sixth commit

dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.11-slim
+
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    gcc \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir --upgrade pip \
+    && pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8080
+
+CMD ["gunicorn", "-b", "0.0.0.0:8080", "app:app"]

question_api/trainning_bgnn.py

@@ -1,90 +0,0 @@
-import torch
-import torch.nn.functional as F
-from torch_geometric.nn import GCNConv
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.model_selection import train_test_split
-import json
-import pickle
-import os
-import re
-import string
-
-# Clean text function
-def clean_text(text):
-    text = text.lower()
-    text = re.sub(r'\[.*?\]', '', text)
-    text = re.sub(r'https?://\S+|www\.\S+', '', text)
-    text = re.sub(r'<.*?>+', '', text)
-    text = re.sub(f'[{re.escape(string.punctuation)}]', '', text)
-    text = re.sub(r'\n', ' ', text)
-    text = re.sub(r'\w*\d\w*', '', text)
-    text = re.sub(' +', ' ', text)
-    return text.strip()
-
-# BiGNN model
-class BiGNN(torch.nn.Module):
-    def __init__(self, input_dim, hidden_dim, output_dim):
-        super(BiGNN, self).__init__()
-        self.conv1 = GCNConv(input_dim, hidden_dim)
-        self.conv2 = GCNConv(hidden_dim, output_dim)
-
-    def forward(self, data):
-        x, edge_index = data.x, data.edge_index
-        x = F.relu(self.conv1(x, edge_index))
-        x = F.dropout(x, training=self.training)
-        x = self.conv2(x, edge_index)
-        return F.log_softmax(x, dim=1)
-
-# Load data
-with open("question_api/bgnn_training_dataset.json", "r", encoding="utf-8") as f:
-    data = json.load(f)
-
-sentences = [clean_text(d["sentence"]) for d in data]
-labels = [d["label"] for d in data]
-
-# Vectorize
-vectorizer = TfidfVectorizer()
-X = vectorizer.fit_transform(sentences).toarray()
-y = torch.tensor(labels)
-
-# Build edge index (fake graph: each node is connected to itself)
-edge_index = torch.tensor([[i for i in range(len(X))], [i for i in range(len(X))]], dtype=torch.long)
-
-# Train/Test Split
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-
-# Convert to tensor
-X_train = torch.tensor(X_train, dtype=torch.float32)
-X_test = torch.tensor(X_test, dtype=torch.float32)
-
-# Create dummy PyG data objects
-train_data = type('Data', (object,), {})()
-train_data.x = X_train
-train_data.edge_index = edge_index[:, :X_train.shape[0]]
-
-test_data = type('Data', (object,), {})()
-test_data.x = X_test
-test_data.edge_index = edge_index[:, :X_test.shape[0]]
-
-# Train model
-model = BiGNN(input_dim=X.shape[1], hidden_dim=16, output_dim=3)
-optimizer = torch.optim.Adam(model.parameters(), lr=0.01)
-epochs = 50
-
-for epoch in range(epochs):
-    model.train()
-    optimizer.zero_grad()
-    out = model(train_data)
-    loss = F.nll_loss(out, y_train)
-    loss.backward()
-    optimizer.step()
-    print(f"Epoch {epoch+1}/{epochs}, Loss: {loss.item():.4f}")
-
-# Save model and vectorizer
-os.makedirs("question_api/artifacts", exist_ok=True)
-torch.save(model.state_dict(), "question_api/artifacts/biggn_model.pt")
-
-with open("question_api/artifacts/vectorizer.pkl", "wb") as f:
-    pickle.dump(vectorizer, f)
-
-print("✅ Model and vectorizer saved.")

requirements.txt

@@ -8,8 +8,16 @@ Flask-CORS==4.0.0
 # Google AI
 google-generativeai==0.3.2
 
-# ML/NLP Libraries - Updated to compatible versions
-torch==2.2.0
+--extra-index-url https://download.pytorch.org/whl/cpu
+torch==2.1.2+cpu
+torchvision==0.16.2+cpu
+torchaudio==2.1.2+cpu
+
+torch-geometric==2.5.0
+torch-scatter==2.1.2
+torch-sparse==0.6.18
+torch-cluster==1.6.3
+torch-spline-conv==1.2.2
 transformers==4.35.2
 scikit-learn==1.3.2
 nltk==3.8.1