Proxy fixes, streaming support, Admin-UI overhaul
Backend: - Fix Content-Length mismatch by not forwarding client headers to Ollama - Proxy /v1/chat/completions directly to Ollama's OpenAI-compatible endpoint (eliminates manual Ollama↔OpenAI format conversion, fixes tool use) - Add streaming support via SSE passthrough - Fix ollama_url /v1 suffix stripped on save - Replace BaseHTTPMiddleware with FastAPI global dependency (fixes double logging) - Add rotating usage log (8 KB, logs key name + model + token estimate + prompt preview) - Add httpx timeout 300s - Add activate and delete endpoints for API keys - Return usage data (tokens/requests) in GET /api/api-keys Frontend: - Admin table: remove ID column, status as icon, icon-only action buttons with CSS tooltips - Add activate + delete buttons; edit available for inactive keys too - Quota columns: fixed equal width, progress bars with k-unit formatting - Create form: structured layout matching edit form style - Edit form: token inputs in k units (÷1000 display, ×1000 on save) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Oliver Hofmann
co-authored by
Claude Sonnet 4.6
Claude Sonnet 4.6
parent
c62cafc202
commit
dd8f69ecb6
+43
-5
@@ -8,7 +8,7 @@ from fastapi.staticfiles import StaticFiles
|
||||
from sqlalchemy.orm import Session
|
||||
from database import get_db
|
||||
import crud, schemas
|
||||
from models import APIKey as APIKeyModel
|
||||
from models import APIKey as APIKeyModel, Usage as UsageModel
|
||||
|
||||
app = FastAPI(title="Ollama Proxy Admin API")
|
||||
|
||||
@@ -31,13 +31,24 @@ def require_admin_auth(request: Request):
|
||||
if not secrets.compare_digest(token, ADMIN_PASSWORD):
|
||||
raise HTTPException(status_code=401, detail="Invalid admin password")
|
||||
|
||||
@app.get("/api/api-keys", response_model=list[schemas.APIKey])
|
||||
@app.get("/api/api-keys", response_model=list[schemas.APIKeyWithUsage])
|
||||
async def read_api_keys(
|
||||
skip: int = 0, limit: int = 100,
|
||||
db: Session = Depends(get_db),
|
||||
_ = Depends(require_admin_auth),
|
||||
):
|
||||
return db.query(APIKeyModel).offset(skip).limit(limit).all()
|
||||
keys = db.query(APIKeyModel).offset(skip).limit(limit).all()
|
||||
result = []
|
||||
for key in keys:
|
||||
item = schemas.APIKeyWithUsage.model_validate(key)
|
||||
usage = db.query(UsageModel).filter(UsageModel.api_key_id == key.id).first()
|
||||
if usage:
|
||||
item.tokens_used_today = usage.tokens_used_today or 0
|
||||
item.tokens_used_month = usage.tokens_used_month or 0
|
||||
item.requests_today = usage.requests_today or 0
|
||||
item.requests_month = usage.requests_month or 0
|
||||
result.append(item)
|
||||
return result
|
||||
|
||||
@app.post("/api/api-keys", response_model=schemas.APIKeyCreated)
|
||||
async def create_api_key(
|
||||
@@ -87,6 +98,32 @@ async def deactivate_api_key(
|
||||
db.commit()
|
||||
return {"message": "API key deactivated"}
|
||||
|
||||
@app.put("/api/api-keys/{api_key_id}/activate")
|
||||
async def activate_api_key(
|
||||
api_key_id: int,
|
||||
db: Session = Depends(get_db),
|
||||
_ = Depends(require_admin_auth),
|
||||
):
|
||||
db_key = db.query(APIKeyModel).filter(APIKeyModel.id == api_key_id).first()
|
||||
if not db_key:
|
||||
raise HTTPException(status_code=404, detail="API key not found")
|
||||
db_key.is_active = True
|
||||
db.commit()
|
||||
return {"message": "API key activated"}
|
||||
|
||||
@app.delete("/api/api-keys/{api_key_id}")
|
||||
async def delete_api_key(
|
||||
api_key_id: int,
|
||||
db: Session = Depends(get_db),
|
||||
_ = Depends(require_admin_auth),
|
||||
):
|
||||
db_key = db.query(APIKeyModel).filter(APIKeyModel.id == api_key_id).first()
|
||||
if not db_key:
|
||||
raise HTTPException(status_code=404, detail="API key not found")
|
||||
db.delete(db_key)
|
||||
db.commit()
|
||||
return {"message": "API key deleted"}
|
||||
|
||||
@app.get("/api/proxy-info")
|
||||
async def get_proxy_info(_ = Depends(require_admin_auth)):
|
||||
host = os.getenv("PROXY_HOST", "0.0.0.0")
|
