nodejs-firestore
nodejs-firestore copied to clipboard
googleapis
FieldValue.vector works well on top, but does not work in nested fields
Environment
- Operating System version: firebase cloud functions
- Firebase SDK version:
- "firebase-admin": "^12.2.0",
- "firebase-functions": "^5.0.1",
- Firebase Product: Firestore
- Node.js version: v18.20.3
- NPM version: 10.7.0
Problem
FieldValue.vector works well on top, but does not work in nested fields
Steps to reproduce:
This code works well
const admin = require("firebase-admin");
const functions = require("firebase-functions");
const embedder = require("./create_embedding");
exports.autoCreateEmbedding = functions.runWith({memory: "1GB"})
.firestore.document("z_embedding/{docId}").onCreate(async (snap) => {
const fv = admin.firestore.FieldValue;
const data = snap.data();
const n = data.name;
const n2 = data.name2;
const tensorEmbedding1 = await embedder.createEmbeddingTensor(n);
const tensorEmbedding2 = await embedder.createEmbeddingTensor(n2);
const googleEmbedding1 = await embedder.createEmbeddingGoogle(n);
const googleEmbedding2 = await embedder.createEmbeddingGoogle(n2);
console.log(`created embeddings`);
const te = {t1: fv.vector( tensorEmbedding1), t2: fv.vector(tensorEmbedding2)};
const ge = {g1: fv.vector(googleEmbedding1), g2: fv.vector(googleEmbedding2)};
// concat embeddings into one object
const embeddings = {...te, ...ge}; // PROBLEM WILL BE HERE
console.log(`updating embeddings`);
try {
await snap.ref.update(embeddings);
} catch (error) {
console.log("Error updating document: ", error);
}
});
What happened? How can we make the problem occur? When I change the problem line from
const embeddings = {...te, ...ge}; // PROBLEM WILL BE HERE
to
const embeddings = {te, ge};
await snap.ref.update(embeddings);
operation fails with
Error updating document: Error: 13 INTERNAL: An internal error occurred.
Relevant Code:
createEmbeddingGoogle: async function(text) {
const projectId = JSON.parse(process.env.FIREBASE_CONFIG).projectId;
// SETUP MODEL
const model = "text-multilingual-embedding-002";
const clientOptions = {apiEndpoint: "us-central1-aiplatform.googleapis.com"};
const endpoint = `projects/${projectId}/locations/us-central1/publishers/google/models/${model}`;
const instances = [helpers.toValue({content: toSuperLower(text), taskType: "QUESTION_ANSWERING"})];
const request = {endpoint, instances};
const client = new PredictionServiceClient(clientOptions);
// GET EMBEDDING
const [response] = await client.predict(request);
const prediction = response.predictions[0];
const embeddings = prediction.structValue.fields.embeddings;
const values = embeddings.structValue.fields.values.listValue.values;
const embeddingsArray = values.map((value) => value.numberValue);
return embeddingsArray;
},
createEmbeddingTensor: async function(text) {
tf.setBackend("tensorflow");
const model = await use.load();
const embeddings = await model.embed(text);
const embeddingsArray = embeddings.arraySync().flat();
return embeddingsArray;
},
Additional
To verify that I am creating the correct object format I tested with this and it works well
exports.autoCreateEmbedding = functions.runWith({memory: "1GB"})
.firestore.document("z_embedding/{docId}").onCreate(async (snap) => {
// const fv = admin.firestore.FieldValue;
const data = snap.data();
const n = data.name;
const n2 = data.name2;
// const tensorEmbedding1 = await embedder.createEmbeddingTensor(n);
// const tensorEmbedding2 = await embedder.createEmbeddingTensor(n2);
// const googleEmbedding1 = await embedder.createEmbeddingGoogle(n);
// const googleEmbedding2 = await embedder.createEmbeddingGoogle(n2);
console.log(`created embeddings`);
const te = {t1: n, t2: n2};
const ge = {g1: n, g2: n2};
// concat embeddings into one object
const embeddings = {te, ge};
console.log(`updating embeddings`);
try {
await snap.ref.update(embeddings);
} catch (error) {
console.log("Error updating document: ", error);
}
});
Error 13 internal is definitely unexpected. However, I wasn't able to reproduce the issue by nesting vectors in other object. Are you able to provide us with logs from the SDK? Add this line to your repro to configure SDK logging:
setLogFunction(console.log);
I added the line and got the following results.
Firestore (7.9.0) 2024-07-11T07:20:23.748Z YLwHZ [WriteBatch.commit]: Sending 1 writes
Firestore (7.9.0) 2024-07-11T07:20:23.749Z YLwHZ [ClientPool.acquire]: Creating a new client (requiresGrpc: false)
Firestore (7.9.0) 2024-07-11T07:20:23.829Z ##### [clientFactory]: Initialized Firestore GAPIC Client (useFallback: false)
Firestore (7.9.0) 2024-07-11T07:20:23.831Z YLwHZ [Firestore.request]: Sending request:
Firestore (7.9.0) 2024-07-11T07:20:24.051Z YLwHZ [Firestore.request]: Received error: Error: 13 INTERNAL: An internal error occurred.
at callErrorFromStatus (/workspace/node_modules/@grpc/grpc-js/build/src/call.js:31:19)
at Object.onReceiveStatus (/workspace/node_modules/@grpc/grpc-js/build/src/client.js:193:76)
at Object.onReceiveStatus (/workspace/node_modules/@grpc/grpc-js/build/src/client-interceptors.js:360:141)
at Object.onReceiveStatus (/workspace/node_modules/@grpc/grpc-js/build/src/client-interceptors.js:323:181)
at /workspace/node_modules/@grpc/grpc-js/build/src/resolving-call.js:129:78
at process.processTicksAndRejections (node:internal/process/task_queues:77:11)
for call at
at ServiceClientImpl.makeUnaryRequest (/workspace/node_modules/@grpc/grpc-js/build/src/client.js:161:32)
at ServiceClientImpl.
Thanks for the log snippet. Unfortunately that doesn't contain any info that will help me diagnose further. Can you perhaps share your project ID?
You can share privately by creating a support case at https://firebase.google.com/support/troubleshooter/contact. Reference this github issue in the support case and ask them to forward the issue to me for faster resolution.
We were able to reproduce the issue and are working on a fix, however it will probably be a little bit before it's rolled out.
Thanks for reporting this!
Hi, I apologize for the long delay on the rollout, but this should be pushed out now. Please let me know if you're still seeing this issue.
Hi, I have tested with the latest versions:
"@google-cloud/aiplatform": "^3.27.0",
"firebase-admin": "^12.4.0",
"firebase-functions": "^5.1.0",
works like a charm.
Thank You.