running now

app.py

@@ -46,12 +46,10 @@ async def detect_contact(input: TextInput):
             }
         
      # If no regex patterns match, use the model
-        probabilities = predict(input.text)
-        probability = probabilities[1]  # Probability of containing contact info
-        is_contact = probability > 0.5  # You can adjust this threshold as needed
+        # Probability of containing contact info
+        is_contact = predict(input.text)  # You can adjust this threshold as needed
         return {
             "text": input.text,
-            "contact_probability": probability,
             "is_contact_info": is_contact,
             "method": "model"
         }

predictor.py

@@ -83,16 +83,18 @@ test_sentences = [
 ]
 
 
+# Function to predict
 def predict(text):
     with torch.no_grad():
         inputs = torch.tensor([text_pipeline(text)])
         if inputs.size(1) < max(FILTER_SIZES):
+            # Pad the input if it's shorter than the largest filter size
             padding = torch.zeros(1, max(FILTER_SIZES) - inputs.size(1), dtype=torch.long)
             inputs = torch.cat([inputs, padding], dim=1)
         inputs = inputs.to(device)
         outputs = model(inputs)
-        probabilities = F.softmax(outputs, dim=1)
-        return probabilities.squeeze().tolist()
+        return torch.argmax(outputs, dim=1).item()
+
 
 
 # Test the sentences

requirements.txt

@@ -1,4 +1,73 @@
-fastapi==0.68.0
-uvicorn==0.15.0
-torch==2.4.1
-transformers==4.10.0
+annotated-types==0.7.0
+anyio==4.6.0
+blis==0.7.11
+catalogue==2.0.10
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpathlib==0.19.0
+colorama==0.4.6
+confection==0.1.5
+cymem==2.0.8
+distro==1.9.0
+en-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl#sha256=86cc141f63942d4b2c5fcee06630fd6f904788d2f0ab005cce45aadb8fb73889
+fastapi==0.115.0
+filelock==3.13.1
+fsspec==2024.2.0
+greenlet==3.1.1
+groq==0.11.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.2
+huggingface-hub==0.25.1
+idna==3.10
+Jinja2==3.1.3
+langcodes==3.4.0
+language_data==1.2.0
+marisa-trie==1.2.0
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+murmurhash==1.0.10
+networkx==3.2.1
+numpy==1.26.3
+packaging==24.1
+pillow==10.2.0
+preshed==3.0.9
+psycopg2==2.9.9
+pydantic==2.9.2
+pydantic_core==2.23.4
+Pygments==2.18.0
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+safetensors==0.4.5
+setuptools==70.0.0
+shellingham==1.5.4
+smart-open==7.0.4
+sniffio==1.3.1
+spacy==3.7.6
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+SQLAlchemy==2.0.35
+srsly==2.4.8
+starlette==0.38.5
+sympy==1.12
+thinc==8.2.5
+tokenizers==0.19.1
+torch==2.2.0
+torchaudio==2.4.1+cu118
+torchdata==0.7.1
+torchtext==0.16.2
+torchvision==0.19.1+cu118
+tqdm==4.66.5
+transformers==4.44.2
+typer==0.12.5
+typing_extensions==4.12.2
+urllib3==2.2.3
+uvicorn==0.30.6
+wasabi==1.1.3
+weasel==0.4.1
+wrapt==1.16.0

vocab.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28edf2ae44d144c4566f0e5f95b856391166ac138ee578bac7fd9db151e1790a
+size 5184491