What is the difference between querying the index and querying the Docs object directly? Why do I need a Docs() object? #906
Unanswered
Smogglethorp-T-Hendlesworthington
asked this question in
Q&A
Replies: 1 comment
-
Querying the index and querying the
In summary, use the index for fast, efficient querying when you have a pre-built index and need quick answers. Use the To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
One can do something like:
This whole process takes maybe two minutes for about 25 papers.
On the other hand, we can build a
Docs
object usingDocs.add("/path/to/pdf")
. The process takes much longer, and also seems to come with a lot more data (e.g., thedocs
andtext
objects for each paper), but runningdocs.query(...)
doesn't seem to give a different answer, or any faster.What's the real difference between these two things and why would I use one over the other? The documentation talks about caching embeddings (saving the
docs
andtext
objects for later manual addition into aDocs()
object), but why would I do this over just saving the built-index and querying that?Beta Was this translation helpful? Give feedback.
All reactions