hofmannol/llmproxy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Log actual Ollama token counts and add user guide

Browse Source 
Add a second usage log line after each proxy response with actual ↑prompt ↓completion
token counts from Ollama (prompt_eval_count/eval_count for native endpoints,
usage object for OpenAI endpoint). Also adds KURZANLEITUNG.md for students and
colleagues covering API access, model selection, Python examples, opencode setup,
and quota/admin information.
This commit is contained in:
Oliver Hofmann
2026-05-08 07:21:36 +02:00
parent 256bafe30d
commit cced65693c
2 changed files with 184 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/main.py
+16 -3
View File
@@ -101,7 +101,11 @@ async def generate(request: Request, db: Session = Depends(get_db)):
request.state.api_key_name, body.get("model", "?"), prompt_tokens, prompt_preview)
try:
response = await proxy_request(f"{ollama_url}/api/generate", method="POST", json_data=body)
return JSONResponse(content=response.json(), status_code=response.status_code)
resp_json = response.json()
usage_log.info('%s | /api/generate | %s | actual ↑%d ↓%d tokens',
request.state.api_key_name, body.get("model", "?"),
resp_json.get("prompt_eval_count", 0), resp_json.get("eval_count", 0))
return JSONResponse(content=resp_json, status_code=response.status_code)
except Exception as exc:
error_log.error("Proxy error | %s | /api/generate | %s | %s: %s",
request.state.api_key_name, body.get("model", "?"), type(exc).__name__, exc, exc_info=exc)
@@ -121,7 +125,11 @@ async def chat(request: Request, db: Session = Depends(get_db)):
request.state.api_key_name, body.get("model", "?"), prompt_tokens, _last_user_msg(messages))
try:
response = await proxy_request(f"{ollama_url}/api/chat", method="POST", json_data=body)
return JSONResponse(content=response.json(), status_code=response.status_code)
resp_json = response.json()
usage_log.info('%s | /api/chat | %s | actual ↑%d ↓%d tokens',
request.state.api_key_name, body.get("model", "?"),
resp_json.get("prompt_eval_count", 0), resp_json.get("eval_count", 0))
return JSONResponse(content=resp_json, status_code=response.status_code)
except Exception as exc:
error_log.error("Proxy error | %s | /api/chat | %s | %s: %s",
request.state.api_key_name, body.get("model", "?"), type(exc).__name__, exc, exc_info=exc)
@@ -185,7 +193,12 @@ async def openai_chat_completions(request: Request, db: Session = Depends(get_db
try:
response = await proxy_request(target, method="POST", json_data=body)
return JSONResponse(content=response.json(), status_code=response.status_code)
resp_json = response.json()
usage = resp_json.get("usage", {})
usage_log.info('%s | /v1/chat/completions | %s | actual ↑%d ↓%d tokens',
request.state.api_key_name, model_name,
usage.get("prompt_tokens", 0), usage.get("completion_tokens", 0))
return JSONResponse(content=resp_json, status_code=response.status_code)
except Exception as exc:
error_log.error("Proxy error | %s | /v1/chat/completions | %s | %s: %s",
request.state.api_key_name, model_name, type(exc).__name__, exc, exc_info=exc)