[HN Gopher] Show HN: GitHub-assistant - Natural language questio...
       ___________________________________________________________________
        
       Show HN: GitHub-assistant - Natural language questions from your
       GitHub data
        
       Simon(sfarshid) and I spend a lot of time on GitHub. As data nerds
       we put together a quick tool to explore your repository's data.
       How it works:  - Data Loading: We use dlt to pull data (issues,
       PRs, commits, stars) from GitHub  - Semantic Layer: Relta wraps the
       underlying dataset into a semantic layer so the LLM doesn't
       hallucinate.  - Text-to-SQL: A text-to-SQL agent transforms your
       plain-English question into a query using the semantic layer  -
       Generative Charts: assistant-ui dynamically generates a chart based
       on the SQL query  - Refinements: If the semantic layer can't handle
       your question, our agent submits semantic layer improvements via
       pull requests  Hosted version: https://github-assistant.com  Demo
       Video: https://youtu.be/ATaf98nID5c  Check out the repo + hosted
       version and let us know what you think.
        
       Author : aazo11
       Score  : 44 points
       Date   : 2024-12-22 00:41 UTC (22 hours ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | croemer wrote:
       | 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!
        
         | sfarshid wrote:
         | Just updated the README, thanks for the suggestion!
        
         | aazo11 wrote:
         | 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.
        
         | aazo11 wrote:
         | Was able to reproduce and pushed an update. Thanks for calling
         | this out.
        
       | bberenberg wrote:
       | Pretty nifty, is Relta going to be OSS as well?
        
         | aazo11 wrote:
         | 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:
           | 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] - https://popsia.com
        
       | diggan wrote:
       | 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:
         | Same thoughts
        
           | aazo11 wrote:
           | 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 https://medium.com/relta/github-
           | assistant-49ae388ad758
        
             | aazo11 wrote:
             | There will new data from the graphql API added over time.
             | Would love your feedback on which data you like to see
             | added https://docs.github.com/en/graphql
        
               | diggan wrote:
               | 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:
               | 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.
        
       | eddywebs wrote:
       | Can this help in explaining how the code works, its schematics or
       | HLD of a given github repo ?
        
         | aazo11 wrote:
         | No this currently only answers questions from the GitHub
         | graphql API.
        
       ___________________________________________________________________
       (page generated 2024-12-22 23:02 UTC)