Replies: 1 comment
-
Hi @systemz64! I'm Dosu and I’m helping the llama_index team. Currently, there is no documented way to enforce that your custom index names (like "tree_index" and "vector_index") are used as the top-level keys in the The Workarounds:
Summary: If you need more details on how to implement such a lookup or want to see example code, let me know! To reply, just mention my name @dosu. How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi
I have test application where I am generating both a tree index and a vector index. I am naming these specifically as follows:
_` tree_index = TreeIndex(
nodes,
storage_context=storage_context,
index_id="tree_index",
show_progress=True # Shows a progress bar during ingestion
)
#tree_index.index_id = "tree_index"
logger.info("Tree Index created/updated in ChromaDB.")
Right now I am using ChromaDB and SimpleIndexStore to test. The index_store.json file shows this:
{"index_store/data": {"3078825e-2aad-47c9-baa1-fdd22c8e8071": {"type": "tree", "data": "{"index_id": "
There does not seem to be a way get the store to use the name I have provided which makes loading the index really hard.
Would anyone have a suggestion around this?
Thx
Beta Was this translation helpful? Give feedback.
All reactions