||||
@@ -107,9 +144,10 @@ async def update_settings(
|
||||
db: Session = Depends(get_db),
|
||||
_ = Depends(require_admin_auth),
|
||||
):
|
||||
crud.set_setting(db, "ollama_url", settings.ollama_url)
|
||||
ollama_url = settings.ollama_url.rstrip('/').removesuffix('/v1')
|
||||
crud.set_setting(db, "ollama_url", ollama_url)
|
||||
crud.set_setting(db, "default_model", settings.default_model)
|
||||
return settings
|
||||
return schemas.Settings(ollama_url=ollama_url, default_model=settings.default_model)
|
||||
|
||||
@app.get("/api/ollama-models")
|
||||
async def get_ollama_models(
|
||||
|
||||
+81
-83
@@ -1,135 +1,133 @@
|
||||
import time
|
||||
import uuid
|
||||
import logging
|
||||
import os
|
||||
from logging.handlers import RotatingFileHandler
|
||||
from pathlib import Path
|
||||
|
||||
from fastapi import FastAPI, HTTPException, Depends, Request
|
||||
from fastapi.responses import JSONResponse
|
||||
from fastapi.responses import JSONResponse, StreamingResponse
|
||||
from sqlalchemy.orm import Session
|
||||
from database import get_db, SessionLocal
|
||||
from database import get_db
|
||||
import crud
|
||||
import httpx
|
||||
import os
|
||||
|
||||
app = FastAPI(title="Ollama Proxy")
|
||||
# Rotating usage log (8 KB per file, 3 backups)
|
||||
_log_path = Path(os.getenv("LOG_FILE", "logs/usage.log"))
|
||||
_log_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
_handler = RotatingFileHandler(str(_log_path), maxBytes=8192, backupCount=3, encoding="utf-8")
|
||||
_handler.setFormatter(logging.Formatter("%(asctime)s | %(message)s", datefmt="%Y-%m-%d %H:%M:%S"))
|
||||
usage_log = logging.getLogger("proxy.usage")
|
||||
usage_log.setLevel(logging.INFO)
|
||||
usage_log.addHandler(_handler)
|
||||
usage_log.propagate = False
|
||||
|
||||
async def proxy_request(url: str, method: str = "GET", json_data: dict = None, headers: dict = None):
|
||||
async with httpx.AsyncClient() as client:
|
||||
response = await client.request(method=method, url=url, json=json_data, headers=headers)
|
||||
return response
|
||||
def _last_user_msg(messages: list, max_len: int = 120) -> str:
|
||||
for msg in reversed(messages):
|
||||
if msg.get("role") == "user":
|
||||
text = (msg.get("content") or "").replace("\n", " ").strip()
|
||||
return text[:max_len] + ("…" if len(text) > max_len else "")
|
||||
return ""
|
||||
|
||||
@app.middleware("http")
|
||||
async def authenticate_and_quota(request: Request, call_next):
|
||||
async def require_api_key(request: Request, db: Session = Depends(get_db)):
|
||||
auth_header = request.headers.get("Authorization", "")
|
||||
if auth_header.startswith("Bearer "):
|
||||
api_key = auth_header.replace("Bearer ", "")
|
||||
api_key = auth_header[7:]
|
||||
elif auth_header.startswith("sk-"):
|
||||
api_key = auth_header
|
||||
else:
|
||||
return JSONResponse(status_code=401, content={"detail": "Invalid or missing API key"})
|
||||
raise HTTPException(status_code=401, detail="Invalid or missing API key")
|
||||
db_key = crud.verify_api_key(db, api_key)
|
||||
if not db_key:
|
||||
raise HTTPException(status_code=401, detail="Invalid API key")
|
||||
request.state.api_key_id = db_key.id
|
||||
request.state.api_key_name = db_key.name
|
||||
|
||||
# Uses its own session since middleware cannot use Depends
|
||||
db = SessionLocal()
|
||||
try:
|
||||
db_key = crud.verify_api_key(db, api_key)
|
||||
if not db_key:
|
||||
return JSONResponse(status_code=401, content={"detail": "Invalid API key"})
|
||||
request.state.api_key_id = db_key.id
|
||||
finally:
|
||||
db.close()
|
||||
app = FastAPI(title="Ollama Proxy", dependencies=[Depends(require_api_key)])
|
||||
|
||||
response = await call_next(request)
|
||||
return response
|
||||
async def proxy_request(url: str, method: str = "GET", json_data: dict = None):
|
||||
async with httpx.AsyncClient(timeout=300.0) as client:
|
||||
response = await client.request(method=method, url=url, json=json_data)
|
||||
return response
|
||||
|
||||
@app.post("/api/generate")
|
||||
