File size: 3,948 Bytes
3154e52 | 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 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 | import os
from fastapi import FastAPI, Request, HTTPException, Depends
from fastapi.responses import StreamingResponse
from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
import httpx
import json
import time
import uuid
app = FastAPI()
security = HTTPBearer()
API_KEY = os.environ.get("API_KEY", "!TU MUSISZ EDYTOWAC!") # np. "moj-tajny-klucz"
MODEL = os.environ.get("MODEL", "!TU MUSISZ EDYTOWAC!") # np. "deepseek-r1:14b" albo "hf.co/unsloth/GLM-4.7-Flash-GGUF:UD-TQ1_0"
OLLAMA_BASE = "http://127.0.0.1:11434"
if "!TU MUSISZ EDYTOWAC!" in (API_KEY, MODEL):
raise RuntimeError("Ustaw zmienne API_KEY i MODEL w HF Space Settings -> Variables")
def verify_key(credentials: HTTPAuthorizationCredentials = Depends(security)):
if credentials.credentials != API_KEY:
raise HTTPException(status_code=401, detail="Invalid API key")
return credentials.credentials
@app.get("/v1/models")
async def list_models(key: str = Depends(verify_key)):
return {
"object": "list",
"data": [{
"id": MODEL,
"object": "model",
"created": int(time.time()),
"owned_by": "ollama",
}]
}
@app.post("/v1/chat/completions")
async def chat_completions(request: Request, key: str = Depends(verify_key)):
body = await request.json()
messages = body.get("messages", [])
temperature = body.get("temperature", 0.6) # !TU MUSISZ EDYTOWAC! domyślna temperatura (0.0-2.0)
top_p = body.get("top_p", 0.95) # !TU MUSISZ EDYTOWAC! domyślne top_p (0.0-1.0)
options = {"temperature": temperature, "top_p": top_p}
if "max_tokens" in body:
options["num_predict"] = body["max_tokens"]
ollama_payload = {
"model": MODEL,
"messages": messages,
"stream": True,
"options": options,
}
completion_id = f"chatcmpl-{uuid.uuid4().hex}"
created = int(time.time())
async def generate():
async with httpx.AsyncClient(timeout=300.0) as client:
async with client.stream("POST", f"{OLLAMA_BASE}/api/chat", json=ollama_payload) as resp:
async for line in resp.aiter_lines():
if not line:
continue
try:
chunk = json.loads(line)
except Exception:
continue
msg = chunk.get("message", {})
done = chunk.get("done", False)
if done:
delta = {}
else:
delta = {}
if msg.get("thinking") is not None:
delta["reasoning_content"] = msg["thinking"]
if msg.get("content") is not None:
delta["content"] = msg["content"]
data = {
"id": completion_id,
"object": "chat.completion.chunk",
"created": created,
"model": MODEL,
"choices": [{
"index": 0,
"delta": delta,
"finish_reason": "stop" if done else None,
}]
}
yield f"data: {json.dumps(data)}\n\n"
if done:
break
yield "data: [DONE]\n\n"
return StreamingResponse(generate(), media_type="text/event-stream")
@app.get("/health")
async def health():
async with httpx.AsyncClient(timeout=5.0) as client:
try:
r = await client.get(f"{OLLAMA_BASE}/api/version")
ollama_ok = r.status_code == 200
except Exception:
ollama_ok = False
return {"status": "ok" if ollama_ok else "starting", "model": MODEL}
|