Update Embeddings.ipynb to show output_dimenstionality parameter.
#82
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
…onality to 10 for simpler print statement
| @@ -35,18 +35,34 @@ | |||
| }, | |||
There was a problem hiding this comment.
Line #12. output_dimensionality=10)
It sounds like this change is to add this parameter but it's hidden in this code snippet comparing task types without explanation.
Maybe add a section after this block with a short note? e.g.:
## Truncating embeddings The text-embedding-004 model also supports lower embedding dimensions. Specify output_dimensionality to truncate the output. ` result1 = genai.embed_content( model="models/text-embedding-004", content="Hello world) result2 = genai.embed_content( model="models/text-embedding-004", content="Hello world", output_dimensionality=10) (len(result1), len(result2)) `
Can we talk about the relationship between the index and specificity? It'd be great to add a statement like "When using text-embedding-004, each dimension adds diminishing value so truncating may be effective in constrained environments ." - but I haven't verified if this is true.
Reply via ReviewNB
There was a problem hiding this comment.
@markmcd I haven't verified it either but I think it would be a great add! @MarkDaoust what do you think?
| @@ -35,18 +35,34 @@ | |||
| }, | |||
There was a problem hiding this comment.
There was a problem hiding this comment.
(That way you wouldn't need the '... trimmed')
|
Thanks for the updates! I made a couple quick changes and committed an updated version of this notebook for an event today. (Sorry if that makes this PR out of sync, working quickly from a coffee shop), we can iterate and refine from there. |
No description provided.