Skip to content

Commit

Permalink
small change of text and logo
Browse files Browse the repository at this point in the history
  • Loading branch information
Formartha committed Feb 28, 2024
1 parent af24ef3 commit 7a08365
Show file tree
Hide file tree
Showing 2 changed files with 14 additions and 7 deletions.
Binary file added .readme/ai1899-cover.jpeg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
21 changes: 14 additions & 7 deletions README.md
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

0 comments on commit 7a08365

Please sign in to comment.