Hello , I am trying to built RAG pipeline and i am a new commer in this field.
My setup is like two containers one for vector store and one for querying from the data. I am using llama3 embedding model from my machine locally.
I am facing isuue that embeddings are created but they are not added to the database and so i cannot query them, i am using client method to do it. The script runs without error but while accessing the data base there are no embeddings. Any suggestion or guidance will be helpful.
Thank you !
hi @Mit_Patel !!
Welcome to our community 
If I understood it correctly, you are vectorizing the data yourself, and inserting the vector alongside your object.
If that’s the case, this is what we call “Bring your own vectors”.
The other option is to let Weaviate vectorize it for you. On that case you need to set up the collection properly with the vectorizer you want.
Can you share the code snippet where you ingest the data?
That will allow to troubleshoot it better.
THanks!