Verba doesn't read my .env-file
Hi ! I have a debian linux runing all fine. I have made a venv and installed Verba with pip install . I have made a verba.env file and placed it in the venv/verrba/ folder. In the file I have spec for...
View ArticleColbertV2 Support
Hey @JK_Rider, yes the notebook would be super helpful. From this reference – #2 supports my initial assumption that queries and documents are zero-padded to fixed length: “2. BERT manages this...
View ArticleColbertV2 Support
Additional note: we are on this and you can expect something soon. Please follow: HNSW Multi-value vectors (colbert) · Issue #4278 · weaviate/weaviate · GitHub
View ArticleClik here to view.
ColbertV2 Support
@CShorten Ex 1: Using BGE-M3 with Flag Embedding Ex 2: Using JinaColbert with official colbert repo If you need any more examples or some more context, let me know.
View ArticleWeaviate Openai Embedding Models
All of Openai’s embedding models currently max out 8192 tokens. Some open-source embedding models support larger context windows, but I’d suggest chunking your data and you’ll(probably) get better...
View ArticleHow to get the disk usage for weaviate data for each collection
Description: Does there is a way that I can get the disk usage for weaviate data for each collection? Server Setup Information Weaviate Server Version: 1.26 Deployment Method: docker/k8s/AWS Multi...
View ArticleWeaviate Openai Embedding Models
Could you please guide in this regard? @DudaNogueira @JK_Rider
View ArticleWeaviate Openai Embedding Models
Here’s a quick guide on Chunking which should help out:A Guide to Chunking Strategies for Retrieval Augmented Generation (RAG) — Sagacify.
View ArticleClik here to view.
Explosive growth (to 10sec) of request latency when one cluster's node fails
Description We have a weaviate cluster with 3 nodes. Average request latency (crud/vsearch+QUORUM) 10-70ms. When one node fails (or a pod restarts), eg: “weaviate-2”, the requests latency increases to...
View ArticleExplosive growth (to 10sec) of request latency when one cluster's node fails
Hi @wvuser, Thanks for the report. You are correct, this is definitely unexpected. If a QUORUM can still be achieved and you only send your requests to nodes that report ready, there is no reason for...
View ArticleWeaviate Client for Self-Hosted environment
Description We are planning to host Weaviate in our AWS environment, and would like to understand whether Weaviate provides any UI Client to view the data of the Weaviate. Server Setup Information...
View ArticleExplosive growth (to 10sec) of request latency when one cluster's node fails
Hello @wvuser, This is José Luis, QA at Weaviate. Thanks a lot for reporting this issue. I did manage to reproduce it with the steps you provided. The good news is that this issue has been already...
View ArticleWeaviate Client for Self-Hosted environment
hi @saurbhhsharrma !! We don’t have a UI app you could access your self hosted clusters. We are developing some of those Apps in our console. However, you can easily use a client, eg python v4 client...
View ArticleHow to get the disk usage for weaviate data for each collection
Hi Alisha! Whenever a new collection is created on a node, a folder will be created that stores all content related to that collection in the wherever your PERSISTENCE_DATA_PATH is defined. So AFAIK,...
View ArticleClik here to view.
Verba doesn't read my .env-file
hi! Welcome to our community The environment variable file must be called .env and not verba.env Ps: @hugmun hope those keys are not valid ones Let me know if this helps! Thanks!
View ArticleClik here to view.
Google automatic token generation
Hi @Cobyboss !! This is the corresponding documentation: weaviate.io Google AI + Weaviate | Weaviate - Vector Database Google AI offers a wide range of models for natural language processing and...
View ArticleClik here to view.
Weaviate Openai Embedding Models
hi @spark !! as @JK_Rider mentioned, the issue is about passing too much context. If you see this when vectorizing (which seems to be the case, considering the “update vector” part of the log), it is...
View ArticleClik here to view.
Weaviate Openai Embedding Models
By the way we an upcoming webinar on this topic: Chunking Live workshop Wednesday, August 28th 9am PDT, 12pm EDT, 6pm CEST weaviate.io Online Workshops & Events | Weaviate - Vector Database -Join...
View ArticleGRCP connection failure when processing data-intensive batches
Hi @Nancy_Viviana_Espino ! How are you uploading the vectors? Have you tried changing some config as per the resource planning doc? One option is try using the ASYNX_INDEXING. My guess here is that...
View ArticleGoogle automatic token generation
I was trying to follow the documentation from that link and made changes as I showed in my code earlier, but I could not get it to work. I am using 1.25.10
View Article