at [...]/node_modules/google-gax/build/src/normalCalls/timeout.js:44:16
at OngoingCallPromise.call ([...]/node_modules/google-gax/build/src/call.js:67:27)
at NormalApiCaller.call ([...]/node_modules/google-gax/build/src/normalCalls/normalApiCaller.js:34:19)
at [...]/node_modules/google-gax/build/src/createApiCall.js:84:30
at process.processTicksAndRejections (node:internal/process/task_queues:95:5) {
code: 13,
details: 'Received RST_STREAM with code 0',
metadata: Metadata { internalRepr: Map(0) {}, options: {} }
}
```
I am making the request in this way:
```
const { PredictionServiceClient } = require('@google-cloud/aiplatform').v1;
const API_ENDPOINT = [...];
const PROJECT_ID = [...];
const aiPlatformClient = new PredictionServiceClient({ credentials: tempAuthKey});
const response = await aiPlatformClient.predict({
instances: [
{
content: query,
}
],
parameters: {
[...]
}
});
```
The link and values for PROJECT_ID etc are taken from the sample prompt.
The tempAuthKey is a JSON object generated for a subuser, which should have all permissions for endpoint useage.
I would highly appreciate any help to figure out what I am doing wrong here.
LinkedIn
Twitter