async def generate(request: Request, db: Session = Depends(get_db)):
|
||||
api_key_id = request.state.api_key_id
|
||||
ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
|
||||
|
||||
body = await request.json()
|
||||
|
||||
prompt_tokens = crud.count_tokens(body.get("prompt", ""))
|
||||
if not crud.check_and_increment_quota(db, api_key_id, tokens=prompt_tokens, requests=1):
|
||||
|
||||
if not crud.check_and_increment_quota(db, request.state.api_key_id, tokens=prompt_tokens, requests=1):
|
||||
raise HTTPException(status_code=429, detail="Quota exceeded")
|
||||
|
||||
response = await proxy_request(f"{ollama_url}/api/generate", method="POST", json_data=body, headers=dict(request.headers))
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code, headers=dict(response.headers))
|
||||
prompt_preview = (body.get("prompt", "").replace("\n", " ").strip())[:120]
|
||||
usage_log.info('%s | /api/generate | %s | ~%d tokens | "%s"',
|
||||
request.state.api_key_name, body.get("model", "?"), prompt_tokens, prompt_preview)
|
||||
response = await proxy_request(f"{ollama_url}/api/generate", method="POST", json_data=body)
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code)
|
||||
|
||||
@app.post("/api/chat")
|
||||
async def chat(request: Request, db: Session = Depends(get_db)):
|
||||
api_key_id = request.state.api_key_id
|
||||
ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
|
||||
|
||||
body = await request.json()
|
||||
messages = body.get("messages", [])
|
||||
prompt_tokens = sum(crud.count_tokens(msg.get("content") or "") for msg in messages)
|
||||
|
||||
prompt_tokens = sum(crud.count_tokens(msg.get("content", "")) for msg in body.get("messages", []))
|
||||
if not crud.check_and_increment_quota(db, api_key_id, tokens=prompt_tokens, requests=1):
|
||||
if not crud.check_and_increment_quota(db, request.state.api_key_id, tokens=prompt_tokens, requests=1):
|
||||
raise HTTPException(status_code=429, detail="Quota exceeded")
|
||||
|
||||
response = await proxy_request(f"{ollama_url}/api/chat", method="POST", json_data=body, headers=dict(request.headers))
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code, headers=dict(response.headers))
|
||||
usage_log.info('%s | /api/chat | %s | ~%d tokens | "%s"',
|
||||
request.state.api_key_name, body.get("model", "?"), prompt_tokens, _last_user_msg(messages))
|
||||
response = await proxy_request(f"{ollama_url}/api/chat", method="POST", json_data=body)
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code)
|
||||
|
||||
@app.get("/api/tags")
|
||||
async def list_models(request: Request, db: Session = Depends(get_db)):
|
||||
async def list_models(db: Session = Depends(get_db)):
|
||||
ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
|
||||
response = await proxy_request(f"{ollama_url}/api/tags", method="GET", headers=dict(request.headers))
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code, headers=dict(response.headers))
|
||||
response = await proxy_request(f"{ollama_url}/api/tags", method="GET")
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code)
|
||||
|
||||
@app.get("/api/versions")
|
||||
async def versions(request: Request, db: Session = Depends(get_db)):
|
||||
async def versions(db: Session = Depends(get_db)):
|
||||
ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
|
||||
response = await proxy_request(f"{ollama_url}/api/versions", method="GET", headers=dict(request.headers))
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code, headers=dict(response.headers))
|
||||
response = await proxy_request(f"{ollama_url}/api/versions", method="GET")
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code)
|
||||
|
||||
@app.get("/v1/models")
|
||||
async def list_openai_models(request: Request, db: Session = Depends(get_db)):
|
||||
async def list_openai_models(db: Session = Depends(get_db)):
|
||||
ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
|
||||
response = await proxy_request(f"{ollama_url}/api/tags", method="GET", headers=dict(request.headers))
|
||||
