Batch inserts failing for weaviate
Hi! I believe this is an issue on how your Weaviate is exposed. Maybe, the client is hitting the url, but traefik is not delivering the request correctly, and returning with a 404 error. and yes, if...
View ArticleClik here to view.
Hybrid Search Implementation Without Predefined Sparse Vectors in Weaviate
this question was also asked and answered here: Hybrid search with embedding outside the database Support hi @LauraZ !! The hybrid search is a fusion of the keyword search and the vector search. When...
View ArticleMessage': "module 'text2vec-transformers': invalid combination of properties
Hi! While checking the code, it looks like this is a guardrail to make sure there is something vectorizable to pass to the embeddings service. However, it only seems to check for a text data type, but...
View ArticleSpecifying properties with multi-tenancy causes bug
Oh, I see. This is a pitfall of the AUTOSCHEMA_ENABLED feature. Note that we do not recommend leaving AUTOSCHEMA_ENABLED in production as it can create new properties if you specify a wrong property...
View ArticleGoogle automatic token generation
Any updates? I’ve done a workaround solution in the meantime but would appreciate a better solution.
View ArticleBinary Quantization Vector Not Found in Collection
Hi, I have setup a binary quantization on my collection like this collection = client.collections.create( name=collection_name,...
View ArticleBatch inserts failing for weaviate
Hello, I believe that too. I can check on the configuration of ingress for this. However, from the logs, the request was forwarded from traefik to weavaite server as I could see the log with message:...
View ArticleHybrid Search near_text distance filtering
Hi, it is not yet part of the docs, but there is a new parameter to filter all results based on the vector distance - so any result that has a distance higher than the max vector distance is filtered...
View ArticleConnect to Weaviate instance WITHOUT grpc
I want to connect to my old weaviate instance. However, in its current settings, it doesn’t have a load balancer with grpc configured, so i want to do it without grpc. I want to connect to it via...
View ArticleHybrid Search near_text distance filtering
Hello Dirk, Thank you for your help. Your solution has resolved the issue.
View ArticleConnect to Weaviate instance WITHOUT grpc
Hey, then you need to use the old typescript client (v2). V3 only works with GRPC
View ArticleOllama dial tcp [::1]:11434: connect: connection refused
Thanks for your reply @DudaNogueira! I was able to successfully run both the command and the python script. I also converted the script to js and ran it successfully*, so it seems that the issue is...
View ArticleClik here to view.
Ollama dial tcp [::1]:11434: connect: connection refused
Glad to hear that @sjogden ! and that now you are no longer blocked!! Happy coding! And remember: we are here to help whenever needed
View ArticleWeaviate startup time has increased with 1.25 onwards
Description We have upgraded from 1.24.23 to 1.26.4. Earlier weaviate was able to start up within a second, however after upgrading, it takes 2-10 seconds to come up for small dataset. As per...
View ArticleConnect to Weaviate instance WITHOUT grpc
Thank you so much for the clarification. For me it was not clear whether grpc was mandatory for the client, i thought it preferred grpc over http. What mislead me was, the fact that grpcHost was...
View ArticleConnect to Weaviate instance WITHOUT grpc
Another solution would be making a fallback mechanism. I’d be glad to help prepare a pr for that as well, but obviously that’d take more time.
View ArticleClik here to view.
Google automatic token generation
HI! This feature is only available to be set on the server side as of now. and Not on the client side. We do have a feature request to add this feature to the client side too:...
View ArticleClik here to view.
Text search and multiple embeddings
Hi @vrano, Sure thing! I’m always happy to help! For your first point, yes, you can add properties and indexes to a collection after it’s created, but there’s an important aspect to keep in mind: If...
View ArticleCreating RAG using own data vectorized in Azure
Hi All, I’ve vectorized my data using Azure OpenAI Embeddings, but I wanted to confirm if I’m approaching the creation of collections correctly. So far, only the content itself is vectorized, while...
View ArticleClik here to view.
.near_text vector search score is very low
I am creating a schema as below I’ve added the data to the collection, but when I query it for the nearest results to the test term “Art Briefs” (which is an exact match in the collection), I’m...
View Article