feat/enhance the multi-modal support (#8818)

api/pyproject.toml

@@ -158,7 +158,7 @@ nomic = "~3.1.2"
 novita-client = "~0.5.7"
 numpy = "~1.26.4"
 oci = "~2.135.1"
-openai = "~1.51.2"
+openai = "~1.52.0"
 openpyxl = "~3.1.5"
 pandas = { version = "~2.2.2", extras = ["performance", "excel"] }
 psycopg2-binary = "~2.9.6"
@@ -216,6 +216,7 @@ matplotlib = "~3.8.2"
 newspaper3k = "0.2.8"
 nltk = "3.8.1"
 numexpr = "~2.9.0"
+pydub = "~0.25.1"
 qrcode = "~7.4.2"
 twilio = "~9.0.4"
 vanna = { version = "0.7.3", extras = ["postgres", "mysql", "clickhouse", "duckdb"] }