Clik here to view.
Sizing disk storage for Weaviate
@vradhik I’ve built this WebApp Weaviate Disk Calculator which should help in estimating the disk size roughly - see if this helps Streamlit Weaviate Disk Storage Calculator is a Streamlit-based...
View ArticleLangchain integration with Weaviate Client v4 - Hybrid search not working
Description It seems the langchain SelfQueryRetriever still generates the filters as per Weaviate Client v3. The filter follows the v3 format, which, for unknown reasons, changed in v4. This is the...
View ArticleClik here to view.
Langchain integration with Weaviate Client v4 - Hybrid search not working
Hi! I believe that this retriever is deprecated Here is the docs for the current integration, and here a recipe we have on how to use Weaviate with Langchain python.langchain.com Weaviate | 🦜️🔗...
View ArticleHave multiple vectors for a single object in the same index?
Description I have records with a field ‘content’, which is a large text body. I want to divide the body into chunks, and vectorize each chunk. However, each chunk should link to the same record....
View ArticleClik here to view.
Have multiple vectors for a single object in the same index?
Morning @Tejas_Sharma Weaviate supports multiple vector embeddings per object through “named vectors” which you already put your hand on. With named vectors, you can store multiple vector embeddings...
View ArticleClik here to view.
Is hybrid search with multiple queries possible?
hi @RisingOrange ! Welcome to our community The document you linked is doing in fact a collection.query.near_vector I believe this is what you want: from weaviate.classes.query import HybridVector,...
View ArticleIs hybrid search with multiple queries possible?
Thanks, that’s helpful! I tried the code on weaviate 4.13.2 and got “Providing lists of lists has been deprecated. Please provide a dictionary with target names as keys and lists of numbers as...
View ArticleHave multiple vectors for a single object in the same index?
Hey Mohamed, Thanks for responding. Those are exactly the problems I have with named vectors, both of them. I need to be able to search on the same index. Is there no solution for this?
View ArticleIs hybrid search with multiple queries possible?
The text queries will boil down to tokens for the bm25 phase of the search So query = "This query has multiple tokens" will be the same as query = [ ["this", "query"], ["has", "multiple", "tokens"] ]...
View ArticleOpenai Vectorizer failing to reach embeddings endpoint
Description I am creating a collection as follows: self.collections[self.test_case_collection_name] = self.client.collections.create( name=self.test_case_collection_name,...
View ArticleQuery Agent API
Do you know if we can filter the agent queries? Or somehow restrict the responses to specific collection properties?
View ArticleOpenai Vectorizer failing to reach embeddings endpoint
Hi @Cam_Quilici ! Welcome to Weaviate Community! It seems that you are encountering OpenAI timeout issues that could happen when inserting large datasets. I noticed that failed objects that could...
View ArticleHave multiple vectors for a single object in the same index?
To be honest, aside from what you’ve already shared—which I agree is a bit clunky—I’m not entirely sure of a better alternative at the moment. If I come across easier solution, I’ll definitely let you...
View ArticleClik here to view.
Have multiple vectors for a single object in the same index?
Hi @Tejas_Sharma ! One possibility to explore is Ref2Vec That way you can have your content chunks vectorized independently and providing their vectors to the record centroid. Now you can search per...
View ArticleOpenai Vectorizer failing to reach embeddings endpoint
Thank you for your response. When I try to insert with this code, I get the following message: 2025-04-29 09:38:59,953 - weaviate-client - ERROR - {'message': 'Failed to send all objects in a batch of...
View ArticleLangchain integration with Weaviate Client v4 - Hybrid search not working
Hi Duda, Not sure why the SelfQueryRetriever should be obsolete. We use it with other vector stores, including Weaviate (Client v3) and the advantage is that it abstracts the underlying databases. If...
View ArticleHave multiple vectors for a single object in the same index?
Thanks @Mohamed_Shahin @DudaNogueira ! Oh wow Ref2Vec seems interesting, but it would require a migration still right… I think the chunking + separate record + with a metadata property foreignId to...
View ArticleOpenai Vectorizer failing to reach embeddings endpoint
hi @Cam_Quilici !! Do you have any resource usage reading? We have some dashboards here for prometheus and grafana: weaviate-local-k8s/manifests/grafana-dashboards at main ·...
View ArticleClik here to view.
Langchain integration with Weaviate Client v4 - Hybrid search not working
hi @atolto-pirla ! I am sorry, I believe I mistaken the classes Actually, this is the deprecated one: WeaviateHybridSearchRetriever — 🦜🔗 LangChain documentation This is considering that Weaviate...
View ArticleOpenai Vectorizer failing to reach embeddings endpoint
So I tried increasing GOMEMLIMIT as well as ASYNC_INDEXING and these did not help solve the issue. Additionally, using a fixed batch size does not work. There is something seriously strange happening...
View Article