feat: improve assistant knowledge import and database compatibility

This commit is contained in:
吉鑫升 committed 2026-09-02 17:55:17 +08:00
1 parent fbd8dec48f
commit 6b724bd00d
51 files changed
+4393 -1021

No files matched your search

@@ -40,6 +40,7 @@ _MAX_SOURCE_CHARS = 1400
@dataclass(frozen=True)
class LlmWikiRagContext:
knowledge_base_ids: list[str]
assistant_knowledge_base_ids: list[str]
source_count: int
prompt: str
sources: list[dict[str, Any]]
@@ -50,6 +51,10 @@ def _store(request: Request) -> LlmWikiStore | None:
return getattr(request.app.state, "llmwiki_store", None)
def _assistant_store(request: Request) -> Any | None:
return getattr(request.app.state, "assistant_knowledge_store", None)
async def _actor(request: Request) -> tuple[str, bool]:
user = await get_optional_user_from_request(request)
if user is None:
@@ -76,6 +81,13 @@ def _body_selected_ids(body: Any) -> list[str]:
return []
def _body_selected_assistant_ids(body: Any) -> list[str]:
for source in (getattr(body, "context", None), getattr(body, "metadata", None)):
if isinstance(source, Mapping) and "assistant_knowledge_base_ids" in source:
return _as_id_list(source.get("assistant_knowledge_base_ids"))
return []
def _assistant_agent_id(body: Any) -> str | None:
assistant_id = validate_agent_id(getattr(body, "assistant_id", None))
if assistant_id:
@@ -106,8 +118,17 @@ def resolve_requested_llmwiki_knowledge_base_ids(body: Any) -> list[str]:
return _body_selected_ids(body)
def resolve_requested_assistant_knowledge_base_ids(body: Any) -> list[str]:
"""Return assistant knowledge bases explicitly selected for the run."""
return _body_selected_assistant_ids(body)
def llmwiki_selection_requested(body: Any) -> bool:
return bool(resolve_requested_llmwiki_knowledge_base_ids(body))
return bool(
resolve_requested_llmwiki_knowledge_base_ids(body)
or resolve_requested_assistant_knowledge_base_ids(body)
)
def _latest_human_query(graph_input: dict[str, Any]) -> str:
@@ -191,18 +212,50 @@ def _source_from_result(result: dict[str, Any], mapping: dict[str, Any], index:
}
def _source_from_assistant_result(result: dict[str, Any], index: int) -> dict[str, Any]:
title = str(result.get("title") or f"助手知识库片段 {index}")
matched_section = result.get("matched_section") if isinstance(result.get("matched_section"), Mapping) else {}
content = str(
matched_section.get("content")
or result.get("content_markdown")
or result.get("content")
or result.get("summary")
or ""
)
snippet = str(result.get("summary") or content)
raw = {
**result,
"source": "助手知识库",
"url": "/page/workspace/knowledge/assistant",
}
return {
"index": index,
"id": result.get("id") or result.get("slug") or f"assistant:{index}",
"title": title,
"type": "assistant_knowledge",
"snippet": _truncate(snippet, 360),
"content": content,
"source": "助手知识库",
"score": float(result.get("score") or 0),
"url": "/page/workspace/knowledge/assistant",
"skillName": "assistant_knowledge_search",
"mode": "citation",
"raw": raw,
}
def _build_prompt(query: str, sources: list[dict[str, Any]]) -> str:
if not sources:
return "当前用户选择了 LLMWiki 知识库,但 DeerFlow 未检索到可用片段。请直接说明没有检索到可用背景资料,不要编造知识库内容或引用编号。"
return "当前用户选择了知识库,但 DeerFlow 未检索到可用片段。请直接说明没有检索到可用背景资料,不要编造知识库内容或引用编号。"
lines = [
"当前用户选择了 LLMWiki 知识库。DeerFlow 已在模型回答前自动检索到以下背景资料。",
"当前用户选择了知识库。DeerFlow 已在模型回答前自动检索到以下背景资料。",
"请优先依据这些资料回答;如果资料不足,请明确说明不足之处,不要编造。",
"引用规则:正文关键结论必须使用 [1]、[2] 这样的编号引用下方资料;只能引用存在的编号;不要在正文末尾重复输出完整参考文献列表,前端会展示引用卡片。",
"",
f"用户问题:{query}",
"",
f'<llmwiki_wiki_reference_batch source_count="{len(sources)}">',
f'<knowledge_reference_batch source_count="{len(sources)}">',
]
for source in sources:
meta = " / ".join(
@@ -213,12 +266,12 @@ def _build_prompt(query: str, sources: list[dict[str, Any]]) -> str:
)
if item
)
lines.append(f"[{source['index']}] {source.get('title') or 'LLMWiki 片段'}")
lines.append(f"[{source['index']}] {source.get('title') or '知识库片段'}")
if meta:
lines.append(f"来源:{meta}")
lines.append(_truncate(str(source.get("content") or source.get("snippet") or ""), _MAX_SOURCE_CHARS))
lines.append("")
lines.append("</llmwiki_wiki_reference_batch>")
lines.append("</knowledge_reference_batch>")
return "\n".join(lines).strip()
@@ -229,52 +282,99 @@ async def build_llmwiki_rag_context(
graph_input: dict[str, Any],
) -> LlmWikiRagContext:
selected_ids = resolve_requested_llmwiki_knowledge_base_ids(body)
if not selected_ids:
return LlmWikiRagContext([], 0, "", [], "")
runtime = get_resolved_llmwiki_runtime(getattr(request.app.state, "config", None))
local_config = request.app.state.config.llmwiki.local_wiki_index
if not (local_config.enabled and local_config.internal_search_enabled) and not runtime.weknora_enabled:
return LlmWikiRagContext(selected_ids, 0, "", [], "")
