Spaces:
Runtime error
Runtime error
File size: 1,784 Bytes
f410bac 5fa76ab 27bf18d 5fa76ab f410bac 714866c 5fa76ab e6fa3d8 0eb14ad 473963a 5fa76ab f441c05 5fa76ab 27bf18d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from huggingface_hub import InferenceClient
import streamlit as st
app = FastAPI()
# Allow all CORS
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.2")
class Item(BaseModel):
prompt: str
history: list
system_prompt: str
temperature: float = 0.0
max_new_tokens: int = 10240
top_p: float = 0.15
repetition_penalty: float = 1.0
def format_prompt(message, history):
return message
def generate(item: Item):
temperature = float(item.temperature)
if temperature < 1e-2:
temperature = 1e-2
top_p = float(item.top_p)
generate_kwargs = dict(
temperature=temperature,
max_new_tokens=item.max_new_tokens,
top_p=top_p,
repetition_penalty=item.repetition_penalty,
do_sample=True,
seed=42,
)
formatted_prompt = format_prompt(f"{item.system_prompt}, {item.prompt}", item.history)
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
@app.post("/generate/")
async def generate_text(item: Item):
# reject if key not the same
apiKey = st.secrets["API_KEY"]
# if apiKey != key:
# return jsonify({
# "image_url": image_url,
# "model": model,
# "result": "Invalid API Key",
# }), 400
return {
"response": generate(item),
"key": apiKey
}
|