added project

Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.9
+
+WORKDIR /app
+COPY . /app
+
+ENV HF_HOME=/app/.cache
+
+RUN mkdir -p /app/.cache/huggingface/hub && \
+    chmod -R 777 /app/.cache && \
+    chmod -R 777 /app/.cache/huggingface
+
+
+
+RUN pip install --upgrade pip
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+EXPOSE 7860
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,123 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from sentence_transformers import SentenceTransformer,util
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LogisticRegression
+from fastapi.middleware.cors import CORSMiddleware
+import uvicorn
+import numpy as np
+import pandas as pd
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Allow all origins; restrict this in production
+    allow_credentials=True,
+    allow_methods=["*"],  # Allow all HTTP methods
+    allow_headers=["*"],  # Allow all HTTP headers
+)
+
+
+# Initialize the FastAPI app
+
+
+# Load the pre-trained SentenceTransformer model
+model = SentenceTransformer("Alibaba-NLP/gte-base-en-v1.5", trust_remote_code=True)
+
+# Define the request body schema
+class TextInput(BaseModel):
+    text: str
+
+# Home route
+@app.get("/")
+async def home():
+    return {"message": "welcome to home page"}
+
+# Define the API endpoint for generating embeddings
+@app.post("/embed")
+async def generate_embedding(text_input: TextInput):
+    """
+    Generate a 768-dimensional embedding for the input text.
+    Returns the embedding in a structured format with rounded values.
+    """
+    try:
+        # Generate the embedding
+        embedding = model.encode(text_input.text, convert_to_tensor=True).cpu().numpy()
+
+        # Round embedding values to 2 decimal places
+        rounded_embedding = np.round(embedding, 2).tolist()
+
+        # Return structured response
+        return {
+            "dimensions": len(rounded_embedding),
+            "embeddings": [rounded_embedding]
+        }
+
+    except Exception as e:
+        # Handle any errors
+        raise HTTPException(status_code=500, detail=f"An error occurred: {str(e)}")
+    
+
+
+model = SentenceTransformer("Alibaba-NLP/gte-base-en-v1.5", trust_remote_code=True)
+df = pd.read_excel("sms_process_data_main.xlsx")
+
+    # Split the data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(df["MessageText"], df["label"], test_size=0.2, random_state=42)
+
+    # Generate embeddings for the training data
+X_train_embeddings = model.encode(X_train.tolist(), show_progress_bar=True)
+
+    # Initialize and train the Logistic Regression model
+logreg_model = LogisticRegression(max_iter=100)
+logreg_model.fit(X_train_embeddings, y_train)
+
+# Define input schema
+class TextInput(BaseModel):
+    text: str
+
+@app.post("/prediction")
+async def generate_prediction(text_input: TextInput):
+    """
+    Predict the label for the given text input using the trained model.
+    """
+    try:
+        # Check if input text is provided
+        if not text_input.text.strip():
+            raise ValueError("Input text cannot be empty.")
+
+        # Generate embedding for the input text
+        new_embedding = model.encode([text_input.text])
+
+        # Predict the label using the trained Logistic Regression model
+        prediction = logreg_model.predict(new_embedding).tolist()[0]  # Extract single prediction
+
+        # Return structured response
+        return {
+            "predicted_label": prediction
+        }
+    except ValueError as ve:
+        raise HTTPException(status_code=400, detail=str(ve))
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"An error occurred: {str(e)}")
+    
+class SentencesInput(BaseModel):
+    sentence1: str
+    sentence2: str
+@app.post("/text_to_tensor")
+def text_to_tensor(input: SentencesInput):
+    try:
+        # Generate embeddings
+        embeddings = model.encode([input.sentence1, input.sentence2])
+
+        # Compute cosine similarity
+        cosine_similarity = util.cos_sim(embeddings[0], embeddings[1]).item()
+
+        return {"cosine_similarity": round(cosine_similarity, 3)}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"An error occurred: {str(e)}")
+
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,6 @@
+fastapi[standard]
+pandas
+scikit-learn
+joblib
+uvicorn
+sentence-transformers