Add support for Ollama streaming output and integrate Open-WebUI as the chat UI demo

examples/lightrag_ollama_demo.py

@@ -1,4 +1,6 @@
+import asyncio
 import os
+import inspect
 import logging
 from lightrag import LightRAG, QueryParam
 from lightrag.llm import ollama_model_complete, ollama_embedding
@@ -49,3 +51,20 @@ print(
 print(
     rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid"))
 )
+
+# stream response
+resp = rag.query(
+    "What are the top themes in this story?",
+    param=QueryParam(mode="hybrid", stream=True),
+)
+
+
+async def print_stream(stream):
+    async for chunk in stream:
+        print(chunk, end="", flush=True)
+
+
+if inspect.isasyncgen(resp):
+    asyncio.run(print_stream(resp))
+else:
+    print(resp)