aws-amplify / aws-amplify/docs

Feature Request: Vector search within documentation

Open
#6,881 1 comment 0 reactions 0 assignees View on GitHub
amplify/docs-engineering feature-request
Dominant language
MDX
Stars
506
Forks
1.1k
Avg merge
3h 14m
Merged PRs (30d)
1

Description

**Is your feature request related to a problem? Please describe.**
Poor results with Q related to Amplify.

**Describe the solution you'd like**
A vectorized documentation that allows simple retrieval of similar chunks of content within specific documentations, e.g. AWS Amplify V6.

**Describe alternatives you've considered**
The introduction of Q has been nice, but searching through other people's niche problems seems to retrieve unrelated results and recommend unrelated solutions quite often. Especially when encountering issues with less popular services like Amplify, compared to Lambda or DynamoDB.

**Additional context**
I have implemented a RAG chatbot for my employer by constructing an automatic workflow that scrapes the website every so often, checks if the text has been updated (or look at metadata if it exists), and re-chunks the text, and re-vectorizes the chunks. I have combined this with a simple LLM for customers to chat to.
I feel like communicating directly to the documentation rather than random people's niche problems and random people's solutions would be more helpful and relevant.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.