-
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
Showing
2 changed files
with
14 additions
and
7 deletions.
There are no files selected for viewing
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
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 |
---|---|---|
@@ -1,19 +1,26 @@ | ||
<img src=".readme/ai1899-cover.jpeg" alt="ai1899 cover" width="220"> | ||
|
||
What? | ||
------ | ||
this project intended for whoever wants to use humanized queries to select test cases. | ||
The idea is to have a test and it's description and test steps, then a system or initiator could query it. | ||
ai1899 is a project designed for anyone seeking to utilize humanized queries for selecting test cases efficiently. | ||
Leveraging Sentence Transformers, Flask, and QDRANT, this project facilitates the creation of vectors from test case descriptions. | ||
Consequently, users can query the system via Flask APIs to retrieve test cases that match specific criteria. | ||
|
||
The project employs models that can be selected and downloaded offline from Hugging Face's repository: https://huggingface.co. | ||
During development, the primary model utilized was msmarco-distilbert-base-tas-b, accessible here: https://huggingface.co/sentence-transformers/msmarco-distilbert-base-tas-b | ||
|
||
How to run? | ||
---------- | ||
to improve performance and reduce footprint, the idea is to have the model loaded on a shared volume using: | ||
download_model.py. After running it, please provide proper path to the docker-compose.yaml file. | ||
To enhance performance and minimize footprint, | ||
the recommended approach is to load the model onto a shared volume using download_model.py, however, | ||
You can use upsert api to ingest the vectors. | ||
|
||
To start the stack | ||
-------------------- | ||
To initiate the stack, execute the following command: | ||
----------------------------------------------------- | ||
DEVICE=/path/to/downloaded/model LM_MODEL=model-name docker compose up -d | ||
|
||
Troubleshoot | ||
------------ | ||
There is a known issue to install docker-compose on Mx processors (Mac), to fix it you should. | ||
1. pip3 install "cython<3.0.0" wheel && pip3 install pyyaml==5.4.1 --no-build-isolation | ||
2. pip3 install docker-compose | ||
2. pip3 install docker-compose |