jakob.scheid/word-language-detector-ai-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fixed a bug

Browse Source
This commit is contained in:
Jakob Scheid
2026-03-08 00:57:35 +01:00
parent 3d5fa332dc
commit 282ac24869
1 changed files with 9 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+9 -2
View File
@@ -14,8 +14,8 @@ LOCATION=/srv/word-language-detector-ai-api
sudo apt install python3 sudo apt install python3
# install dependencies # install dependencies
python3 -m pip install simple-cache --index-url https://repo.jcloud-services.ddns.net/simple/ python3 -m pip install simple-cache --index-url https://repo.jcloud-services.ddns.net/simple/ --break-system-packages
python3 -m pip install fastapi pydantic tensorflow uvicorn scikit-learn python3 -m pip install fastapi pydantic tensorflow uvicorn scikit-learn --break-system-packages
# set up directories # set up directories
sudo mkdir -p $LOCATION sudo mkdir -p $LOCATION
@@ -28,12 +28,15 @@ sudo rm -f word-language-detector-ai-api_0.1.0_linux-aarch_source.tar.gz
# Optional: download the model # Optional: download the model
# You can leave this part out if you want to provide the model yourself. Notice that the directory has to include following files: 'label_encoder.json' (label encoder), 'language_detector.keras' (the actual model), 'max_len' (token maximum length) and 'tokenizer.json' (tokenizer). It is recommended to download the model as below. # You can leave this part out if you want to provide the model yourself. Notice that the directory has to include following files: 'label_encoder.json' (label encoder), 'language_detector.keras' (the actual model), 'max_len' (token maximum length) and 'tokenizer.json' (tokenizer). It is recommended to download the model as below.
curl -fsSL --retry 3 -o word-language-detector-ai_0.1.0_tf_model_artifacts.tar.gz https://repo.jcloud-services.ddns.net/models/word-language-detector-ai/word-language-detector-ai_0.1.0_tf_model_artifacts.tar.gz curl -fsSL --retry 3 -o word-language-detector-ai_0.1.0_tf_model_artifacts.tar.gz https://repo.jcloud-services.ddns.net/models/word-language-detector-ai/word-language-detector-ai_0.1.0_tf_model_artifacts.tar.gz
sudo mkdir -p $LOCATION/model
sudo tar -xzf word-language-detector-ai_0.1.0_tf_model_artifacts.tar.gz -C $LOCATION/model sudo tar -xzf word-language-detector-ai_0.1.0_tf_model_artifacts.tar.gz -C $LOCATION/model
sudo rm -f word-language-detector-ai_0.1.0_tf_model_artifacts.tar.gz sudo rm -f word-language-detector-ai_0.1.0_tf_model_artifacts.tar.gz
``` ```
Note: Ensure you at least approximately 700 KB of disk space is available. During the installation, approximately 850 KB of disk space must be available. Without the model, you need approximately 400 KB of disk space and approximately 500 MB of disk space during the installation. Note: Ensure you at least approximately 700 KB of disk space is available. During the installation, approximately 850 KB of disk space must be available. Without the model, you need approximately 400 KB of disk space and approximately 500 MB of disk space during the installation.
## Run the API ## Run the API
To run the API, run `src/api.py` in the package directory. Here is an example with `/srv/word-language-detector-ai-api` as the package directory To run the API, run `src/api.py` in the package directory. Here is an example with `/srv/word-language-detector-ai-api` as the package directory
@@ -51,6 +54,10 @@ For the full API documentation, see the docs path of the API.
## Changelog ## Changelog
### Version 0.1.1
- added `--break-system-packages` to `pip install ...`
- bug fix: create model directory before downloading the model
### Version 0.1.0 ### Version 0.1.0
- initial release - initial release
- API for the word language detector AI - API for the word language detector AI