feat(knowledge): 支持文件导入沉淀知识,知识图谱可视化随主题切换
- 后端新增 /api/knowledge/ingest/file:上传 md/txt/pdf/word/ppt/excel, 转 Markdown 后走 wiki-capture LLM 蒸馏为陈述式知识笔记,失败回退逐字草稿 - service.capture_file + 文档专用蒸馏提示词,按主题拆分 1~4 页 - 知识图谱导出 HTML 支持 ?theme=light|dark,布局稳定后冻结, 按度数缩放节点,悬停/点击聚焦邻居 - 前端知识库页新增「导入文件」对话框与 ingestKnowledgeFile API - 智能体问答页与简介侧边栏 UI 优化;批量人物蒸馏脚本提取正文逻辑修正 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
17bb3715d1
commit
3845d5090b
14 files changed
+1040
-352
No files matched your search
@@ -13,9 +13,12 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import mimetypes
|
||||
import re
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from fastapi import APIRouter, BackgroundTasks, HTTPException, Request
|
||||
from fastapi import APIRouter, BackgroundTasks, File, Form, HTTPException, Request, UploadFile
|
||||
from fastapi.responses import FileResponse
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
@@ -26,6 +29,12 @@ from deerflow.knowledge.service import EmptyThreadError
|
||||
from deerflow.runtime import serialize_channel_values
|
||||
from deerflow.runtime.references import build_reference_batches
|
||||
from deerflow.runtime.user_context import get_effective_user_id
|
||||
from deerflow.utils.file_conversion import CONVERTIBLE_EXTENSIONS, convert_file_to_markdown
|
||||
|
||||
# Plain-text/markdown files are read directly; binary documents are converted.
|
||||
_TEXT_EXTENSIONS = {".md", ".markdown", ".txt", ".text", ""}
|
||||
# Bound the in-memory read so a knowledge import can't OOM the gateway.
|
||||
_MAX_IMPORT_BYTES = 25 * 1024 * 1024
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
router = APIRouter(prefix="/api/knowledge", tags=["knowledge"])
|
||||
@@ -299,6 +308,80 @@ async def ingest_threads_batch(body: BatchIngestRequest, request: Request) -> di
|
||||
return {"ok": True, "processed": len(items), "created": created, "skipped": skipped, "failed": failed, "llm_fallback": llm_fallback, "items": items}
|
||||
|
||||
|
||||
async def _extract_upload_text(file: UploadFile) -> tuple[str, str]:
|
||||
"""Read an uploaded file and return ``(filename, markdown_text)``.
|
||||
|
||||
Plain-text/markdown is decoded directly; PDF/Office documents are converted
|
||||
to Markdown via the shared converter. Raises ``HTTPException`` on empty /
|
||||
oversized / unsupported / unparseable files.
|
||||
"""
|
||||
name = file.filename or "document"
|
||||
ext = Path(name).suffix.lower()
|
||||
raw = await file.read()
|
||||
if not raw:
|
||||
raise HTTPException(status_code=400, detail="文件为空")
|
||||
if len(raw) > _MAX_IMPORT_BYTES:
|
||||
raise HTTPException(status_code=413, detail=f"文件过大,最大支持 {_MAX_IMPORT_BYTES // (1024 * 1024)}MB")
|
||||
|
||||
if ext in _TEXT_EXTENSIONS:
|
||||
text = raw.decode("utf-8", errors="ignore")
|
||||
elif ext in CONVERTIBLE_EXTENSIONS:
|
||||
# Convert in an isolated temp dir; a fixed safe name avoids path issues
|
||||
# while preserving the extension so the converter detects the type.
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
tmp_path = Path(tmp) / f"import{ext}"
|
||||
tmp_path.write_bytes(raw)
|
||||
md_path = await convert_file_to_markdown(tmp_path)
|
||||
if md_path is None:
|
||||
raise HTTPException(status_code=422, detail=f"无法解析文件:{name}")
|
||||
text = md_path.read_text(encoding="utf-8", errors="ignore")
|
||||
else:
|
||||
raise HTTPException(status_code=415, detail=f"不支持的文件类型:{ext or '未知'}(支持 md/txt/pdf/word/ppt/excel)")
|
||||
|
||||
if not text.strip():
|
||||
raise HTTPException(status_code=422, detail="文件内容为空或无法提取文本")
|
||||
return name, text
|
||||
|
||||
|
||||
@router.post("/ingest/file")
|
||||
@require_auth
|
||||
async def ingest_file(
|
||||
request: Request,
|
||||
file: UploadFile = File(...),
|
||||
title: str | None = Form(default=None),
|
||||
tags: str | None = Form(default=None),
|
||||
status: str = Form(default="approved"),
|
||||
model_name: str | None = Form(default=None),
|
||||
) -> dict[str, Any]:
|
||||
"""Import an uploaded file into the knowledge base as wiki note(s).
|
||||
|
||||
Converts the file to Markdown, distills it via the wiki-capture LLM pipeline
|
||||
(same as thread capture), and writes the resulting declarative note(s) into
|
||||
the shared vault. ``tags`` is a comma/space-separated string.
|
||||
"""
|
||||
service = get_knowledge_service(request)
|
||||
name, text = await _extract_upload_text(file)
|
||||
tag_list = [t for t in re.split(r"[,,\s]+", tags or "") if t]
|
||||
try:
|
||||
result = await service.capture_file(
|
||||
content_md=text,
|
||||
filename=name,
|
||||
title=(title or None),
|
||||
tags=tag_list,
|
||||
status=status,
|
||||
created_by=get_effective_user_id(),
|
||||
model_name=(model_name or None),
|
||||
)
|
||||
except EmptyThreadError:
|
||||
raise HTTPException(status_code=422, detail="文件内容无可沉淀的知识")
|
||||
return {
|
||||
"note": result["note"],
|
||||
"created": result["created"],
|
||||
"notes": result.get("notes", [result["note"]]),
|
||||
"llm_fallback": result.get("llm_fallback", False),
|
||||
}
|
||||
|
||||
|
||||
@router.post("/ingest/search")
|
||||
@require_auth
|
||||
async def ingest_search(body: IngestSearchRequest, request: Request) -> dict[str, Any]:
|
||||
|
||||
Reference in new issue
Block a user