one

main.py

@@ -1,29 +1,25 @@
 from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
-from sentence_transformers import SentenceTransformer, util
+from sentence_transformers import SentenceTransformer
 import numpy as np
 
 # Initialize the FastAPI app
 app = FastAPI()
 
-# Load the embedding models
-embedding_model = SentenceTransformer("Alibaba-NLP/gte-base-en-v1.5", trust_remote_code=True)
-similarity_model = SentenceTransformer("all-MiniLM-L6-v2")
+# Load the pre-trained SentenceTransformer model from Hugging Face
+#model = SentenceTransformer("//huggingface.co/spaces/Kabila22/Kabilan_embedding_1", trust_remote_code=True)
+model = SentenceTransformer("Alibaba-NLP/gte-base-en-v1.5", trust_remote_code=True)
 
-# Define request body schemas
+# Define the request body schema
 class TextInput(BaseModel):
     text: str
 
-class SimilarityInput(BaseModel):
-    text1: str
-    text2: str
-
 # Home route
 @app.get("/")
 async def home():
-    return {"message": "Welcome to the embedding and similarity API. Use /docs to test the endpoints."}
+    return {"message": "Welcome to embedding SMS API, use /docs to post SMS text and get dimensions"}
 
-# Endpoint for generating embeddings
+# Define the API endpoint
 @app.post("/embed")
 async def generate_embedding(text_input: TextInput):
     """
@@ -31,42 +27,21 @@ async def generate_embedding(text_input: TextInput):
     Returns the embedding in a structured format with rounded values.
     """
     try:
-        embedding = embedding_model.encode(text_input.text, convert_to_tensor=True).cpu().numpy()
+        # 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, decimals=2).tolist()
+
+        # Get the number of dimensions
         dimensions = len(rounded_embedding)
 
+        # Return structured response
         return {
             "dimensions": dimensions,
-            "embeddings": rounded_embedding
+            "embeddings": [rounded_embedding]  # Wrap the embedding inside a list
         }
     except Exception as e:
+        # Handle any errors
         raise HTTPException(status_code=500, detail=str(e))
 
-# New endpoint for calculating cosine similarity
-@app.post("/similarity")
-async def calculate_similarity(similarity_input: SimilarityInput):
-    """
-    Calculate cosine similarity between two text inputs.
-    """
-    try:
-        # Compute embeddings
-        embeddings1 = similarity_model.encode(similarity_input.text1, convert_to_tensor=True)
-        embeddings2 = similarity_model.encode(similarity_input.text2, convert_to_tensor=True)
-
-        # Compute cosine similarity
-        cosine_similarity = util.cos_sim(embeddings1, embeddings2).item()
-
-        return {
-            "text1": similarity_input.text1,
-            "text2": similarity_input.text2,
-            "cosine_similarity": round(cosine_similarity, 4)
-        }
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
-
-# Run the FastAPI app
-if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=7860)
-
-