Clik here to view.
Problem with near_text Query and Metadata Filtering in Weaviate
hi @lisascat !! Welcome to our community I was not able to reproduce this. Here is some code so we can share: client.collections.delete("Test") collection = client.collections.create( "Test",...
View ArticleClik here to view.
Problem with near_text Query and Metadata Filtering in Weaviate
note that if you have an ID for you objects, you can use it, like explained here: weaviate.io Create objects | Weaviate The examples on this page demonstrate how to create individual objects in...
View ArticleEmbeded weaviate with objects stuck at 20; connect_to_local shows thousands...
Ok, can you share some code I can reproduce this? If possible, separated from the project. Weaviate current version is 1.27.2, if you are running with Embedded, you can specify a version there. Let me...
View ArticleEmbeded weaviate with objects stuck at 20; connect_to_local shows thousands...
I shared entire project. Code in calling create are the same for embedded and use_local_connection. import os import sys import weaviate from weaviate import WeaviateClient from weaviate.classes.init...
View ArticleFilter index breaks after updating/inserting new records
For anybody finding this in the future, the fix is included in v1.27.3, v1.26.10, and v1.25.25
View ArticleLocally running RAG pipeline with Verba and Llama3 with Ollama
Oh, nice! Thanks for sharing! I have also noticed ollama performing better when running directly on host instead of docker. For one dataset it was importing in host, but not on docker. I run mac,...
View ArticleEmbeded weaviate with objects stuck at 20; connect_to_local shows thousands...
The code is not formatted. I was not able to run it. Can you for example create a google collab? One thing I noticed, is that you seem to be instantiating two embedded, use_async_with_embedded and...
View ArticleEmbeded weaviate with objects stuck at 20; connect_to_local shows thousands...
The code for aysnc is commented out. I’ll try to create a google collab . thanks
View ArticleEmbeded weaviate with objects stuck at 20; connect_to_local shows thousands...
will try 1.27.3 as well. thanks
View ArticleProblem with near_text Query and Metadata Filtering in Weaviate
Hello @DudaNogueira thank you for your response! The insertion worked, and the search is also functioning correctly. What I don’t understand is why, when using: batch_size = 100 # Batch size for i in...
View ArticleProblem with near_text Query and Metadata Filtering in Weaviate
Oh, I see. When you use WeaviateVectorStore.from_documents the framework (not sure what are you using, llamaindex or langchain) will embed it for you following it’s own login. This means it will...
View ArticleEmbeded weaviate with objects stuck at 20; connect_to_local shows thousands...
Here is the log; shows first file has 18 chucks loaded; 2nd has 10. When final counts the object, it shows 20 2024-11-13 16:32:09,935 - INFO - === file_path:...
View ArticleClik here to view.
Embeded weaviate with objects stuck at 20; connect_to_local shows thousands...
here is same code, by switching to local connection; the counts of object is 25 iner fastapi_onazure-t2v-transformers-1 Started 0.2s Container fastapi_onazure-contextionary-1 Started 0.2s Container...
View ArticleProblem with near_text Query and Metadata Filtering in Weaviate
Hi @DudaNogueira! Thanks again for your previous help. The solution you suggested worked perfectly, and I was able to resolve the initial issue. However, I encountered other challenges as I adapted...
View ArticleVectorization failed for some batches: 500, message='Internal Server Error'
Idk where to see the logs. I googled it and it says look in the tray. The only option I have is to quit ollama. I’m still searching for the logs.
View ArticleClik here to view.
Couldn't connect to Weaviate, check your URL/API KEY: [Errno 30] Read-only...
Thank you very much for your help. I have successfully used cloud weaviate, and now I want to deploy Embedded Weaviate locally, but I don’t seem to see the command for downloading in Embedded Weaviate...
View ArticleClik here to view.
Embeded weaviate with objects stuck at 20; connect_to_local shows thousands...
cw257900: 2024-11-13 16:43:36,276 - INFO - HTTP Request: GET http://localhost:8080/v1/schema/PDF_COLLECTION “HTTP/1.1 404 Not Found” 2024-11-13 16:43:36,279 - INFO - HTTP Request: GET...
View ArticleClik here to view.
Problem with near_text Query and Metadata Filtering in Weaviate
Hi! Great! Glad to hear we are making progress Now, you need to understand that in your scenario, Weaviate will have two indices: 1 - A Named Vector called transcription_vector 2 - An inverted index...
View ArticleClik here to view.
Problem with near_text Query and Metadata Filtering in Weaviate
If you want to learn more on tokenization: weaviate.io Overview of tokenization | Weaviate Tokenization is the process of breaking text into smaller units, called tokens. This is an important step...
View ArticleVectorization failed for some batches: 500, message='Internal Server Error'
In Mac (and probably linux too) it is here: tail -n 100 ~/.ollama/logs/server.log
View Article