模板导出增强 + 模特性别分组 + 三合一提示词精简
1) 模板导出：识别「基码表-胸围」填 sku.bust（多个胸围列都填）；申报价格模糊匹配多列统一按加价后价格填写；详情图文不再拼接 img_url_2；SPU 款式来源统一填「现货款」；商品产地国家简称映射（沙特→沙特阿拉伯） 2) 模特性别分组：model_features 按男女分组，按模板类目含男/女固定取对应性别模特（含 Pinterest 模式 pipeline） 3) 三合一提示词：去掉 DESIGN CONTENT 四要素描述（设计已由设计稿提供） 4) 生图尺寸：全部改为读 config 不再硬编码（设计图 compose.design_size / 合成图 compose.size / 种草图 seed_shot.size）
This commit is contained in:
@@ -1,7 +1,8 @@
|
||||
"""Pinterest 参考模式节点 1/3：LLM 生成搜索词（pinterest_search）。
|
||||
"""Pinterest 参考模式节点 1/3：按需生成单个搜索词（pinterest_search）。
|
||||
|
||||
流程：国家 Pinterest 种子词池 → LLM 生成搜索词（json_schema 结构化 + 动态注入已用词防重复）
|
||||
→ 全局过滤（已用/黑名单/不适合T恤/去重）→ 持久化已用词。
|
||||
按需搜索：每次只生成 1 个搜索词（LLM json_schema + 动态注入已用词防重复），
|
||||
带短袖/印花设计引导，保证搜索词适合短袖 T 恤印花。
|
||||
不在此处持久化已用词 —— 只有爬取成功（真正用掉）才标记已用（见 pinterest_scrape）。
|
||||
|
||||
兜底链：LLM json_schema → json_object → 解析失败/调用失败 → 回退种子词池随机抽样。
|
||||
带 with_fallback：任何异常都不中断，返回空列表由下游跳过。
|
||||
@@ -15,7 +16,6 @@ from graph.pinterest import (
|
||||
load_used_terms,
|
||||
merge_used,
|
||||
sample_seeds,
|
||||
save_used_terms,
|
||||
)
|
||||
from graph.validate import with_fallback
|
||||
|
||||
@@ -32,72 +32,88 @@ def pinterest_search_node(state: Dict[str, Any]) -> Dict[str, Any]:
|
||||
return {"pinterest_search_terms": [], "errors": errors}
|
||||
|
||||
provider = str(pcfg.get("provider") or "openai").strip().lower()
|
||||
want = int(pcfg.get("search_terms_per_run", 10))
|
||||
search_mode = str(pcfg.get("search_mode") or "direct").strip().lower()
|
||||
want = int(pcfg.get("search_terms_per_run", 1)) # 每次搜索词数量
|
||||
seed_sample = int(pcfg.get("seed_sample", 40))
|
||||
max_used_in_prompt = int(pcfg.get("max_used_terms_in_prompt", 100))
|
||||
blacklist = config.get("blacklist") or []
|
||||
|
||||
# 1) 种子词池（随机抽样）+ 已用搜索词
|
||||
# 1) 种子词池 + 已用搜索词 + 本轮已尝试词（防同轮重复，不持久化）
|
||||
seeds = sample_seeds(country, seed_sample)
|
||||
used = load_used_terms(output_dir, country)
|
||||
attempted = [str(t).strip() for t in (state.get("pinterest_attempted") or []) if str(t).strip()]
|
||||
rounds = int(state.get("pinterest_rounds") or 0) + 1
|
||||
if not seeds:
|
||||
print(f"[pinterest_search] {country} 无种子词，跳过搜索词生成")
|
||||
return {"pinterest_search_terms": [], "errors": errors}
|
||||
return {"pinterest_search_terms": [], "pinterest_rounds": rounds, "errors": errors}
|
||||
|
||||
# 2) LLM 生成（json_schema + 动态注入已用词）
|
||||
# 已用词只取最近 N 个（默认 100）注入提示词，防 token 超限；过滤仍用全量。
|
||||
used_llm = used[-max_used_in_prompt:] if max_used_in_prompt > 0 else []
|
||||
# 2) 生成搜索词：种子词不再由 LLM 给出，直接由内置国家种子词库随机抽取（优先未用过），
|
||||
# 追加 " t-shirt design"（保证 Pinterest 返回真正的 T 恤印花图）；llm 模式保留兼容
|
||||
terms: List[str] = []
|
||||
llm = None
|
||||
if provider != "static":
|
||||
try:
|
||||
llm = get_backend(provider)
|
||||
if hasattr(llm, "bind_config"):
|
||||
llm.bind_config(config.get("llm_screen") or {})
|
||||
if provider not in ("mock",) and not getattr(llm, "has_key", False):
|
||||
print(f"[pinterest_search] {provider} 未配置 API key，降级 mock")
|
||||
llm = get_backend("mock")
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f"[pinterest_search] LLM 初始化失败: {e}")
|
||||
llm = None
|
||||
if search_mode == "direct":
|
||||
from graph.pinterest import load_pinterest_seeds
|
||||
pool = load_pinterest_seeds(country)
|
||||
used_set = {str(u).strip().lower() for u in merge_used(used, attempted)}
|
||||
fresh = [s for s in pool if s.lower() not in used_set]
|
||||
if not fresh:
|
||||
fresh = pool # 库内词全部用过 → 允许复用（词库有限）
|
||||
terms = [f"{s} t-shirt design" if "t-shirt design" not in s.lower() else s
|
||||
for s in random.sample(fresh, min(want, len(fresh)))]
|
||||
print(f"[pinterest_search] direct 模式：国家种子词库随机抽 {len(terms)} 个 + t-shirt design（{country}）")
|
||||
else:
|
||||
used_llm = merge_used(used, attempted)
|
||||
if max_used_in_prompt > 0:
|
||||
