From 1ab90de913405b45050e0f732a03004087134fda Mon Sep 17 00:00:00 2001
From: zhaoqingang <zhaoqg0118@163.com>
Date: 星期一, 25 十一月 2024 11:11:04 +0800
Subject: [PATCH] 上传dify文件
---
app/api/files.py | 183 +++++++++++++++++++++++++++++++++++++++++----
1 files changed, 165 insertions(+), 18 deletions(-)
diff --git a/app/api/files.py b/app/api/files.py
index 5e2640b..22c2216 100644
--- a/app/api/files.py
+++ b/app/api/files.py
@@ -1,44 +1,191 @@
-from fastapi import Depends, APIRouter, HTTPException, UploadFile, File, requests
+import io
+from typing import Optional, List
+
+import requests
+from fastapi import Depends, APIRouter, HTTPException, UploadFile, File, Query, Form
+from pydantic import BaseModel
from sqlalchemy.orm import Session
+from starlette.responses import StreamingResponse
+from werkzeug.utils import send_file
from app.api import Response, get_current_user, ResponseList
from app.config.config import settings
from app.models.agent_model import AgentType, AgentModel
from app.models.base_model import get_db
from app.models.user_model import UserModel
+from app.service.basic import BasicService
from app.service.bisheng import BishengService
+from app.service.difyService import DifyService
from app.service.ragflow import RagflowService
-from app.service.token import get_ragflow_token, get_bisheng_token
+from app.service.service_token import get_ragflow_token, get_bisheng_token
+import urllib.parse
router = APIRouter()
@router.post("/upload/{agent_id}", response_model=Response)
-async def upload_file(agent_id: str,
- file: UploadFile = File(...),
- db: Session = Depends(get_db),
- current_user: UserModel = Depends(get_current_user)
- ):
+async def upload_files(
+ agent_id: str,
+ file: List[UploadFile] = File(...), # 淇敼杩欓噷锛屾帴鍙楁枃浠跺垪琛�
+ chat_id: str = Query(None, description="The ID of the chat"),
+ db: Session = Depends(get_db),
+ current_user: UserModel = Depends(get_current_user)
+):
agent = db.query(AgentModel).filter(AgentModel.id == agent_id).first()
if not agent:
return Response(code=404, msg="Agent not found")
- # 璇诲彇涓婁紶鐨勬枃浠跺唴瀹�
- try:
- file_content = await file.read()
- except Exception as e:
- return Response(code=400, msg=str(e))
- if agent.agent_type == AgentType.RAGFLOW:
- pass
+ # 妫�鏌� agent 绫诲瀷锛岀‘瀹氭槸鍚﹀厑璁镐笂浼犲涓枃浠�
+ if agent.agent_type in [AgentType.RAGFLOW, AgentType.BISHENG]:
+ if len(file) > 1:
+ return Response(code=400, msg="杩欎釜鏅鸿兘浣撳彧鏀寔浼犲崟涓枃浠�")
- elif agent.agent_type == AgentType.BISHENG:
- bisheng_service = BishengService(base_url=settings.bisheng_base_url)
+ if agent.agent_type == AgentType.RAGFLOW or agent.agent_type == AgentType.BISHENG:
+ file = file[0]
+ # 璇诲彇涓婁紶鐨勬枃浠跺唴瀹�
+ try:
+ file_content = await file.read()
+ except Exception as e:
+ return Response(code=400, msg=str(e))
+
+ if agent.agent_type == AgentType.RAGFLOW:
+ token = get_ragflow_token(db, current_user.id)
+ ragflow_service = RagflowService(base_url=settings.fwr_base_url)
+ # 鏌ヨ浼氳瘽鏄惁瀛樺湪锛屼笉瀛樺湪鍏堝垱寤轰細璇�
+ history = await ragflow_service.get_session_history(token, chat_id)
+ if len(history) == 0:
+ message = {"role": "user", "message": file.filename}
+ await ragflow_service.set_session(token, agent_id, message, chat_id, True)
+
+ doc_ids = await ragflow_service.upload_and_parse(token, chat_id, file.filename, file_content)
+ # 瀵逛簬澶氭枃浠讹紝鍙兘闇�瑕佹敹闆嗘墍鏈塪oc_ids
+ return Response(code=200, msg="", data={"doc_ids": doc_ids, "file_name": file.filename})
+
+ elif agent.agent_type == AgentType.BISHENG:
+ bisheng_service = BishengService(base_url=settings.sgb_base_url)
+ try:
+ token = get_bisheng_token(db, current_user.id)
+ result = await bisheng_service.upload(token, file.filename, file_content)
+ except Exception as e:
+ raise HTTPException(status_code=500, detail=str(e))
+ result["file_name"] = file.filename
+ return Response(code=200, msg="", data=result)
+
+ elif agent.agent_type == AgentType.BASIC:
+ if agent_id == "basic_excel_talk":
+ # 澶勭悊鍗曚釜鏂囦欢鐨勬儏鍐�
+ file_list = file
+ if len(file) == 1 and agent.agent_type != AgentType.BASIC:
+ file_list = [file[0]] # 濡傛灉鍙湁涓�涓枃浠讹紝纭繚瀹冩槸涓�涓垪琛�
+ service = BasicService(base_url=settings.basic_base_url)
+ # 閬嶅巻file_list锛屽瓨鍒癴iles 鍒楄〃涓�
+ files = []
+ for item in file_list:
+ file_content = await item.read()
