From 124bfc93ed2d3702cf9d9af9ff9b5985ec2b7b45 Mon Sep 17 00:00:00 2001
From: zhaoqingang <zhaoqg0118@163.com>
Date: 星期二, 18 二月 2025 15:51:23 +0800
Subject: [PATCH] commit

---
 app/service/v2/chat.py |  134 ++++++++++++++++++++++++++++++++++++++------
 1 files changed, 114 insertions(+), 20 deletions(-)

diff --git a/app/service/v2/chat.py b/app/service/v2/chat.py
index ddd17a2..246b3f1 100644
--- a/app/service/v2/chat.py
+++ b/app/service/v2/chat.py
@@ -1,16 +1,21 @@
+import io
 import json
+
+import fitz
 
 from Log import logger
 from app.config.agent_base_url import RG_CHAT_DIALOG, DF_CHAT_AGENT, DF_CHAT_PARAMETERS, RG_CHAT_SESSIONS, \
-    DF_CHAT_WORKFLOW
+    DF_CHAT_WORKFLOW, DF_UPLOAD_FILE
 from app.config.config import settings
 from app.config.const import *
-from app.models import DialogModel, ApiTokenModel
+from app.models import DialogModel, ApiTokenModel, UserTokenModel
 from app.models.v2.session_model import ChatSessionDao, ChatData
 from app.service.v2.app_driver.chat_agent import ChatAgent
 from app.service.v2.app_driver.chat_data import ChatBaseApply
 from app.service.v2.app_driver.chat_dialog import ChatDialog
 from app.service.v2.app_driver.chat_workflow import ChatWorkflow
+from docx import Document
+from dashscope import get_tokenizer  # dashscope鐗堟湰 >= 1.14.0
 
 
 async def update_session_log(db, session_id: str, message: dict, conversation_id: str):
@@ -40,12 +45,29 @@
         logger.error(e)
     return None
 
+async def get_app_token(db, app_id):
+    app_token = db.query(UserTokenModel).filter_by(id=app_id).first()
+    if app_token:
+        return app_token.access_token
+    return ""
+
+
 
 async def get_chat_token(db, app_id):
     app_token = db.query(ApiTokenModel).filter_by(app_id=app_id).first()
     if app_token:
         return app_token.token
     return ""
+
+
+async def add_chat_token(db, data):
+    try:
+        api_token = ApiTokenModel(**data)
+        db.add(api_token)
+        db.commit()
+    except Exception as e:
+        logger.error(e)
+
 
 
 async def get_chat_info(db, chat_id: str):
@@ -102,7 +124,7 @@
         logger.error(e)
         try:
             yield "data: " + json.dumps({"message": smart_message_error,
-                                         "error": "**ERROR**: " + str(e), "status": http_500},
+                                         "error": "\n**ERROR**: " + str(e), "status": http_500},
                                         ensure_ascii=False) + "\n\n"
         except:
             ...
@@ -168,6 +190,7 @@
                 data = ans.get("data", {})
                 event = smart_workflow_finished
                 node_list.append(ans)
+
             elif ans.get("event") == message_end:
                 event = smart_message_end
             else:
@@ -182,7 +205,7 @@
         logger.error(e)
         try:
             yield "data: " + json.dumps({"message": smart_message_error,
-                                         "error": "**ERROR**: " + str(e), "status": http_500},
+                                         "error": "\n**ERROR**: " + str(e), "status": http_500},
                                         ensure_ascii=False) + "\n\n"
         except:
             ...
@@ -192,7 +215,7 @@
                                                   "error": error}, conversation_id)
 
 
-async def service_chat_basic(db, chat_id: str, question: str, session_id: str, user_id):
+async def service_chat_basic(db, chat_id: str, chat_data: ChatData, session_id: str, user_id, mode: str):
     ...
 
