Refactor Dockerfile and requirements.txt; update model paths in config.py

Dockerfile

@@ -10,6 +10,8 @@ RUN apt-get update && apt-get install -y \
 
 COPY requirements.txt ./
 COPY src/ ./src/
+COPY input/ ./input/
+COPY models/ ./models/
 
 RUN pip3 install -r requirements.txt
 
@@ -17,4 +19,6 @@ EXPOSE 8501
 
 HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
 
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+ENV PYTHONPATH="/app/src:${PYTHONPATH}"
+
+ENTRYPOINT ["streamlit", "run", "src/demo.py", "--server.port=8501", "--server.address=0.0.0.0"]

requirements.txt

@@ -1,3 +1,11 @@
-altair
+pydantic
+pydantic-settings
+networkx
+numpy
 pandas
-streamlit
+streamlit
+st-link-analysis
+torch
+tqdm
+transformers
+torch-geometric

src/config.py

@@ -2,13 +2,13 @@ from pydantic_settings import BaseSettings
 
 
 class Config(BaseSettings):
-    EMBEDDING_MODEL_PATH: str = r"C:\Users\pc\Desktop\Projects\Masters\data_mining\semantic_knowledge_graph\demo\models\embedding\gte-multilingual-base"
-    TRAINING_DATA_PATH: str = r"C:\Users\pc\Desktop\Projects\Masters\data_mining\semantic_knowledge_graph\demo\input\train_data_with_embeddings.parquet"
+    EMBEDDING_MODEL_PATH: str = "/models/embedding/gte-multilingual-base"
+    TRAINING_DATA_PATH: str = "input/train_data_with_embeddings.parquet"
 
-    GNN_MODEL_PATH: str = r"C:\Users\pc\Desktop\Projects\Masters\data_mining\semantic_knowledge_graph\demo\models\undirected_gnn\gnn_classifier_model.pth"
-    GNN_GRAPH_DATA_PATH: str = r"C:\Users\pc\Desktop\Projects\Masters\data_mining\semantic_knowledge_graph\demo\models\undirected_gnn\gnn_graph_data.pt"
-    LABEL_MAPPING_PATH: str = r"C:\Users\pc\Desktop\Projects\Masters\data_mining\semantic_knowledge_graph\demo\models\undirected_gnn\label_mapping.pt"
-    TITLE_TO_ID_PATH: str = r"C:\Users\pc\Desktop\Projects\Masters\data_mining\semantic_knowledge_graph\demo\models\undirected_gnn\title_to_id.pt"
+    GNN_MODEL_PATH: str = "models/undirected_gnn/gnn_classifier_model.pth"
+    GNN_GRAPH_DATA_PATH: str = "models/undirected_gnn/gnn_graph_data.pt"
+    LABEL_MAPPING_PATH: str = "models/undirected_gnn/label_mapping.pt"
+    TITLE_TO_ID_PATH: str = "models/undirected_gnn/title_to_id.pt"
 
     ICON_MAPPING: dict[str, str] = {
         'Africa': 'language',