-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
3563fd4
commit 9e9373f
Showing
1 changed file
with
23 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,23 @@ | ||
# mKB - mimik Knowledge Base Microservice | ||
mKB is a microservice designed for performing semantic searches on datasets. These datasets are pre-processed, chunked, and indexed by creating vector representations (embeddings) of the documents using the mimik dataset-cli tool. | ||
|
||
## Features | ||
|
||
### Dataset Management | ||
|
||
- Create Datasets: Upload pre-processed JSON datasets to the Knowledge Base. | ||
- List Datasets: Retrieve a list of all available datasets. | ||
- Delete Datasets: Remove datasets by their name. | ||
- Upload Chunks: Add specific chunks to an existing dataset using a pre-processed file. | ||
|
||
### Search and Retrieval | ||
|
||
- Similarity Search: Perform searches across datasets based on a prompt, returning the most relevant content. | ||
- Chunk Retrieval: Retrieve individual chunks by their chunkId for detailed inspection. | ||
|
||
## Installation Guide | ||
|
||
1. Download the latest .zip file for the most recent release [HERE](https://github.com/edgeMicroservice/mKB/releases). | ||
2. Unzip the package. | ||
3. Locate the unzipped .tar file; this is the artifact needed for the edge microservice deployment. | ||
4. If you are deploying the edge microservice for the first time, please follow the [edge microservice deployment quick start guide](https://devdocs.mimik.com/tutorials/01-index). |