feat(inference): add tutorial how to implement RAG with managed infer… #3744
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
the
status: draft
Laure-di
force-pushed
the
int-add-inference
branch
2 times, most recently
from
255e7ec
to
752d1a8
Compare
Laure-di
force-pushed
the
int-add-inference
branch
2 times, most recently
from
4328de4
to
6ba5ea2
Compare
Laure-di
force-pushed
the
int-add-inference
branch
4 times, most recently
from
73c7b8c
to
003a3b6
Compare
Laure-di
force-pushed
the
int-add-inference
branch
6 times, most recently
from
66e5b1c
to
3609f75
Compare
Laure-di
force-pushed
the
int-add-inference
branch
from
3609f75
to
d9f4ef2
Compare
tgenaitay
reviewed
Sep 26, 2024
There was a problem hiding this comment.
Thanks for the first version!
Thoughts
- I couldn't follow as it was unclear where each piece of code should go. I mean, past the .env file, I'm left with python snippets all around. Perhaps we can split into what's setup, and what goes into a python file.
- I believe some of the .env variables are not used.
- I believe we are not using the scaleway sdk and wonder why invoking it
- The tutorial is around langchain, so I think its key components should be introduced (watch out I believe one is deprecated already)
- Overall to be very practical it would be ideal in the end to have a functioning RAG. The critical thing I'm missing is perhaps a fileset I can really import so that I get a "wow" effect in last chapter. Without this element, I wouldn't reach the goal you have set as "What are the commands to set up XX with the CLI of Scaleway?"
Laure-di
force-pushed
the
int-add-inference
branch
4 times, most recently
from
abc4837
to
53c2aa9
Compare
Co-authored-by: ldecarvalho-doc <[email protected]>
Co-authored-by: ldecarvalho-doc <[email protected]>
Co-authored-by: ldecarvalho-doc <[email protected]>
Co-authored-by: ldecarvalho-doc <[email protected]>
Co-authored-by: ldecarvalho-doc <[email protected]>
Laure-di
force-pushed
the
int-add-inference
branch
6 times, most recently
from
fcfcb0c
to
709786d
Compare
Laure-di
force-pushed
the
int-add-inference
branch
from
709786d
to
403fd5e
Compare
remyleone
reviewed
Oct 4, 2024
Laure-di
force-pushed
the
int-add-inference
branch
from
cd3be0e
to
e944486
Compare
Laure-di
force-pushed
the
int-add-inference
branch
from
e944486
to
69c9974
Compare
bene2k1
reviewed
Oct 4, 2024
Co-authored-by: Benedikt Rollik <[email protected]>
Co-authored-by: Benedikt Rollik <[email protected]>
github-actions
bot
removed
the
status: draft
bene2k1
approved these changes
Oct 4, 2024
RoRoJ
approved these changes
Oct 4, 2024
Co-authored-by: Rowena Jones <[email protected]>
bene2k1
reviewed
Oct 4, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
A tutorial for inference to.known: how to implement Retrieval-Augmented Generation (RAG) using Scaleway's managed inference, PostgreSQL, pgvector, and object storage.