used_llm = used_llm[-max_used_in_prompt:]
|
||||
llm = None
|
||||
if provider != "static":
|
||||
try:
|
||||
llm = get_backend(provider)
|
||||
if hasattr(llm, "bind_config"):
|
||||
llm.bind_config(config.get("llm_screen") or {})
|
||||
if provider not in ("mock",) and not getattr(llm, "has_key", False):
|
||||
print(f"[pinterest_search] {provider} 未配置 API key，降级 mock")
|
||||
llm = get_backend("mock")
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f"[pinterest_search] LLM 初始化失败: {e}")
|
||||
llm = None
|
||||
|
||||
if llm is not None and hasattr(llm, "generate_pinterest_terms"):
|
||||
try:
|
||||
ctx = {"country": country, "seeds": seeds, "used_terms": used_llm, "count": want}
|
||||
res = llm.generate_pinterest_terms(ctx)
|
||||
terms = [str(t).strip() for t in (res.get("search_terms") or []) if str(t).strip()]
|
||||
print(f"[pinterest_search] LLM 生成搜索词 {len(terms)} 个（{country}，已用词注入 {len(used_llm)}/{len(used)}）")
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f"[pinterest_search] LLM 生成失败，回退种子词池: {e}")
|
||||
terms = []
|
||||
if llm is not None and hasattr(llm, "generate_pinterest_terms"):
|
||||
try:
|
||||
ctx = {"country": country, "seeds": seeds, "used_terms": used_llm, "count": want}
|
||||
res = llm.generate_pinterest_terms(ctx)
|
||||
terms = [str(t).strip() for t in (res.get("search_terms") or []) if str(t).strip()]
|
||||
print(f"[pinterest_search] LLM 生成搜索词 {len(terms)} 个（{country}，已用词注入 {len(used_llm)}）")
|
||||
except Exception as e: # noqa: BLE001
|
||||
print(f"[pinterest_search] LLM 生成失败，回退种子词池: {e}")
|
||||
terms = []
|
||||
|
||||
# 3) 兜底：LLM 无结果 → 种子词池随机抽样
|
||||
if not terms:
|
||||
terms = random.sample(seeds, min(want, len(seeds))) if seeds else []
|
||||
print(f"[pinterest_search] 兜底：从种子词池取 {len(terms)} 个")
|
||||
# 3) 兜底：LLM 无结果 → 种子词池随机抽样
|
||||
if not terms:
|
||||
terms = [f"{s} t-shirt design" if "t-shirt design" not in s.lower() else s
|
||||
for s in random.sample(seeds, min(want, len(seeds)))]
|
||||
print(f"[pinterest_search] 兜底：从种子词池取 {len(terms)} 个")
|
||||
|
||||
# 4) 全局过滤（已用/黑名单/不适合T恤/去重）
|
||||
filtered = filter_search_terms(terms, used, blacklist)
|
||||
if len(filtered) < want and seeds:
|
||||
# 不足时用种子词池补充（同样过滤），保证数量
|
||||
extra = filter_search_terms(seeds, merge_used(used, filtered), blacklist)
|
||||
for t in extra:
|
||||
if len(filtered) >= want:
|
||||
break
|
||||
filtered.append(t)
|
||||
|
||||
# 5) 持久化已用词
|
||||
new_used = merge_used(used, filtered)
|
||||
save_used_terms(output_dir, country, new_used)
|
||||
# 4) 全局过滤（已用/本轮已尝试/黑名单/不适合T恤/去重）——注意：不在此处持久化已用词
|
||||
# direct 模式：抽样时已避开已用词（库内词有限，全部用过后允许复用），不再额外过滤
|
||||
if search_mode == "direct":
|
||||
filtered = terms
|
||||
else:
|
||||
filtered = filter_search_terms(terms, merge_used(used, attempted), blacklist)
|
||||
if not filtered and seeds:
|
||||
# 生成词全被过滤 → 从种子词池补充（同样过滤）
|
||||
extra = filter_search_terms(seeds, merge_used(used, attempted), blacklist)
|
||||
filtered = extra[:want]
|
||||
|
||||
stats = dict(state.get("stats") or {})
|
||||
stats["pinterest_search"] = {
|
||||
"provider": provider,
|
||||
"round": rounds,
|
||||
"generated": len(terms),
|
||||
"filtered": len(filtered),
|
||||
"used_total": len(new_used),
|
||||
"used_total": len(used),
|
||||
}
|
||||
print(f"[pinterest_search] 搜索词 {len(filtered)} 个（已用累计 {len(new_used)}）: "
|
||||
f"{', '.join(filtered[:6])}{'...' if len(filtered) > 6 else ''}")
|
||||
print(f"[pinterest_search] 第 {rounds} 轮搜索词 {len(filtered)} 个（已用累计 {len(used)}）: "
|
||||
f"{', '.join(filtered[:3])}{'...' if len(filtered) > 3 else ''}")
|
||||
|
||||
return {"pinterest_search_terms": filtered, "stats": stats, "errors": errors}
|
||||
return {"pinterest_search_terms": filtered, "pinterest_rounds": rounds,
|
||||
"stats": stats, "errors": errors}
|
||||
|
||||
Reference in New Issue
Block a user