fix: remove embedding dims config from .env.example (pingcap#472)

.env.example

@@ -17,15 +17,12 @@ TIDB_PASSWORD=
 TIDB_DATABASE=
 TIDB_SSL=true
 
-# CAUTION: Do not change EMBEDDING_DIMS after initializing the database.
-# Changing the embedding dimensions requires recreating the database and tables.
-# The default EMBEDDING_DIMS and EMBEDDING_MAX_TOKENS are set for the OpenAI text-embedding-3-small model.
-# If using a different embedding model, adjust these values according to the model's specifications.
-# For example:
-#   openai/text-embedding-3-small: EMBEDDING_DIMS=1536, EMBEDDING_MAX_TOKENS=8191
-#   maidalun1020/bce-embedding-base_v1: EMBEDDING_DIMS=768, EMBEDDING_MAX_TOKENS=512
-#   BAAI/bge-m3: EMBEDDING_DIMS=1024, EMBEDDING_MAX_TOKENS=8192
-EMBEDDING_DIMS=1536
-# EMBEDDING_MAX_TOKENS should be equal or smaller than the embedding model's max tokens,
-# it indicates the max size of document chunks.
+# EMBEDDING_MAX_TOKENS indicates the max size of document chunks.
+#
+# EMBEDDING_MAX_TOKENS should be smaller than the embedding model's max tokens due
+# to the tokenizer difference. (see: https://github.com/pingcap/autoflow/issues/397)
+#
+# Go to https://tidb.ai/docs/embedding-model to check the max tokens of the embedding model.
+#
+# Notice: this variable will be deprecated in the future.
 EMBEDDING_MAX_TOKENS=2048