adding Vectorization service

src/ctp_slack_bot/services/VectorizationService.py

@@ -0,0 +1,64 @@
+from pydantic import BaseModel, validator
+from typing import List, Optional
+from ctp_slack_bot.core.config import settings
+import numpy as np
+from openai import AsyncOpenAI  # Updated import
+
+
+class VectorizationService(BaseModel):
+    """
+    Service for vectorizing chunks of text data.
+    """
+    def __init__(self):
+        self.client = AsyncOpenAI(api_key=settings.OPENAI_API_KEY)
+
+        
+    async def get_embeddings(self, texts: List[str]) -> np.ndarray:
+        """Get embeddings for a list of texts using OpenAI's API.
+        
+        Args:
+            texts (List[str]): List of text chunks to embed
+            
+        Returns:
+            np.ndarray: Array of embeddings with shape (n_texts, VECTOR_DIMENSION)
+            
+        Raises:
+            ValueError: If the embedding dimensions don't match expected size
+        """
+        try:
+            # Use the initialized client instead of the global openai module
+            response = await self.client.embeddings.create(
+                model=settings.EMBEDDING_MODEL,
+                input=texts,
+                encoding_format="float"  # Ensure we get raw float values
+            )
+            
+            # Extract embeddings and verify dimensions
+            embeddings = np.array([data.embedding for data in response.data])
+            
+            if embeddings.shape[1] != settings.VECTOR_DIMENSION:
+                raise ValueError(
+                    f"Embedding dimension mismatch. Expected {settings.VECTOR_DIMENSION}, "
+                    f"but got {embeddings.shape[1]}. Please update VECTOR_DIMENSION "
+                    f"in config.py to match the model's output."
+                )
+                
+            return embeddings 
+            
+        except Exception as e:
+            print(f"Error getting embeddings: {str(e)}")
+            raise
+
+    def _test(self):
+        """
+        Test the vectorization service.
+        """
+
+        pass
+
+
+
+vs = VectorizationService()
+vs._test()
+    
+