Feat - Progress updated

src/api/services/embedding_service.py

@@ -87,6 +87,8 @@ class EmbeddingService:
         self.model = model
         self.batch_size = batch_size
         self.semaphore = asyncio.Semaphore(max_concurrent_requests)  # Rate limiter
+        self.total_requests = 0  # Total number of requests to process
+        self.completed_requests = 0  # Number of completed requests
 
     async def get_embedding(self, text: str) -> List[float]:
         """Generate embeddings for the given text using OpenAI."""
@@ -96,6 +98,8 @@ class EmbeddingService:
                 response = await self.client.embeddings.create(
                     input=[text], model=self.model
                 )
+                self.completed_requests += 1  # Increment completed requests
+                self._log_progress()  # Log progress
                 return response.data[0].embedding
         except Exception as e:
             logger.error(f"Failed to generate embedding: {e}")
@@ -106,6 +110,9 @@ class EmbeddingService:
     ) -> pd.DataFrame:
         """Create embeddings for the target column in the dataset."""
         logger.info("Generating embeddings...")
+        self.total_requests = len(df)  # Set total number of requests
+        self.completed_requests = 0  # Reset completed requests counter
+
         batches = [
             df[i : i + self.batch_size] for i in range(0, len(df), self.batch_size)
         ]
@@ -126,3 +133,10 @@ class EmbeddingService:
         )
         df_batch[output_column] = embeddings
         return df_batch
+
+    def _log_progress(self):
+        """Log the progress of embedding generation."""
+        progress = (self.completed_requests / self.total_requests) * 100
+        logger.info(
+            f"Progress: {self.completed_requests}/{self.total_requests} ({progress:.2f}%)"
+        )