AnswerDotAI / AnswerDotAI/RAGatouille
Feature Request : Please include server search code from official Colbert repository into this repository for production usages.
- Dominant language
- Python
- Stars
- 4k
- Forks
- 276
- PR merge metrics
- No merged PRs in 30d
Description
> The [official ColBERT implementation](https://github.com/stanford-futuredata/ColBERT) has a built-in query server (using Flask), which you can easily query via API requests and does support indexes generated with RAGatouille! This should be enough for most small applications, so long as you can persist the index on disk.
For now, I have followed the above advice to solve my problem. But I think this repository should become defacto repo
for serving and searching needs for Colbert. This would allow users to integrate such a server into third party search solutions like typesense and so on.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing the built-in Flask query server in the official ColBERT repository and how it loads persisted indexes generated by RAGatouille. Determine the integration scope and API surface needed here; done should mean users can run a production-oriented server, query it through API requests, and search indexes persisted on disk.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- flask, python
- Domain
- api, backend, search
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100