_______ __ _______
| | |.---.-..----.| |--..-----..----. | | |.-----..--.--.--..-----.
| || _ || __|| < | -__|| _| | || -__|| | | ||__ --|
|___|___||___._||____||__|__||_____||__| |__|____||_____||________||_____|
on Gopher (inofficial)
URI Visit Hacker News on the Web
COMMENT PAGE FOR:
URI Show HN: GitHub-assistant â Natural language questions from your GitHub data
eddywebs wrote 22 hours 53 min ago:
Can this help in explaining how the code works, its schematics or HLD
of a given github repo ?
aazo11 wrote 21 hours 29 min ago:
No this currently only answers questions from the GitHub graphql API.
diggan wrote 23 hours 32 min ago:
Is there any information you can get out of this that isn't already
available in the GitHub.com UI? I tried asking things like "What could
the most interesting information you can tell me about this
repository?" but it seems like most of the data is already available in
the UI in pretty much the same format, except you click a link to see
it instead of writing a question and waiting for a reply.
eddywebs wrote 22 hours 53 min ago:
Same thoughts
aazo11 wrote 21 hours 30 min ago:
We pull data from the GitHub API which includes data that that is
not available from GitHub.com pages. Currently only PR, Issues,
Commit and Star data is being loaded. You can also read more here
URI [1]: https://medium.com/relta/github-assistant-49ae388ad758
aazo11 wrote 21 hours 17 min ago:
There will new data from the graphql API added over time. Would
love your feedback on which data you like to see added
URI [1]: https://docs.github.com/en/graphql
diggan wrote 17 hours 18 min ago:
Maybe a better question: What questions could be answered with
your service, that could not be answered with just cURL + Git +
the GitHub API?
aazo11 wrote 14 hours 57 min ago:
Great question! The purpose of github-assistant is to
showcase the technologies that make it easy to build a
tool/feature like this, not necessarily for it to be a
stand-alone service. With dlt/Relta/LangGraph/assistant-ui we
spin this up in about 10 days. For example:
- The GitHub graphql API limits to 100 items to be queried at
a time and has pretty opaque secondary rate limits. Building
this with cURL would take effort. dlt handles all this
complexity to set up a robust pipeline by providing a
connector to the GitHub API.
- Creating semantic layers manually from a relational dataset
and leveraging it in a text-to-sql pipeline to prevent
hallucinations (similar to those we highlighted in our Medium
post) would take lots of manual effort, which Relta
streamlines.
- Creating a chat front-end with charts was made easy by
assistant-ui
Hope this makes sense.
bberenberg wrote 1 day ago:
Pretty nifty, is Relta going to be OSS as well?
aazo11 wrote 16 hours 59 min ago:
Yes in the future. We share the source code in both commercial and
non-commercial engagements already. Drop me a line at amir [at]
relta.dev if interested.
bberenberg wrote 16 hours 44 min ago:
I am building an AI Slack Moderator bot [0] as a side project. I
was thinking that this could be a cool intermediate layer to allow
a user to ask questions about moderation logs. However I am not
ready to build this for now. Feel free to add me to an email list
for people who want to know when you OSS it down the line.
[0] -
URI [1]: https://popsia.com
croemer wrote 1 day ago:
Tried adding a repo I work on, import worked after failing first, but
then the query result was that there was no data on top contributors.
Put the video in the Readme!
aazo11 wrote 1 day ago:
Was able to reproduce and pushed an update. Thanks for calling this
out.
aazo11 wrote 1 day ago:
Hi -- strange that didn't work. Overall, the semantic layer is
designed to provide very tight guardrails and not hallucinate. You
can see the agent suggest changes to the semantic layer if you give
the produced answer a thumbs down.
The idea is for the system to provide answers that have close to 100%
accuracy, but make it a single click for developers to to improve the
semantic layer.
sfarshid wrote 1 day ago:
Just updated the README, thanks for the suggestion!
DIR <- back to front page