add stream chat (#811)

### What problem does this PR solve?

#709 
### Type of change

- [x] New Feature (non-breaking change which adds functionality)

api/utils/api_utils.py

@@ -25,7 +25,6 @@ from flask import (
 from werkzeug.http import HTTP_STATUS_CODES
 
 from api.utils import json_dumps
-from api.versions import get_rag_version
 from api.settings import RetCode
 from api.settings import (
     REQUEST_MAX_WAIT_SEC, REQUEST_WAIT_SEC,
@@ -84,9 +83,6 @@ def request(**kwargs):
     return sess.send(prepped, stream=stream, timeout=timeout)
 
 
-rag_version = get_rag_version() or ''
-
-
 def get_exponential_backoff_interval(retries, full_jitter=False):
     """Calculate the exponential backoff wait time."""
     # Will be zero if factor equals 0