Error: "Proto field is not repeating, cannot start list"

Search, No Filter
1

Hello, Looking for some hints or guidance on the following error when executing a simple query (see code below). This error only appears if I query by id. Thanks!

pinecone.core.client.exceptions.PineconeApiException: (400)
Reason: Bad Request
HTTP response headers: HTTPHeaderDict({‘content-type’: ‘text/plain’, ‘content-length’: ‘50’, ‘date’: ‘Tue, 16 Apr 2024 02:43:13 GMT’, ‘server’: ‘envoy’, ‘connection’: ‘close’})
HTTP response body: : Proto field is not repeating, cannot start list.

Here is my sample Python code:

#!/usr/bin/env python3

import os

from config import set_environment
from pinecone import Pinecone, PodSpec 
from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings

set_environment()

model_name = "BAAI/bge-m3"
index_name = "coachai-poc-" + model_name[model_name.find("/")+1:].lower()
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
spec = PodSpec(				
	environment='us-east-1-aws',
	pod_type='p1.x1'
) 

embeddings = HuggingFaceInferenceAPIEmbeddings(
	api_key=os.environ["HUGGINGFACEHUB_API_TOKEN"], model_name=model_name
)

index = pc.Index(index_name)

# Create index if it doesn't already exist
if index_name not in pc.list_indexes().names():
	pc.create_index(
		name=index_name,
		dimension=len(embeddings.embed_documents(["hello world"][0])),
		metric="dotproduct",
		spec=spec
	)		

# Upsert a simple vector
values = embeddings.embed_documents(["hello world"])
vectors = [{
	"id": "doc1#abc", 
	"values": values[0]
}]	
index.upsert(vectors=vectors)


# Query based on id
index.query(
	id=['doc2#abc'],
	top_k=1
)
2

Hi @madiver3, the id parameter accepts a string, not a list. In your case, if your ID is doc2#abc, the query would look like:

# Query based on id
index.query(
	id='doc2#abc',
	top_k=1
)