Quantcast
Viewing all articles
Browse latest Browse all 14069

How can I store an ObjectIndex in my file system so I don't need to recreate it every time with LlamaIndex?

Starting off by saying that I'm totally new to this, so super thankful for any help I can get!

I have the following code (from one of the SQL examples from LlamaIndex's website)

engine = create_engine('url')sql_database = SQLDatabase(engine)table_node_mapping = SQLTableNodeMapping(sql_database)index_text = "Some text describing the table"table_schema_objs = []table_schema_objs.append(SQLTableSchema(table_name="table_name", context_str=index_text))index = ObjectIndex.from_objects(  table_schema_objs,  table_node_mapping,  VectorStoreIndex,)

It works perfectly fine, and I can then use the SQLTableRetrieverQueryEngine to query the database and get answers. But I want to be able to create the index once so I can reuse it without recreating it every time.

One of the other examples from the website shows how to store the index to a folder like this

parser = SimpleNodeParser()nodes = parser.get_nodes_from_documents(documents)index = GPTVectorStoreIndex(nodes)index.storage_context.persist(persist_dir="index")

I want to do the same thing but with the index I created with ObjectIndex.from_objects, but I can't seem to figure out how.

I can of course create another type of index, but from the other examples it seemed like they used text to input to create the index from and not objects.


Viewing all articles
Browse latest Browse all 14069

Trending Articles



<script src="https://jsc.adskeeper.com/r/s/rssing.com.1596347.js" async> </script>