+ files.append(('files', (item.filename, file_content, 'application/octet-stream')))
+
+ result = await service.excel_talk_upload(chat_id, files)
+ if not result:
+ return Response(code=400, msg="涓婁紶鏂囦欢鍑洪敊")
+
+ return Response(code=200, msg="", data=result)
+
+ elif agent_id == "basic_paper_agent":
+ service = BasicService(base_url=settings.basic_paper_url)
+ result = await service.paper_file_upload(chat_id, file.filename, file_content)
+
+ elif agent.agent_type == AgentType.DIFY:
+ file = file[0]
+ # 璇诲彇涓婁紶鐨勬枃浠跺唴瀹�
+ try:
+ file_content = await file.read()
+ except Exception as e:
+ return Response(code=400, msg=str(e))
+ dify_service = DifyService(base_url=settings.dify_base_url)
try:
token = get_bisheng_token(db, current_user.id)
- result = await bisheng_service.upload(token, file.filename, file_content)
+ result = await dify_service.upload(token, file.filename, file_content, current_user.id)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
+ result["file_name"] = file.filename
return Response(code=200, msg="", data=result)
+ return Response(code=200, msg="", data=result)
+
+
+@router.get("/download/", response_model=Response)
+async def download_file(
+ url: Optional[str] = Query(None, description="URL of the file to download for bisheng"),
+ agent_id: str = Query(..., description="Agent ID"),
+ doc_id: Optional[str] = Query(None, description="Optional doc id for ragflow agents"),
+ doc_name: Optional[str] = Query(None, description="Optional doc name for ragflow agents"),
+ file_id: Optional[str] = Query(None, description="Optional file id for basic agents"),
+ file_type: Optional[str] = Query(None, description="Optional file type for basic agents"),
+ db: Session = Depends(get_db)
+):
+ agent = db.query(AgentModel).filter(AgentModel.id == agent_id).first()
+ if not agent:
+ return Response(code=404, msg="Agent not found")
+
+ if agent.agent_type == AgentType.BISHENG:
+ url = urllib.parse.unquote(url)
+ # 浠� URL 涓彁鍙栨枃浠跺悕
+ parsed_url = urllib.parse.urlparse(url)
+ filename = urllib.parse.unquote(parsed_url.path.split('/')[-1])
+ url = url.replace("http://minio:9000", settings.sgb_base_url)
+ elif agent.agent_type == AgentType.RAGFLOW:
+ if not doc_id:
+ return Response(code=400, msg="doc_id is required")
+ url = f"{settings.fwr_base_url}/v1/document/get/{doc_id}"
+ filename = doc_name
+ elif agent.agent_type == AgentType.BASIC:
+ if agent_id == "basic_excel_talk":
+ return await download_basic_file(file_id, file_type)
+
+ elif agent_id == "basic_question_talk":
+ return await download_basic_file(file_id, file_type)
else:
- return Response(code=200, msg="Unsupported agent type")
+ return Response(code=400, msg="Unsupported agent type")
+
+ try:
+ # 鍙戦�丟ET璇锋眰鑾峰彇鏂囦欢鍐呭
+ response = requests.get(url, stream=True)
+ response.raise_for_status() # 妫�鏌ヨ姹傛槸鍚︽垚鍔�
+
+ # 杩斿洖娴佸紡鍝嶅簲
+ return StreamingResponse(
+ response.iter_content(chunk_size=1024),
+ media_type="application/octet-stream",
+ headers={"Content-Disposition": f"attachment; filename*=utf-8''{urllib.parse.quote(filename)}"}
+ )
+ except Exception as e:
+ raise HTTPException(status_code=400, detail=f"Error downloading file: {e}")
+
+
+async def download_basic_file(file_id: str, file_type: str):
+ service = BasicService(base_url=settings.basic_base_url)
+ if not file_type or not file_id:
+ return Response(code=400, msg="file_type and file_id is required")
+ if file_type == "image":
+ content, filename, mimetype = await service.excel_talk_image_download(file_id)
+ return StreamingResponse(
+ io.BytesIO(content),
+ media_type=mimetype,
+ headers={"Content-Disposition": f"attachment; filename={filename}"}
+ )
+ elif file_type == "excel":
+ content, filename, mimetype = await service.excel_talk_excel_download(file_id)
+ return StreamingResponse(
+ io.BytesIO(content),
+ media_type=mimetype,
+ headers={"Content-Disposition": f"attachment; filename={filename}"}
+ )
+ elif file_type == "word":
+ content, filename, mimetype = await service.questions_talk_word_download(file_id)
+ return StreamingResponse(
+ io.BytesIO(content),
+ media_type=mimetype,
+ headers={"Content-Disposition": f"attachment; filename={filename}"}
+ )
+ else:
+ return Response(code=400, msg="Unsupported file type")
\ No newline at end of file
--
Gitblit v1.8.0