Skip to content

error occurs at update_embeddings #56

@3CE8D2BAC65BDD6AA9

Description

@3CE8D2BAC65BDD6AA9

I have been trying https://github.com/weaviate/weaviate-examples/blob/main/harrypotter-qa-haystack-weaviate/JUPYTER-HarryPotter-QA-Haystack-Weaviate.ipynb a few times at my local machine.

My code is:

from haystack.utils

import clean_wiki_text
import pandas as pd

harry = pd.read_csv("https://s3.eu-central-1.amazonaws.com/deepset.ai-farm-qa/datasets/documents/harry_potter_wiki.csv")

dicts = []

for ix, row in harry.iterrows():
dic = {

    'content': clean_wiki_text(row.text),
    'meta': {
        'name': row['name'],
        'url': row.url
    }
}
dicts.append(dic)

from haystack.utils import launch_weaviate
launch_weaviate()
from haystack.document_stores import WeaviateDocumentStore
document_store = WeaviateDocumentStore() # assumes Weaviate is running on http://localhost:8080
document_store.write_documents(documents=dicts, batch_size=100)
from haystack.nodes import EmbeddingRetriever

retriever = EmbeddingRetriever(document_store=document_store, model_format="sentence_transformers", embedding_model="sentence-transformers/multi-qa-mpnet-base-dot-v1",)
document_store.update_embeddings(retriever)
from haystack.nodes import FARMReader
reader = FARMReader(model_name_or_path="deepset/tinyroberta-squad2", use_gpu=True)

everything went smooth until this line:

document_store.update_embeddings(retriever)

The error message is:

Exception has occurred: WeaviateDocumentStoreError
Query results contain errors: [{'locations': [{'column': 6, 'line': 1}], 'message': 'explorer: list class: search: invalid pagination params: query maximum results exceeded', 'path': ['Get', 'Document']}]
File "/home/ky/weaviate/harrypotter.py", line 26, in
document_store.update_embeddings(retriever)
haystack.document_stores.weaviate.WeaviateDocumentStoreError: Query results contain errors: [{'locations': [{'column': 6, 'line': 1}], 'message': 'explorer: list class: search: invalid pagination params: query maximum results exceeded', 'path': ['Get', 'Document']}]

Any idea how to resolve this?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions