Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Rerank-Doc] : Added root level rerank microservices documentation #760

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[Rerank-Doc] : Added root level rerank microservices documentation #760

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
852bd0d
[Rerank-Doc] : Added root level rerank microservices documentation
prerakalw Oct 3, 2024
776e9ce
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Oct 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 39 additions & 0 deletions comps/reranks/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
# ReRank Microservice

## Introduction

Provides functionality for reranking outputs.
It allows for fine-tuning the results based on specific criteria, improving the overall quality and relevance for the user.
Comment on lines +5 to +6
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Might be better to copy some text from one of the uServices like TEI. That nicely describes prioritizing documents.
For example...

Suggested change
Provides functionality for reranking outputs.
It allows for fine-tuning the results based on specific criteria, improving the overall quality and relevance for the user.
Reranking Microservices, are straightforward yet immensely potent tools for semantic search. When provided with a query and a collection of documents, reranking swiftly indexes the documents based on their semantic relevance to the query, arranging them from most to least pertinent. Each microservice significantly enhances overall accuracy. In a text retrieval system, either a dense embedding model or a sparse lexical search index is often employed to retrieve relevant text documents based on the input. However, a reranking model can further refine this process by rearranging potential candidates into a final, optimized order.```


## Key Features
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This key features section would be more helpful if it offered specifics.
As it reads now these sound like platitudes.


- **Configurable Ranking Criteria**: Define custom ranking rules based on various factors like relevance, creativity, style, or user-defined metrics.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sounds like a cool feature but I don't see pointers to where and how I would configure.

- **Multiple Ranking Models**: Integrate with different ranking models, enabling flexibility in selection based on the desired outcome and data type.
- **Real-time Reranking**: Rerank outputs in real-time, ensuring the best possible results are presented to the user with minimal latency.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
- **Real-time Reranking**: Rerank outputs in real-time, ensuring the best possible results are presented to the user with minimal latency.
- **Real-time Reranking**: Rerank documents in real-time, ensuring the best possible results are presented to the user with minimal latency.

Word choice

- **Performance Monitoring**: Monitor the performance of the reranking process, including processing time and effectiveness of applied rules.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Like configurable ranking criteria, this sounds cool but I don't see anything in the uservice readmes about how to do this.

- **Scalability**: Designed to handle large-scale workloads and support increasing volumes of generated outputs.
- **Integration with Other Services**: Seamless integration with other microservices in the application for a smooth data flow and overall processing pipeline.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As above, would benefit from some specifics.


## Additional Notes

- This document provides a high-level overview of the Reranking Microservice.
- For detailed information on configuration, available ranking models, and API documentation, please refer to the dedicated service specifications.
- This microservice can be customized to specific application needs through configuration and integration with external tools.

## Users are able to configure and build reranking-related services according to their actual needs.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In this section it would be helpful to guide people on what each of those microservices does or why you would choose one of them.


### Reranking Microservice with TEI

For details, please refer to [readme](tei/README.md).

### Reranking Microservice with Mosec

For details, please refer to this [readme](mosec/langchain/README.md).

### Reranking Microservice with FastRAG

For details, please refer to this [readme](fastrag/README.md).

### Reranking Microservice with VideoQnA

For details, please refer to this [readme](videoqna/README.md).