gramps/cAIc
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix: replace triage import with LLAMA_SERVER_BASE for deployed compat

Browse Source
This commit is contained in:
gramps
2026-07-13 07:59:38 -07:00
parent 12a7d92f99
commit 6f95cc67bb
1 changed files with 1 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
routers/chat.py
+1 -3
View File
@@ -8,11 +8,10 @@ import httpx
from fastapi import APIRouter, HTTPException, Request from fastapi import APIRouter, HTTPException, Request
from fastapi.responses import StreamingResponse from fastapi.responses import StreamingResponse
from config import DEFAULT_MODEL from config import DEFAULT_MODEL, LLAMA_SERVER_BASE
from db import get_db, get_upload_context from db import get_db, get_upload_context
from memory import process_remember_command from memory import process_remember_command
from rag import build_system_prompt from rag import build_system_prompt
from triage import get_inference_url as _get_inference_url
from search import (calculate_perplexity, is_uncertain, is_refusal, from search import (calculate_perplexity, is_uncertain, is_refusal,
clean_hedging, format_search_results, format_direct_answer, clean_hedging, format_search_results, format_direct_answer,
extract_search_query, query_searxng) extract_search_query, query_searxng)
@@ -126,7 +125,6 @@ async def chat(request: Request):
all_logprobs = [] all_logprobs = []
tokens_per_sec = 0.0 tokens_per_sec = 0.0
completion_tokens = 0 completion_tokens = 0
inference_base = await _get_inference_url(user_message)
if remember_response: if remember_response:
yield f"data: {json.dumps({'token': remember_response + chr(10) + chr(10), 'conversation_id': conv_id})}\n\n" yield f"data: {json.dumps({'token': remember_response + chr(10) + chr(10), 'conversation_id': conv_id})}\n\n"