Spaces:
Build error
Build error
Update main.py
Browse files
main.py
CHANGED
|
@@ -1,10 +1,6 @@
|
|
| 1 |
import fastapi
|
| 2 |
-
import json
|
| 3 |
-
import markdown
|
| 4 |
import uvicorn
|
| 5 |
-
from fastapi.responses import HTMLResponse
|
| 6 |
from fastapi.middleware.cors import CORSMiddleware
|
| 7 |
-
from sse_starlette.sse import EventSourceResponse
|
| 8 |
from ctransformers import AutoModelForCausalLM
|
| 9 |
from pydantic import BaseModel
|
| 10 |
|
|
@@ -22,35 +18,15 @@ app.add_middleware(
|
|
| 22 |
|
| 23 |
@app.get("/")
|
| 24 |
async def index():
|
| 25 |
-
|
| 26 |
-
<html>
|
| 27 |
-
<head>
|
| 28 |
-
</head>
|
| 29 |
-
<body>
|
| 30 |
-
<h1><a href="https://matthoffner-wizardcoder-ggml.hf.space/docs">FastAPI Docs</a></h1>
|
| 31 |
-
<iframe
|
| 32 |
-
src="https://matthoffner-monacopilot.hf.space"
|
| 33 |
-
frameborder="0"
|
| 34 |
-
width="850"
|
| 35 |
-
height="450"
|
| 36 |
-
></iframe>
|
| 37 |
-
</body>
|
| 38 |
-
</html>
|
| 39 |
-
"""
|
| 40 |
-
return HTMLResponse(content=html_content, status_code=200)
|
| 41 |
|
| 42 |
-
class
|
| 43 |
-
|
| 44 |
|
| 45 |
-
@app.post("/
|
| 46 |
-
async def
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
for chat_chunk in llm.generate(chat_chunks):
|
| 50 |
-
yield dict(data=json.dumps(llm.detokenize(chat_chunk)))
|
| 51 |
-
yield dict(data="[DONE]")
|
| 52 |
-
|
| 53 |
-
return EventSourceResponse(server_sent_events(tokens, llm))
|
| 54 |
|
| 55 |
if __name__ == "__main__":
|
| 56 |
uvicorn.run(app, host="0.0.0.0", port=8000)
|
|
|
|
| 1 |
import fastapi
|
|
|
|
|
|
|
| 2 |
import uvicorn
|
|
|
|
| 3 |
from fastapi.middleware.cors import CORSMiddleware
|
|
|
|
| 4 |
from ctransformers import AutoModelForCausalLM
|
| 5 |
from pydantic import BaseModel
|
| 6 |
|
|
|
|
| 18 |
|
| 19 |
@app.get("/")
|
| 20 |
async def index():
|
| 21 |
+
return {"message": "Hello World"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
+
class InferenceRequest(BaseModel):
|
| 24 |
+
input: str
|
| 25 |
|
| 26 |
+
@app.post("/inference")
|
| 27 |
+
async def inference(request: InferenceRequest):
|
| 28 |
+
generated_text = llm(request.input)
|
| 29 |
+
return {"generated_text": generated_text}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
if __name__ == "__main__":
|
| 32 |
uvicorn.run(app, host="0.0.0.0", port=8000)
|