Find answers from the community

Updated last month

Without seeing a specific error output,

Without seeing a specific error output, it's difficult to answer your question.

6 comments

Yeah, it's

AttributeError: type object 'KnowledgeGraphIndex' has no attribute 'from_vector_store'

But I think, KnowledgeGraphIndex won't have from_vector_store, Because the from_vector_store function is only for Vector DB. So it will not be ready for Graph DB

bbin4ry_d3struct0r

Plain Text

from llama_index.core import KnowledgeGraphIndex

kg_index = KnowledgeGraphIndex.from_documents(
    documents,
    storage_context=storage_context,
    max_triplets_per_chunk=10,
    space_name=space_name,
    edge_types=edge_types,
    rel_prop_names=rel_prop_names,
    tags=tags,
    include_embeddings=True,
)

bbin4ry_d3struct0r

https://docs.llamaindex.ai/en/stable/examples/query_engine/knowledge_graph_query_engine.html

bbin4ry_d3struct0r

This is the template for the v.10 update.

MMicrovn

This will likely require re-indexing the data. Because it is indexed from "documents". I don't want to re-index, just simply query into GraphDB and inference

It was called ".from_document()" function

MMicrovn

I want to query the database without having to re-insert it into Nebula (GraphDB which I am using). Can someone help me?

Add a reply