65 lines
3.3 KiB
Python
65 lines
3.3 KiB
Python
"""Production answer path: retrieval -> model selection -> guard -> rendered text."""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import os
|
|
import threading
|
|
import urllib.request
|
|
from pathlib import Path
|
|
|
|
from tools.rag.common import DB_FILE
|
|
from tools.rag.rag_utils import build_rag_context
|
|
from tools.rag.llm_context import compact_rag_payload
|
|
from tools.graphrag.graph_search import search_graph
|
|
from tools.answer_evaluation.graph_context import graph_context
|
|
from tools.answer_evaluation.checked_generation import generate_checked_answer
|
|
from tools.answer_evaluation.verified_rag import generate_verified_rag
|
|
|
|
_capacity = threading.BoundedSemaphore(2)
|
|
|
|
|
|
def complete_with_configured_model(messages: list[dict]) -> dict:
|
|
key = os.getenv('OPENWEBUI_API_KEY', '').strip()
|
|
if not key:
|
|
raise RuntimeError('Answer model is not configured')
|
|
endpoint = os.getenv('ANSWER_LLM_URL', 'https://ui.tukekemt.xyz/api/chat/completions')
|
|
body = {'model': os.getenv('ANSWER_MODEL', 'model120-fast'), 'messages': messages,
|
|
'temperature': 0, 'stream': False}
|
|
request = urllib.request.Request(endpoint, data=json.dumps(body, ensure_ascii=False).encode(),
|
|
headers={'Content-Type': 'application/json', 'Authorization': 'Bearer ' + key})
|
|
with urllib.request.urlopen(request, timeout=120) as response:
|
|
data = response.read(2 * 1024 * 1024 + 1)
|
|
if len(data) > 2 * 1024 * 1024:
|
|
raise RuntimeError('Answer model output is too large')
|
|
return json.loads(data)
|
|
|
|
|
|
def deliver_answer(question: str, *, engine: str = 'rag', limit: int = 5,
|
|
complete=None, db_file: Path = DB_FILE) -> dict:
|
|
if not _capacity.acquire(blocking=False):
|
|
return {'status': 'error', 'reason': 'answer_capacity_exceeded',
|
|
'accepted_for_delivery': False, 'answer': 'Agent práve spracúva iné odpovede. Skúste to o chvíľu.'}
|
|
try:
|
|
model = complete or complete_with_configured_model
|
|
if engine == 'rag':
|
|
retrieved = compact_rag_payload(build_rag_context(db_file, question, limit=limit))
|
|
result = generate_verified_rag(question, retrieved, model)
|
|
elif engine == 'graphrag':
|
|
context = graph_context(search_graph(question))
|
|
prompt = (Path(__file__).resolve().parents[1] / 'answer_evaluation/graph_answer_prompt.txt').read_text()
|
|
generated = generate_checked_answer(question, context, prompt, model)
|
|
if generated.get('accepted_for_delivery'):
|
|
result = {**generated['answer'], 'accepted_for_delivery': True, 'reason': None,
|
|
'index_version': context.get('index_version'), 'complete': context.get('complete'),
|
|
'truncated': context.get('truncated'), 'truncation_reasons': context.get('truncation_reasons'),
|
|
'attempts': generated['attempts']}
|
|
else:
|
|
result = {'status': 'error', 'reason': 'answer_rejected', 'accepted_for_delivery': False,
|
|
'answer': 'Odpoveď neprešla kontrolou podkladov; neoverené údaje sa nezobrazia.',
|
|
'index_version': context.get('index_version'), 'attempts': generated['attempts']}
|
|
else:
|
|
raise ValueError('Unsupported answer engine')
|
|
return {**result, 'engine': engine}
|
|
finally:
|
|
_capacity.release()
|