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?

When attempting to report an issue, the process recommends using Slack. However, the provided link is not functional unless you have already been added to the Slack account. I suggest that the link should redirect to a service capable of managing invites.

Community Slack
Chat with the community about any issues, questions, or feedback

Hi,

I have tried running the attendance example. However I run into the following error:
TypeError: 'NoneType' object is not subscriptable

Image faces_detected.jpg written to filesystem:  True
Client created (student_test.py file)
127.0.0.1 - - [28/May/2022 20:04:11] "POST / HTTP/1.1" 500 -
Traceback (most recent call last):
  File "E:\weaviate-examples\attendance-system-example\venv\Lib\site-packages\flask\app.py", line 2091, in __call__
    return self.wsgi_app(environ, start_response)
  File "E:\weaviate-examples\attendance-system-example\venv\Lib\site-packages\flask\app.py", line 2076, in wsgi_app
    response = self.handle_exception(e)
  File "E:\weaviate-examples\attendance-system-example\venv\Lib\site-packages\flask\app.py", line 2073, in wsgi_app
    response = self.full_dispatch_request()
  File "E:\weaviate-examples\attendance-system-example\venv\Lib\site-packages\flask\app.py", line 1518, in full_dispatch_request
    rv = self.handle_user_exception(e)
  File "E:\weaviate-examples\attendance-system-example\venv\Lib\site-packages\flask\app.py", line 1516, in full_dispatch_request
    rv = self.dispatch_request()
  File "E:\weaviate-examples\attendance-system-example\venv\Lib\site-packages\flask\app.py", line 1502, in dispatch_request
    return self.ensure_sync(self.view_functions[rule.endpoint])(**req.view_args)
  File "E:\weaviate-examples\attendance-system-example\upload_student.py", line 44, in upload_image
    attendance = markAttendance(faces,own=True) #.drop_duplicates()
  File "E:\weaviate-examples\attendance-system-example\mark.py", line 18, in markAttendance
    name = testit(img)
  File "E:\weaviate-examples\attendance-system-example\student_test.py", line 87, in testit
    ans = res['data']['Get']['Students'][0]['labelName']
TypeError: 'NoneType' object is not subscriptable
127.0.0.1 - - [28/May/2022 20:04:11] "GET /?__debugger__=yes&cmd=resource&f=style.css HTTP/1.1" 200 -
127.0.0.1 - - [28/May/2022 20:04:11] "GET /?__debugger__=yes&cmd=resource&f=debugger.js HTTP/1.1" 200 -
127.0.0.1 - - [28/May/2022 20:04:11] "GET /?__debugger__=yes&cmd=resource&f=console.png HTTP/1.1" 200 -
 * Detected change in 'E:\\weaviate-examples\\attendance-system-example\\upload_student.py', reloading
libpng warning: iCCP: known incorrect sRGB profile
 * Restarting with stat
C:\Program Files\JetBrains\PyCharm Community Edition 2020.2.2\plugins\python-ce\helpers\pydev\pydevd.py:1844: DeprecationWarning: currentThread() is deprecated, use current_thread() instead
  dummy_thread = threading.currentThread()
 * Debugger is active!
 * Debugger PIN: 521-878-846
 * Running on http://127.0.0.1:5000/ (Press CTRL+C to quit)
127.0.0.1 - - [28/May/2022 20:04:59] "GET / HTTP/1.1" 200 -

I used the images from the following directories to test it out:
attendance-system-example\students and attendance-system-example\test

Regards,

when I try to run this sample it break even after installing weaviate-ts-client.

I got this error:

webpack compiled with 1 warning
ERROR in src/weaviate_search.ts:1:15
TS2724: '"weaviate-ts-client"' has no exported member named 'IWeaviateClient'. Did you mean 'WeaviateClient'?
  > 1 | import type { IWeaviateClient } from "weaviate-ts-client";
      |               ^^^^^^^^^^^^^^^
    2 |
    3 | export type FilterInput = {
    4 |   languageIdsSelected: number[];

I installed weaviate_client-3.16.0 to try and use from weaviate.embedded import EmbeddedOptions for weaviate.Client but am getting below error when running this example class_obj through client.schema.create_class(class_obj)

UnexpectedStatusCodeException Traceback (most recent call last)
Input In [4], in
6 # Create a schema to add images
7 # I have used the web page https://weaviate.io/developers/weaviate/v1.11.0/retriever-vectorizer-modules/multi2vec-clip.html
8 # to get help on making a suitable schema. You can read the contents of this web page to know more.
9 class_obj = {
10 "class": "ClipExample",
11 "description": "A class to implement CLIP example",
(...)
41 ]
42 }
---> 44 client.schema.create_class(class_obj)
45 print("Schema class created")

File ~/.local/lib/python3.8/site-packages/weaviate/schema/crud_schema.py:182, in Schema.create_class(self, schema_class)
180 # validate the class before loading
181 check_class(loaded_schema_class)
--> 182 self._create_class_with_primitives(loaded_schema_class)
183 self._create_complex_properties_from_class(loaded_schema_class)

File ~/.local/lib/python3.8/site-packages/weaviate/schema/crud_schema.py:708, in Schema._create_class_with_primitives(self, weaviate_class)
706 raise RequestsConnectionError("Class may not have been created properly.") from conn_err
707 if response.status_code != 200:
--> 708 raise UnexpectedStatusCodeException("Create class", response)

UnexpectedStatusCodeException: Create class! Unexpected status code: 422, with response body: {'error': [{'message': 'vectorizer: no module with name "multi2vec-clip" present'}]}.

While following the example: monitoring-prometheus-grafana, I encountered with the following error: err="open /prometheus/queries.active: permission denied" in the logs of the prometheus container.

It is simply that you have to change ownership for /data/prometheus folder so that inside the container the mounted folder is accesible. This can easily be done with the following command:
sudo chown -R 65534:65534 data/prometheus/

Perhaps this happened because I'm not running on rootless docker, however I think this should be specified as one of the steps in the repo's README

We are trying to achieve some class object property reference links to other class objects property in order to reduce process time for the vectorization and memory. But We are facing issue with below error when calling to batch.add_reference() error as
{'error': [{'message': "ref batch: write inverted batch: write additions: no bucket for prop 'section_content__meta_count' found"}]}
Setup for test: We are using weaviate 1.18.2 version:
We followed steps as per reference example https://weaviate.io/developers/weaviate/client-libraries/python#manual-batching
Can you please provide complete setup of example or is there any bug in provided example steps.

Hi,
I'm currently working in a system where I score the document based on a calculated score from two separate retrievals, each one with it's own sbert model (a linear sum of two cosine similarities) . Is this type of query possible with weaviate? If so, is there any example I can have look?
Thanks!

This notebook needs to be updated. The cell, where the data is imported, is doing it manually, now it is possible to do it with the client. This cell:

## doing this manually until the client is updated
import requests

def import_posts_with_vectors(posts, vectors):
    if len(posts) != len(vectors):
        raise Exception("len of posts ({}) and vectors ({}) does not match".format(len(posts), len(vectors)))
        
    for i, post in enumerate(posts):
        r = requests.post('http://localhost:8080/v1/objects', json={
            "class": "Post",
            "vector": vectors[i].tolist(),
            "properties": {
                "content": post,
            }
        })
             
        if r.status_code > 399:
            print(res)