Find answers from the community

Home
Members
jjmachan
j
jjmachan
Offline, last seen 3 months ago
Joined September 25, 2024
This is because from what I understand Nodes are the ones that are the smallest units, which can be indexed. I'm aware that you can index a document too with Document(text, embedding=embs) but this seems like duplication.
6 comments
j
L
I'm facing an issue when using callbacks in an async setting. Bascially the outputs are mixed up. I'm not sure if I'm using the callbacks correctly in this case...
5 comments
j
L
seems like aquery() does not work as expected. I've mentioned more here https://github.com/jerryjliu/llama_index/issues/6463
4 comments
j
L
where can I get an example of how to use llamaindex with async=True? searched the docs but didn't find any examples there...

edit
got something here https://github.com/jerryjliu/llama_index/blob/main/examples/async/AsyncGPTTreeIndexDemo.ipynb
1 comment
L
any idea which tool @jerryjliu0 used to create these diagrams 😅
2 comments
j
j
I think its used for embeddings. can you try and change that too in the service context? From the codebase I think LlamaIndex doesnot use weaviate to compute the embeddings, it only uses the vector store to store the text and embeddings and compute similarity.
Does weaviate have capabilities to compute embeddings?
1 comment
L
I've been trying out updating and deleting documents from the index but seems like that is an issue?
Plain Text
doc = Document(text=txt)
simple_index.insert(doc)

but this uses the nodeparser to break the doc down. Now if I want to do update/delete, the original doc, it seems I can't because the docstore has only nodes but I have only document objects.

Plain Text
# update
doc.text = "how to make wealth = build a startup"
simple_index.update(doc) # fails silently because delete fails (this works by deleting and inserting)

# delete
index.delete(doc.doc_id) # fails silently 
len(simple_index.docstore.docs)
11 comments
j
j
L