Find answers from the community

Updated 5 months ago

Embeddings

At a glance
Is there any way I can see the embedding contents ?
L
K
12 comments
Embeddings are in chroma. Would have to use chromas api to fetch them I think
While started the index as a query engine loaded from the vector store, I could see it computing embeddings for all the documents via Llama debugger trace. Is it that while it runs the query it computes the embeddings for the documents rather than at index creation time ?
I'm not sure what you mean exactly. Maybe you can give a code sample for what you run

At query time, your query text does need to be embedded.
I wanted to know that when I create an index with documents , does it creates embedding at the time or when I initiate the query engine, it does at runtime. This is for the text that is present in the nodes/chunks
As shown in the code, while creating the query engine, its adds embedding for the existing IDs which was created earlier
Attachment
Screenshot_2023-12-06_at_10.54.51_PM.png
Attachment
Screenshot_2023-12-06_at_10.57.01_PM.png
Please let me know if you still didn't get the question ?
I'm not sure where those logs are coming from, BUT in the first screenshot, no embeddings are called or created, except for one embedding for the query text.
Like, I know this with 100% certainty
My guess is this is just logs from chroma loading the index
Yes, this is exactly what I guessed as well since it is shown in the second screenshot that the node embeddings are created while creating the index. Thanks for the clarification, I will play around with chroma API to find where these embeddings are stored !
Add a reply
Sign up and join the conversation on Discord