store = _store(request)
if store is None:
return LlmWikiRagContext(selected_ids, 0, "", [], "")
assistant_selected_ids = resolve_requested_assistant_knowledge_base_ids(body)
if not selected_ids and not assistant_selected_ids:
return LlmWikiRagContext([], [], 0, "", [], "")
query = _latest_human_query(graph_input)
if not query:
return LlmWikiRagContext(selected_ids, 0, "", [], "")
return LlmWikiRagContext(selected_ids, assistant_selected_ids, 0, "", [], "")
user_id, is_admin = await _actor(request)
rows: list[dict[str, Any]] = []
for mapping_id in selected_ids:
row = await store.get_authorized(mapping_id, user_id, write=False, is_admin=is_admin)
if row is None:
raise HTTPException(status_code=404, detail=f"Knowledge base {mapping_id} not found")
rows.append(row)
search_service = getattr(request.app.state, "llmwiki_retrieval_service", None)
if search_service is None:
return LlmWikiRagContext(
selected_ids,
0,
"Wiki 检索暂不可用。请明确说明系统检索不可用,不要表述为资料不存在。",
[],
query,
)
try:
payload = await search_service.search(query, rows, top_k_pages=_MAX_SOURCES)
except WikiIndexError as exc:
logger.warning("Wiki-only pre-retrieval failed user=%s kb_count=%s code=%s", sanitize_log_param(user_id), len(rows), exc.code)
return LlmWikiRagContext(selected_ids, 0, f"Wiki 检索暂不可用({exc.code})。请明确说明系统检索状态,不要声称知识库没有资料。", [], query)
mapping_by_id = {str(row["id"]): row for row in rows}
sources: list[dict[str, Any]] = []
for result in payload.get("results") or []:
mapping = mapping_by_id.get(str(result.get("knowledge_base_id") or ""))
if mapping is None:
continue
sources.append(_source_from_result(result, mapping, len(sources) + 1))
if len(sources) >= _MAX_SOURCES:
break
return LlmWikiRagContext(selected_ids, len(sources), _build_prompt(query, sources), sources, query)
runtime = get_resolved_llmwiki_runtime(getattr(request.app.state, "config", None))
local_config = request.app.state.config.llmwiki.local_wiki_index
user_id, is_admin = await _actor(request)
if selected_ids:
llmwiki_available = (local_config.enabled and local_config.internal_search_enabled) or runtime.weknora_enabled
store = _store(request)
if not llmwiki_available or store is None:
if not assistant_selected_ids:
return LlmWikiRagContext(selected_ids, assistant_selected_ids, 0, "", [], query)
else:
rows: list[dict[str, Any]] = []
for mapping_id in selected_ids:
row = await store.get_authorized(mapping_id, user_id, write=False, is_admin=is_admin)
if row is None:
raise HTTPException(status_code=404, detail=f"Knowledge base {mapping_id} not found")
rows.append(row)
search_service = getattr(request.app.state, "llmwiki_retrieval_service", None)
if search_service is None:
if not assistant_selected_ids:
return LlmWikiRagContext(
selected_ids,
assistant_selected_ids,
0,
"Wiki 检索暂不可用。请明确说明系统检索不可用,不要表述为资料不存在。",
[],
query,
)
try:
payload = (
await search_service.search(query, rows, top_k_pages=_MAX_SOURCES)
if search_service is not None
else {"results": []}
)
except WikiIndexError as exc:
logger.warning(
"Wiki-only pre-retrieval failed user=%s kb_count=%s code=%s",
sanitize_log_param(user_id),
len(rows),
exc.code,
)
if not assistant_selected_ids:
return LlmWikiRagContext(
selected_ids,
assistant_selected_ids,
0,
f"Wiki 检索暂不可用({exc.code})。请明确说明系统检索状态,不要声称知识库没有资料。",
[],
query,
)
payload = {"results": []}
mapping_by_id = {str(row["id"]): row for row in rows}
for result in payload.get("results") or []:
mapping = mapping_by_id.get(str(result.get("knowledge_base_id") or ""))
if mapping is None:
continue
sources.append(_source_from_result(result, mapping, len(sources) + 1))
if len(sources) >= _MAX_SOURCES:
break
if assistant_selected_ids and len(sources) < _MAX_SOURCES:
assistant_store = _assistant_store(request)
if assistant_store is not None:
rows = await assistant_store.search_pages(
base_ids=assistant_selected_ids,
query=query,
limit=_MAX_SOURCES - len(sources),
include_chunks=True,
embedding_client=getattr(request.app.state, "llmwiki_embedding", None),
)
for row in rows:
sources.append(_source_from_assistant_result(row, len(sources) + 1))
if len(sources) >= _MAX_SOURCES:
break
return LlmWikiRagContext(
selected_ids,
assistant_selected_ids,
len(sources),
_build_prompt(query, sources),
sources,
query,
)
def attach_llmwiki_rag_to_graph_input(
@@ -294,6 +394,7 @@ def attach_llmwiki_rag_to_graph_input(
existing = str(extra.get("prompt_prefix") or "").strip()
extra["prompt_prefix"] = f"{existing}\n\n{rag.prompt}".strip() if existing else rag.prompt
extra["llmwiki_knowledge_base_ids"] = rag.knowledge_base_ids
extra["assistant_knowledge_base_ids"] = rag.assistant_knowledge_base_ids
extra["llmwiki_reference_query"] = rag.query
if rag.sources:
extra["llmwiki_reference_sources"] = rag.sources