 
@@ -200,21 +223,22 @@
     chat_info = db.query(DialogModel).filter_by(id=chat_id).first()
     if not chat_info:
         return {}
-    if chat_info.dialog_type == RG_TYPE:
-        return {"retriever_resource":
-            {
-                "enabled": True
-            }
-        }
-    elif chat_info.dialog_type == BASIC_TYPE:
-        ...
-    elif chat_info.dialog_type == DF_TYPE:
-        token = await get_chat_token(db, chat_id)
-        if not token:
-            return {}
-        url = settings.dify_base_url + DF_CHAT_PARAMETERS
-        chat = ChatBaseApply()
-        return await chat.chat_get(url, {"user": str(user_id)}, await chat.get_headers(token))
+    return chat_info.parameters
+    # if chat_info.dialog_type == RG_TYPE:
+    #     return {"retriever_resource":
+    #         {
+    #             "enabled": True
+    #         }
+    #     }
+    # elif chat_info.dialog_type == BASIC_TYPE:
+    #     ...
+    # elif chat_info.dialog_type == DF_TYPE:
+    #     token = await get_chat_token(db, chat_id)
+    #     if not token:
+    #         return {}
+    #     url = settings.dify_base_url + DF_CHAT_PARAMETERS
+    #     chat = ChatBaseApply()
+    #     return await chat.chat_get(url, {"user": str(user_id)}, await chat.get_headers(token))
 
 
 async def service_chat_sessions(db, chat_id, name):
@@ -224,3 +248,73 @@
     url = settings.fwr_base_url + RG_CHAT_SESSIONS.format(chat_id)
     chat = ChatDialog()
     return await chat.chat_sessions(url, {"name": name}, await chat.get_headers(token))
+
+
+async def service_chat_upload(db, chat_id, file, user_id):
+    files = []
+    token = await get_chat_token(db, chat_id)
+    if not token:
+        return files
+    url = settings.dify_base_url + DF_UPLOAD_FILE
+    chat = ChatBaseApply()
+    for f in file:
+        try:
+            file_content = await f.read()
+            file_upload = await chat.chat_upload(url, {"file": (f.filename, file_content)}, {"user": str(user_id)},
+                                                 {'Authorization': f'Bearer {token}'})
+            try:
+                tokens = await read_file(file_content, f.filename, f.content_type)
+                file_upload["tokens"] = tokens
+            except:
+                ...
+            files.append(file_upload)
+        except Exception as e:
+            logger.error(e)
+    return json.dumps(files) if files else ""
+
+
+async def get_str_token(input_str):
+    # 鑾峰彇tokenizer瀵硅薄锛岀洰鍓嶅彧鏀寔閫氫箟鍗冮棶绯诲垪妯″瀷
+    tokenizer = get_tokenizer('qwen-turbo')
+    # 灏嗗瓧绗︿覆鍒囧垎鎴恡oken骞惰浆鎹负token id
+    tokens = tokenizer.encode(input_str)
+    # print(f"缁忚繃鍒囧垎鍚庣殑token id涓猴細{tokens}銆�")
+    # # 缁忚繃鍒囧垎鍚庣殑token id涓猴細 [31935, 64559, 99320, 56007, 100629, 104795, 99788, 1773]
+    # print(f"缁忚繃鍒囧垎鍚庡叡鏈墈len(tokens)}涓猼oken")
+    # # 缁忚繃鍒囧垎鍚庡叡鏈�8涓猼oken
+    #
+    # # 灏唗oken id杞寲涓哄瓧绗︿覆骞舵墦鍗板嚭鏉�
+    # for i in range(len(tokens)):
+    #     print(f"token id涓簕tokens[i]}瀵瑰簲鐨勫瓧绗︿覆涓猴細{tokenizer.decode(tokens[i])}")
+    return len(tokens)
+
+async def read_pdf(pdf_stream):
+    text = ""
+    with fitz.open(stream=pdf_stream, filetype="pdf") as pdf_document:
+        for page in pdf_document:
+            text += page.get_text()
+    return text
+
+
+async def read_word(word_stream):
+    # 浣跨敤 python-docx 鎵撳紑 Word 鏂囦欢娴�
+    doc = Document(io.BytesIO(word_stream))
+
+    # 鎻愬彇姣忎釜娈佃惤鐨勬枃鏈�
+    text = ""
+    for para in doc.paragraphs:
+        text += para.text
+
+    return text
+
+async def read_file(file, filename, content_type):
+    text = ""
+    if content_type == "application/pdf" or filename.endswith('.pdf'):
+
+        # 鎻愬彇 PDF 鍐呭
+        text = await read_pdf(file)
+    elif content_type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document" or filename.endswith(
+            '.docx'):
+        text = await read_word(file)
+
+    return await get_str_token(text)

--
Gitblit v1.8.0