Cursor Agentandhaijd
9c6afcb61a
需求未定稿时可先跑通追问/判定/出方案；槽位与判定树外置 YAML，后续可接 Ragflow。 Co-authored-by: haijd <haijd@163.com>
95 lines
3.1 KiB
Python
95 lines
3.1 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
import httpx
|
|
|
|
from .config_loader import business_config
|
|
from .settings import settings
|
|
|
|
|
|
class RetrievalResult:
|
|
def __init__(self, chunks: list[dict[str, Any]]):
|
|
self.chunks = chunks
|
|
|
|
|
|
def retrieve_for_scheme(slots: dict[str, str], bundle: list[str]) -> RetrievalResult:
|
|
backend = (settings.retrieval_backend or "mock").lower()
|
|
if backend == "ragflow":
|
|
return _retrieve_ragflow(slots, bundle)
|
|
return _retrieve_mock(slots, bundle)
|
|
|
|
|
|
def _retrieve_mock(slots: dict[str, str], bundle: list[str]) -> RetrievalResult:
|
|
chunks = business_config.chunks
|
|
picked: list[dict[str, Any]] = []
|
|
bundle_set = set(bundle)
|
|
for c in chunks:
|
|
if c.get("product") in bundle_set:
|
|
picked.append(c)
|
|
# tag overlap with slot values
|
|
blob = " ".join(slots.values())
|
|
for c in chunks:
|
|
if c in picked:
|
|
continue
|
|
tags = c.get("tags") or []
|
|
if any(str(t) in blob for t in tags):
|
|
picked.append(c)
|
|
if len(picked) >= 4:
|
|
break
|
|
if not picked:
|
|
picked = chunks[:2]
|
|
return RetrievalResult(picked[:4])
|
|
|
|
|
|
def _retrieve_ragflow(slots: dict[str, str], bundle: list[str]) -> RetrievalResult:
|
|
"""Minimal Ragflow retrieval hook. Falls back to mock if not configured/unavailable."""
|
|
if not settings.ragflow_api_key:
|
|
return _retrieve_mock(slots, bundle)
|
|
|
|
query = " ".join(
|
|
[
|
|
slots.get("tech_category", ""),
|
|
slots.get("scenario", ""),
|
|
slots.get("key_metric", ""),
|
|
" ".join(bundle),
|
|
]
|
|
).strip() or "产品方案"
|
|
dataset_ids = [x for x in settings.ragflow_dataset_ids.split(",") if x.strip()]
|
|
url = settings.ragflow_base_url.rstrip("/") + "/api/v1/retrieval"
|
|
headers = {"Authorization": f"Bearer {settings.ragflow_api_key}"}
|
|
payload: dict[str, Any] = {"question": query, "top_k": 4}
|
|
if dataset_ids:
|
|
payload["dataset_ids"] = dataset_ids
|
|
|
|
try:
|
|
with httpx.Client(timeout=20.0) as client:
|
|
resp = client.post(url, headers=headers, json=payload)
|
|
resp.raise_for_status()
|
|
data = resp.json()
|
|
except Exception:
|
|
return _retrieve_mock(slots, bundle)
|
|
|
|
# Ragflow response shapes vary by version; normalize best-effort
|
|
records = []
|
|
if isinstance(data, dict):
|
|
records = data.get("data") or data.get("chunks") or data.get("records") or []
|
|
if isinstance(records, dict):
|
|
records = records.get("chunks") or records.get("records") or []
|
|
normalized = []
|
|
for i, r in enumerate(records[:4]):
|
|
if not isinstance(r, dict):
|
|
continue
|
|
normalized.append(
|
|
{
|
|
"id": r.get("id") or f"rf-{i}",
|
|
"title": r.get("document_keyword") or r.get("title") or "Ragflow片段",
|
|
"product": r.get("document_id") or "",
|
|
"content": r.get("content") or r.get("text") or "",
|
|
"tags": [],
|
|
}
|
|
)
|
|
if not normalized:
|
|
return _retrieve_mock(slots, bundle)
|
|
return RetrievalResult(normalized)
|