How to Use Supabase VectorStore for Document Processing...

At a glance

The community member is seeking help on how to use Supabase VectorStore to process documents and use the vector store to answer questions. They previously created table embeddings and used SQL similarity search within Supabase. The community members discuss the collection_name parameter and whether it refers to the embedding table. They also reference the Supabase VectorStore documentation and source code, but there is no explicitly marked answer.

Useful resources

mmahdicodex999

hello devs, a bit lost with how to use Supabase VectorStore, i need to process the document once in the Upload, and then use the vector store to answer the questions. most of the examples didn't explain how can be done.
before i was creating table embeddings, and save the embedded document inside it and use sql similarity search inside Supabase.

5 comments

LLogan M

Is something missing from these docs? https://docs.llamaindex.ai/en/stable/examples/vector_stores/SupabaseVectorIndexDemo/

mmahdicodex999

@Logan M what is collection_name? is it the embedding table i have which is look like this:

Plain Text

CREATE TABLE book_embeddings (
    id UUID DEFAULT uuid_generate_v4() PRIMARY KEY, 
    title TEXT NOT NULL,                           
    author TEXT,                                   
    content TEXT,                                  
    embedding VECTOR(1536),                        
    metadata JSONB,                                
    created_at TIMESTAMP DEFAULT NOW()             
);

now all i need is to put the name of my table in collection_name ~?

Plain Text

vector_store = 
SupabaseVectorStore(
    postgres_connection_string=(
        "postgresql://:@:/"
    ),
    collection_name="book_empeddings",
)
storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context
)

i am confused because even i write any other name in collection_name it still will work 😵‍💫

LLogan M

The vecs client needs a collection name?

Maybe reading the source code here would help?
https://github.com/run-llama/llama_index/blob/850d6467764f5842029573e056b226967be09e69/llama-index-integrations/vector_stores/llama-index-vector-stores-supabase/llama_index/vector_stores/supabase/base.py#L74

LLogan M

I never use supabase, so all i can do is reference the notebook and code here lol

mmahdicodex999

thank u logan yeah thats help a lot

Add a reply

Find answers from the community

How to Use Supabase VectorStore for Document Processing and Question Answering