i already have the text2vec and multi2vec modules, why the result shows dont have the nearText option when i use it to query
Hello @chris31522 
Welcome to our community! We’re glad to have you here.
The error you’re encountering suggests there may be an issue with the vectorizer configuration—either it isn’t being recognized, or the collection might have been created without specifying a vectorizer.
Could you please share the following details with me so I can help you further:
- Your Weaviate version
- The deployment details
- The code you’re using for vectorizer configuration & Creating the schema
This will help me pinpoint where the issue might be coming from.
Best regards,
Mohamed Shahin
Weaviate Support Engineer
thanks for the help!
schema = {
"classes": [
{
"class": "Article", # name of the class
"description": "An Article class to store the article summary and its authors", # a description of what this class represents
"properties": [ # class properties
{
"name": "title",
"dataType": ["string"],
"description": "The title of the article",
},
{
"name": "summary",
"dataType": ["text"],
"description": "The summary of the article",
},
{
"name": "wordCount",
"dataType": ["int"],
"description": "The number of words in the article's summary",
},
{
"name": "hasAuthors",
"dataType": ["Author"],
"description": "The authors this article has",
},
{
"name": "hasCategory",
"dataType": ["Category"],
"description": "The category of this article",
}
]
}, {
# Write the Author class here
"class": "Author",
"description": "An Author class to store the author's name and the articles who wrote",
"properties": [
{
"name": "name",
"dataType": ["string"],
"description": "The name of the author",
},
{
"name": "wroteArticles",
"dataType": ["Article"],
"description": "The articles this author has",
}
]
}, {
# Write the Category class here
"class":"Category",
"description":"A Category class to store the category that article belongs to",
"properties":[
{
"name":"name",
"dataType":["string"],
"description":"the name of the category"
}
]
}
]
}
this is the schema and i download the news from the cnn.com as my data
import newspaper
import uuid
import json
from tqdm import tqdm
def get_articles_from_newspaper(
news_url: str,
max_articles: int=100
) -> None:
"""
Download and save newspaper articles as weaviate schemas.
Parameters
----------
newspaper_url : str
Newspaper title.
"""
objects = []
# Build the actual newspaper
news_builder = newspaper.build(news_url, memoize_articles=False)
if max_articles > news_builder.size():
max_articles = news_builder.size()
pbar = tqdm(total=max_articles)
pbar.set_description(f"{news_url}")
i = 0
while len(objects) < max_articles and i < news_builder.size():
article = news_builder.articles[i]
try:
article.download()
article.parse()
article.nlp()
if (article.title != '' and \
article.title is not None and \
article.summary != '' and \
article.summary is not None and\
article.authors):
# create an UUID for the article using its URL
article_id = uuid.uuid3(uuid.NAMESPACE_DNS, article.url)
# create the object
objects.append({
'id': str(article_id),
'title': article.title,
'summary': article.summary,
'authors': article.authors,
'word_count': len(article.summary.split())
})
pbar.update(1)
except:
# something went wrong with getting the article, ignore it
pass
i += 1
pbar.close()
return objects
data = []
data += get_articles_from_newspaper('http://cnn.com')
and then i upload my data
from weaviate.batch import Batch # for the typing purposes
from weaviate.util import generate_uuid5
def add_article(batch: Batch, article_data: dict) -> str:
article_object = {
'title': article_data['title'],
'wordCount': article_data['word_count'],
'summary': article_data['summary'].replace('\n', '') # remove newline character
}
article_id = article_data['id']
# add article to the batch
batch.add_data_object(
data_object=article_object,
class_name='Article',
uuid=article_id
)
return article_id
def add_author(batch: Batch, author_name: str) -> str:
author_object = {'name': author_name}
# generate an UUID for the Author
author_id = generate_uuid5(author_name)
# add author to the batch
# EXERCISE: call here the batch.add_data_object function to add the author to the batch
batch.add_data_object(
data_object=author_object,
class_name='Author',
uuid=author_id
)
return author_id
def add_references(batch: Batch, article_id: str, author_id: str)-> None:
# add references to the batch
## Author -> Article
batch.add_reference(
from_object_uuid=author_id,
from_object_class_name='Author',
from_property_name='wroteArticles',
to_object_uuid=article_id
)
## Article -> Author
# EXERCISE: call here the batch.add_reference function to add the article->author reference
batch.add_reference(
from_object_uuid=article_id,
from_object_class_name='Article',
from_property_name='hasAuthors',
to_object_uuid=author_id
)
client.batch.configure(batch_size=50, dynamic=True, callback=None)
with client.batch as batch:
for i in data:
# add article to the batch
article_id = add_article(batch, i)
for author in i['authors']:
# add author to the batch
author_id = add_author(batch, author)
# add cross references to the batch
add_references(batch, article_id=article_id, author_id=author_id)
Hi @chris31522,
Thank you so much for sharing this information — it’s really helpful! I’ve taken a look, and I can see that the issue is to the fact that a vectorizer hasn’t been specified in your schema ‘vectorizer’.
Here’s an example of how you can add a vectorizer - in the deprecated client:
class_obj = {
“class”: “Article”,
“properties”: [
{
“name”: “title”,
“dataType”: [“text”],
},
],
“vectorizer”: “text2vec-openai” # This can be any vectorizer of your choice
client.schema.create_class(class_obj)
}
Additionally, you’re using an old version of the client / deprecated, which is making things a bit more complicated for you. I highly recommend upgrading to Python Client v4. This version offers friendly syntax and better performance, making it much easier to work with.
Here is how easy you can specify vectorizer in V4:
Here’s what I recommend for your use case:
-
Remove the current schema.
-
Upgrade your Weaviate Client locally by running the following: pip install -U weaviate-client
-
Recreate the schema using the updated syntax (including the vectorizer) - see below:
from weaviate.classes.config import Configure, Property, DataType
client.collections.create(
“Article”,
vectorizer_config=Configure.Vectorizer.text2vec_openai(),
properties=[ # This part is optional, depending on your needs
Property(name=“title”, data_type=DataType.TEXT),
Property(name=“body”, data_type=DataType.TEXT),
]
)
As you can see, the new syntax is much more user-friendly and easier compared to the old version!
- Ingest data using the batch method in v4 — you’ll find it much faster and easier.
One of the main benefits of using the v4 client is that uses a gRPC interface. It is based on HTTP/2 and Protocol Buffers, and is therefore very fast and efficient.
I hope this helps! If you have any questions or need further assistance, don’t hesitate to reach out — I’m here to help.
Best regards,
Mohamed Shahin
Weaviate Support Engineer
Hi @chris31522,
I was curious to know why you opted for the v3 client, as it’s an older version. Were you following a specific tutorial or guide? If so, I’d be happy to assist in updating it to the latest version (v4).
Best regards,
Mohamed Shahin
Weaviate Support
i tried your solution,but there is a new problem:(
i can’t upload my data successfully and the query result is empty! Before I change my code, it can be upload successfully…
Hi @chris31522,
Could you please share the code you used to create the collection? and I’ll help you with that.
Best regards,
Mohamed Shahin,
Weaviate Support Engineer
Hi @chris31522,
Could you please share the scripts you used to create the collection and ingest data? This will help me better understand the configuration and pinpoint the issue.
Additionally, could you provide the Sandbox URL you’re working with?
Best regards,
Mohamed Shahin
Weaviate Support