Find answers from the community

Updated 2 years ago

Versioning

Good morning, everyone. I wanted to share that I've come across some issues with my code this morning. Specifically, I've noticed that GPTSimpleVectorIndex is no longer available and needs to be changed to GPTVectorStoreIndex. Additionally, the way to store and retrieve data has changed, and I need to use the following code: storage_context = StorageContext.from_defaults(persist_dir="./storage"), followed by index = load_index_from_storage(storage_context).

I also noticed that there are now three json files that are created, rather than just one that I can name myself. Unfortunately, I'm still having trouble with my first index.query. Is there a way for me to revert back to an older version of llama_index? Additionally, would someone be able to point me in the direction of documentation that outlines the differences and changes needed in the code? Thank you!

is there anyway i can un-install the latest llama_index and revert back to old version, which is supporting GPTSimpleVectorIndex well ?
L
2 comments
You can specify the version to install, like this, to avoid the new changes pip install llama-index==0.5.27
I would take a read through the docs to see what changed https://gpt-index.readthedocs.io/en/latest/guides/primer/usage_pattern.html

You can name the folder that saves the jsons in the newest version. I think even multiple indexes can share the same folder, but I need to try that out myself still
Add a reply
Sign up and join the conversation on Discord