Bring back embedding logs, at DEBUG level

Author: pamelafox

app/backend/prepdocs.py

@@ -325,7 +325,7 @@ async def main(strategy: Strategy, setup_index: bool = True):
         logging.basicConfig(format="%(message)s", datefmt="[%X]", handlers=[RichHandler(rich_tracebacks=True)])
         # We only set the level to INFO for our logger,
         # to avoid seeing the noisy INFO level logs from the Azure SDKs
-        logger.setLevel(logging.DEBUG)
+        logger.setLevel(logging.INFO)
 
     load_azd_env()
 

app/backend/prepdocslib/embeddings.py

@@ -114,7 +114,11 @@ async def create_embedding_batch(self, texts: list[str], dimensions_args: ExtraA
                         model=self.open_ai_model_name, input=batch.texts, **dimensions_args
                     )
                     embeddings.extend([data.embedding for data in emb_response.data])
-
+                    logger.debug(
+                        "Computed embeddings in batch. Batch size: %d, Token count: %d",
+                        len(batch.texts),
+                        batch.token_length,
+                    )
         return embeddings
 
     async def create_embedding_single(self, text: str, dimensions_args: ExtraArgs) -> list[float]:
@@ -129,7 +133,7 @@ async def create_embedding_single(self, text: str, dimensions_args: ExtraArgs) -
                 emb_response = await client.embeddings.create(
                     model=self.open_ai_model_name, input=text, **dimensions_args
                 )
-
+                logger.debug("Computed embedding for text section. Character count: %d", len(text))
         return emb_response.data[0].embedding
 
     async def create_embeddings(self, texts: list[str]) -> list[list[float]]: