Stratechery RAG demo #7
Open
+3,187
−894
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
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
markbackman
force-pushed
the
mb/rag-function-calling
branch
from
cead6ba
to
771db92
Compare
markbackman
force-pushed
the
mb/rag-function-calling
branch
from
f1404b3
to
1cb49b9
Compare
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Outdated suggestions cannot be applied.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.
RAG demo that uses Stratechery articles as a data source. Some highlights about the implementation:
text-embedding-3-smallis used for embeddingsThe demo indexes the title and published date and the system prompt gets the current date at run time, which allows you to ask questions like: "what was your last article?" or "tell me about what Apple has been up to this year".
The UI contains a drawer that shows you the RAG performance (query time, response time, total RAG time), token utilization (current RAG query and cumulative), and links to the source articles.
Lastly, I've updated the waveform to provide a little more friendly animation during the wait time.