Docker Stream

main.py

@@ -1,4 +1,5 @@
 from fastapi import FastAPI
+from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
 from huggingface_hub import InferenceClient
 import uvicorn
@@ -44,11 +45,13 @@ def generate(item: Item):
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
 
+    # for response in stream:
+    #     output += response.token.text
+    # return output
     for response in stream:
-        output += response.token.text
-    return output
+        yield response.token.text
 
 @app.post("/generate/")
 async def generate_text(item: Item):
-    return {"response": generate(item)}
+    return StreamingResponse(generate(item), media_type="text/plain")