Added endpoint in main and changes in dockerfile

Dockerfile

@@ -20,7 +20,8 @@ RUN pip install --no-cache-dir -r requirements.txt
 COPY . .
 
 # Expose the FastAPI default port
-EXPOSE 7860
+EXPOSE 8000
 
 # Run FastAPI with Uvicorn
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
+

main.py

@@ -1,27 +1,34 @@
 # from fastapi import FastAPI
 # from pydantic import BaseModel
-# from typing import List, Tuple
+# from typing import List
 # import numpy as np
 # from sentence_transformers import SentenceTransformer
 
 # # Load the pre-trained model
 # model = SentenceTransformer('Alibaba-NLP/gte-base-en-v1.5', trust_remote_code=True)
 
-# # Define request model
+# # Define request models
 # class MessageRequest(BaseModel):
 #     messages: List[str]
 
-# # Define response model
+# class CosineSimilarityRequest(BaseModel):
+#     text1: str
+#     text2: str
+
+# # Define response models
 # class EmbeddingResponse(BaseModel):
 #     dimensions: int  # Only return embedding size
 #     numeric_values: List[List[float]]
 
+# class CosineSimilarityResponse(BaseModel):
+#     similarity: float
+
 # # Initialize FastAPI app
 # app = FastAPI()
 
 # @app.get("/")
-# def home ():
-#     return {"Message":"Welcome to homepage, kindly proceed by giving /docs in the URL" }
+# def home():
+#     return {"Message": "Welcome to homepage, kindly proceed by giving /docs in the URL"}
 
 # @app.post("/embed", response_model=EmbeddingResponse)
 # def embed(request: MessageRequest):
@@ -31,6 +38,13 @@
 #         numeric_values=new_embeddings.tolist()
 #     )
 
+# @app.post("/cosine_similarity", response_model=CosineSimilarityResponse)
+# def cosine_similarity(request: CosineSimilarityRequest):
+#     embeddings = model.encode([request.text1, request.text2], convert_to_tensor=True)
+#     cos_sim = np.dot(embeddings[0], embeddings[1]) / (np.linalg.norm(embeddings[0]) * np.linalg.norm(embeddings[1]))
+#     return CosineSimilarityResponse(similarity=cos_sim)
+
+
 from fastapi import FastAPI
 from pydantic import BaseModel
 from typing import List
@@ -48,6 +62,9 @@ class CosineSimilarityRequest(BaseModel):
     text1: str
     text2: str
 
+class SMSClassificationRequest(BaseModel):
+    text: str
+
 # Define response models
 class EmbeddingResponse(BaseModel):
     dimensions: int  # Only return embedding size
@@ -56,6 +73,9 @@ class EmbeddingResponse(BaseModel):
 class CosineSimilarityResponse(BaseModel):
     similarity: float
 
+class SMSClassificationResponse(BaseModel):
+    category: str
+
 # Initialize FastAPI app
 app = FastAPI()
 
@@ -76,3 +96,19 @@ def cosine_similarity(request: CosineSimilarityRequest):
     embeddings = model.encode([request.text1, request.text2], convert_to_tensor=True)
     cos_sim = np.dot(embeddings[0], embeddings[1]) / (np.linalg.norm(embeddings[0]) * np.linalg.norm(embeddings[1]))
     return CosineSimilarityResponse(similarity=cos_sim)
+
+@app.post("/classify_sms", response_model=SMSClassificationResponse)
+def classify_sms(request: SMSClassificationRequest):
+    offer_keywords = ["discount", "offer", "sale", "deal", "promo", "free"]
+    transaction_keywords = ["payment", "transaction", "debit", "credit", "purchase", "order"]
+    
+    text_lower = request.text.lower()
+    
+    if any(word in text_lower for word in offer_keywords):
+        category = "offer"
+    elif any(word in text_lower for word in transaction_keywords):
+        category = "transaction"
+    else:
+        category = "unknown"
+    
+    return SMSClassificationResponse(category=category)