init

app.py

@@ -0,0 +1,102 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Define the model and tokenizer
+tokenizer_emotion = AutoTokenizer.from_pretrained("SamLowe/roberta-base-go_emotions")
+model_emotion = AutoModelForSequenceClassification.from_pretrained("SamLowe/roberta-base-go_emotions")
+
+from transformers import AutoModelForTokenClassification
+
+tokenizer_t_class = AutoTokenizer.from_pretrained("dslim/bert-base-NER")
+
+model_t_class = AutoModelForTokenClassification.from_pretrained("dslim/bert-base-NER")
+
+# FastAPI app
+app = FastAPI()
+
+# Define the request body
+class Input(BaseModel):
+    text: str
+
+@app.post("/emotion")
+async def predict_emotion(input: Input):
+    # Tokenize the input text
+    inputs = tokenizer_emotion(input.text, return_tensors="pt")
+    # Get the model's predictions
+    outputs = model_emotion(**inputs)
+    # Get the predicted class
+    predicted_class_idx = torch.argmax(outputs.logits).item()
+    # Decode the predicted class
+    predicted_class = model_emotion.config.id2label[predicted_class_idx]
+    # Return the prediction
+    return {"predicted_emotion": predicted_class}
+
+# from transformers import pipeline
+
+@app.post("/ner")
+async def perform_ner(item: Input):
+
+    # nlp = pipeline("ner", model=model_t_class, tokenizer=tokenizer_t_class)
+
+    # ner_results = nlp(item.text)
+    # print(ner_results)
+
+    # Tokenize the input text
+    inputs = tokenizer_t_class.encode(item.text, return_tensors="pt")
+    # Get the model's predictions
+    outputs = model_t_class(inputs).logits
+    # Get the predicted classes for each token
+    predictions = torch.argmax(outputs, dim=2)
+    # Decode the tokens and their predicted classes
+    tokens = tokenizer_t_class.convert_ids_to_tokens(inputs[0])
+    predicted_labels = [model_t_class.config.id2label[prediction] for prediction in predictions[0].tolist()]
+    # Pair tokens with their predicted labels
+    token_labels = list(zip(tokens, predicted_labels))
+    # Filter out subwords
+    filtered_token_labels = [(token, label) for token, label in token_labels if not token.startswith("##")]
+    # Return the tokens and their predicted labels
+    return {"token_labels": filtered_token_labels}
+
+
+
+# if __name__ == "__main__":
+#     import uvicorn
+#     uvicorn.run(app, host="0.0.0.0", port=8000)
+
+
+import streamlit as st
+
+st.title("Emotion Detection App")
+
+input_text = st.input("Enter your text here")
+
+if st.button("Predict"):
+
+    # Tokenize the input text
+    inputs = tokenizer_t_class.encode(input_text, return_tensors="pt")
+    # Get the model's predictions
+    outputs = model_t_class(inputs).logits
+    # Get the predicted classes for each token
+    predictions = torch.argmax(outputs, dim=2)
+    # Decode the tokens and their predicted classes
+    tokens = tokenizer_t_class.convert_ids_to_tokens(inputs[0])
+    predicted_labels = [model_t_class.config.id2label[prediction] for prediction in predictions[0].tolist()]
+    # Pair tokens with their predicted labels
+    token_labels = list(zip(tokens, predicted_labels))
+    # Filter out subwords
+    filtered_token_labels = [(token, label) for token, label in token_labels if not token.startswith("##")]
+    # Return the tokens and their predicted labels
+    st.write({"token_labels": filtered_token_labels})
+
+
+    inputs = tokenizer_emotion(input.text, return_tensors="pt")
+    # Get the model's predictions
+    outputs = model_emotion(**inputs)
+    # Get the predicted class
+    predicted_class_idx = torch.argmax(outputs.logits).item()
+    # Decode the predicted class
+    predicted_class = model_emotion.config.id2label[predicted_class_idx]
+    # Return the prediction
+    st.write({"predicted_emotion": predicted_class})

requirements.txt

@@ -0,0 +1,32 @@
+anyio==3.7.0
+certifi==2023.5.7
+charset-normalizer==3.1.0
+click==8.1.3
+exceptiongroup==1.1.1
+fastapi==0.97.0
+filelock==3.12.2
+fsspec==2023.6.0
+h11==0.14.0
+huggingface-hub==0.15.1
+idna==3.4
+Jinja2==3.1.2
+MarkupSafe==2.1.3
+mpmath==1.3.0
+networkx==3.1
+numpy==1.25.0
+packaging==23.1
+pydantic==1.10.9
+PyYAML==6.0
+regex==2023.6.3
+requests==2.31.0
+safetensors==0.3.1
+sniffio==1.3.0
+starlette==0.27.0
+sympy==1.12
+tokenizers==0.13.3
+torch==2.0.1
+tqdm==4.65.0
+transformers==4.30.2
+typing_extensions==4.6.3
+urllib3==2.0.3
+uvicorn==0.22.0