starchat-ggml / main.py
matthoffner's picture
Duplicate from matthoffner/ggml-ctransformers-fastapi
7d51224
raw
history blame
1.3 kB
import fastapi
import json
import markdown
import uvicorn
from fastapi.responses import HTMLResponse
from fastapi.middleware.cors import CORSMiddleware
from sse_starlette.sse import EventSourceResponse
from ctransformers.langchain import CTransformers
from pydantic import BaseModel
llm = CTransformers(model='ggml-model-q4_1.bin', model_type='starcoder')
app = fastapi.FastAPI()
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
@app.get("/")
async def index():
with open("README.md", "r", encoding="utf-8") as readme_file:
md_template_string = readme_file.read()
html_content = markdown.markdown(md_template_string)
return HTMLResponse(content=html_content, status_code=200)
class ChatCompletionRequest(BaseModel):
prompt: str
@app.post("/v1/chat/completions")
async def chat(request: ChatCompletionRequest, response_mode=None):
completion = llm(request.prompt)
async def server_sent_events(chat_chunks):
for chat_chunk in chat_chunks:
yield dict(data=json.dumps(chat_chunk))
yield dict(data="[DONE]")
return EventSourceResponse(server_sent_events(completion))
if __name__ == "__main__":
uvicorn.run(app, host="0.0.0.0", port=8000)