diff --git a/dist/litellm-0.1.7712-py3-none-any.whl b/dist/litellm-0.1.7712-py3-none-any.whl
new file mode 100644
index 000000000..b59fd81b4
Binary files /dev/null and b/dist/litellm-0.1.7712-py3-none-any.whl differ
diff --git a/dist/litellm-0.1.7712.tar.gz b/dist/litellm-0.1.7712.tar.gz
new file mode 100644
index 000000000..b1ad1110d
Binary files /dev/null and b/dist/litellm-0.1.7712.tar.gz differ
diff --git a/dist/litellm-0.1.7713-py3-none-any.whl b/dist/litellm-0.1.7713-py3-none-any.whl
new file mode 100644
index 000000000..a2871cf75
Binary files /dev/null and b/dist/litellm-0.1.7713-py3-none-any.whl differ
diff --git a/dist/litellm-0.1.7713.tar.gz b/dist/litellm-0.1.7713.tar.gz
new file mode 100644
index 000000000..45ac493ba
Binary files /dev/null and b/dist/litellm-0.1.7713.tar.gz differ
diff --git a/litellm/__init__.py b/litellm/__init__.py
index 727d55578..a357292c9 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -322,4 +322,4 @@ from .exceptions import (
 
 )
 from .budget_manager import BudgetManager
-from .proxy_server.proxy_cli import run_server
\ No newline at end of file
+from .proxy.proxy_cli import run_server
\ No newline at end of file
diff --git a/litellm/__pycache__/__init__.cpython-311.pyc b/litellm/__pycache__/__init__.cpython-311.pyc
index 040428ab0..e65faa9a7 100644
Binary files a/litellm/__pycache__/__init__.cpython-311.pyc and b/litellm/__pycache__/__init__.cpython-311.pyc differ
diff --git a/litellm/proxy_server/proxy_cli.py b/litellm/proxy/proxy_cli.py
similarity index 92%
rename from litellm/proxy_server/proxy_cli.py
rename to litellm/proxy/proxy_cli.py
index 6a3be5755..75bad1b6f 100644
--- a/litellm/proxy_server/proxy_cli.py
+++ b/litellm/proxy/proxy_cli.py
@@ -7,7 +7,7 @@ load_dotenv()
 @click.option('--api_base', default=None, help='API base URL.')
 @click.option('--model', required=True, help='The model name to pass to litellm expects') 
 def run_server(port, api_base, model):
-    from proxy_server import app, initialize
+    from .proxy_server import app, initialize
     initialize(model, api_base)
     try:
         import uvicorn
diff --git a/litellm/proxy_server/proxy_server.py b/litellm/proxy/proxy_server.py
similarity index 87%
rename from litellm/proxy_server/proxy_server.py
rename to litellm/proxy/proxy_server.py
index fbb182bcb..4535775d2 100644
--- a/litellm/proxy_server/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -1,3 +1,4 @@
+import litellm
 from fastapi import FastAPI, Request
 from fastapi.responses import StreamingResponse
 import json
@@ -11,6 +12,12 @@ def initialize(model, api_base):
     user_model = model
     user_api_base = api_base
 
+
+# for streaming
+def data_generator(response):
+    for chunk in response:
+        yield f"data: {json.dumps(chunk)}\n\n"
+        
 @app.get("/models") # if project requires model list 
 def model_list(): 
     return dict(
diff --git a/pyproject.toml b/pyproject.toml
index 6f5018ea5..bc7ae8dde 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.771"
+version = "0.1.7713"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"