ollama_models = response.json()
|
||||
openai_models = {
|
||||
"object": "list",
|
||||
"data": [
|
||||
{
|
||||
"id": model["name"],
|
||||
"object": "model",
|
||||
"created": int(model["modified_at"][:10].replace("-", "")) * 1000 if "modified_at" in model else 0,
|
||||
"owned_by": "ollama"
|
||||
}
|
||||
for model in ollama_models.get("models", [])
|
||||
]
|
||||
}
|
||||
return JSONResponse(content=openai_models, status_code=200, headers=dict(response.headers))
|
||||
response = await proxy_request(f"{ollama_url}/v1/models", method="GET")
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code)
|
||||
|
||||
@app.post("/v1/chat/completions")
|
||||
async def openai_chat_completions(request: Request, db: Session = Depends(get_db)):
|
||||
api_key_id = request.state.api_key_id
|
||||
ollama_url = crud.get_setting(db, "ollama_url", os.getenv("OLLAMA_URL", "http://localhost:11434"))
|
||||
default_model = crud.get_setting(db, "default_model", os.getenv("DEFAULT_MODEL", "llama3"))
|
||||
|
||||
body = await request.json()
|
||||
messages = body.get("messages", [])
|
||||
prompt_tokens = sum(crud.count_tokens(msg.get("content", "")) for msg in messages)
|
||||
prompt_tokens = sum(crud.count_tokens(msg.get("content") or "") for msg in messages)
|
||||
|
||||
if not crud.check_and_increment_quota(db, api_key_id, tokens=prompt_tokens, requests=1):
|
||||
if not crud.check_and_increment_quota(db, request.state.api_key_id, tokens=prompt_tokens, requests=1):
|
||||
raise HTTPException(status_code=429, detail="Quota exceeded")
|
||||
|
||||
ollama_body = {
|
||||
"model": body.get("model", default_model),
|
||||
"messages": messages,
|
||||
"stream": body.get("stream", False)
|
||||
}
|
||||
if "model" not in body:
|
||||
body = {**body, "model": default_model}
|
||||
|
||||
response = await proxy_request(f"{ollama_url}/api/chat", method="POST", json_data=ollama_body, headers=dict(request.headers))
|
||||
response_content = response.json().get("message", {}).get("content", "")
|
||||
completion_tokens = crud.count_tokens(response_content)
|
||||
model_name = body["model"]
|
||||
usage_log.info('%s | /v1/chat/completions | %s | ~%d tokens | "%s"',
|
||||
request.state.api_key_name, model_name, prompt_tokens, _last_user_msg(messages))
|
||||
|
||||
openai_response = {
|
||||
"id": f"chatcmpl-{uuid.uuid4().hex}",
|
||||
"object": "chat.completion",
|
||||
"created": int(time.time()),
|
||||
"model": body.get("model", default_model),
|
||||
"choices": [{"index": 0, "message": {"role": "assistant", "content": response_content}, "finish_reason": "stop"}],
|
||||
"usage": {
|
||||
"prompt_tokens": prompt_tokens,
|
||||
"completion_tokens": completion_tokens,
|
||||
"total_tokens": prompt_tokens + completion_tokens,
|
||||
},
|
||||
}
|
||||
return JSONResponse(content=openai_response, status_code=200, headers={"Content-Type": "application/json"})
|
||||
target = f"{ollama_url}/v1/chat/completions"
|
||||
|
||||
if body.get("stream"):
|
||||
async def generate():
|
||||
async with httpx.AsyncClient(timeout=300.0) as client:
|
||||
async with client.stream("POST", target, json=body) as resp:
|
||||
async for chunk in resp.aiter_bytes():
|
||||
yield chunk
|
||||
return StreamingResponse(
|
||||
generate(),
|
||||
media_type="text/event-stream",
|
||||
headers={"Cache-Control": "no-cache", "X-Accel-Buffering": "no"},
|
||||
)
|
||||
|
||||
response = await proxy_request(target, method="POST", json_data=body)
|
||||
return JSONResponse(content=response.json(), status_code=response.status_code)
|
||||
|
||||
@@ -50,5 +50,14 @@ class UsageStats(BaseModel):
|
||||
daily_reset_at: Optional[datetime] = None
|
||||
monthly_reset_at: Optional[datetime] = None
|
||||
|
||||
class Config:
|
||||
from_attributes = True
|
||||
|
||||
class APIKeyWithUsage(APIKey):
|
||||
tokens_used_today: int = 0
|
||||
tokens_used_month: int = 0
|
||||
requests_today: int = 0
|
||||
requests_month: int = 0
|
||||
|
||||
class Config:
|
||||
from_attributes = True
|
||||
Reference in New Issue
Block a user