优化输出

zhaoqingang

2025-02-27 345f2822f5072c34d9f969ae077830af968043b9

 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版本 >= 1.14.0


async def update_session_log(db, session_id: str, message: dict, conversation_id: str):
@@ -23,13 +28,13 @@


async def add_session_log(db, session_id: str, question: str, chat_id: str, user_id, event_type: str,
                          conversation_id: str):
                          conversation_id: str, agent_type):
    try:
        session = await ChatSessionDao(db).update_or_insert_by_id(
            session_id=session_id,
            name=question[:255],
            agent_id=chat_id,
            agent_type=1,
            agent_type=agent_type,
            tenant_id=user_id,
            message={"role": "user", "content": question},
            conversation_id=conversation_id,
@@ -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):
@@ -66,7 +88,7 @@
    token = await get_chat_token(db, rg_api_token)
    url = settings.fwr_base_url + RG_CHAT_DIALOG.format(chat_id)
    chat = ChatDialog()
    session = await add_session_log(db, session_id, question, chat_id, user_id, mode, session_id)
    session = await add_session_log(db, session_id, question, chat_id, user_id, mode, session_id, 1)
    if session:
        conversation_id = session.conversation_id
    message = {"role": "assistant", "answer": "", "reference": {}}
@@ -102,31 +124,52 @@
        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:
            ...
    finally:
        message["role"] = "assistant"
        await update_session_log(db, session_id, message, conversation_id)

async def data_process(data):
    if isinstance(data, str):
        return data.replace("dify", "smart")
    elif isinstance(data, dict):
        for k in list(data.keys()):
            if isinstance(k, str) and "dify" in k:
                new_k = k.replace("dify", "smart")
                data[new_k] = await data_process(data[k])
                del data[k]
            else:
                data[k] = await data_process(data[k])
        return data
    elif isinstance(data, list):
        for i in range(len(data)):
            data[i] = await data_process(data[i])
        return data
    else:
        return data


async def service_chat_workflow(db, chat_id: str, chat_data: ChatData, session_id: str, user_id, mode: str):
    conversation_id = ""
    answer_event = ""
    answer_agent = ""
    answer_workflow = ""
    download_url = ""
    message_id = ""
    task_id = ""
    error = ""
    files = []
    node_list = []
    token = await get_chat_token(db, chat_id)

    chat, url = await get_chat_object(mode)
    if hasattr(chat_data, "query"):
        query = chat_data.query
    else:
        query = "start new workflow"
    session = await add_session_log(db, session_id, query, chat_id, user_id, mode, conversation_id)
    session = await add_session_log(db, session_id,query if query else "start new conversation", chat_id, user_id, mode, conversation_id, 3)
    if session:
        conversation_id = session.conversation_id
    try:
@@ -158,16 +201,26 @@
                event = smart_message_file
            elif ans.get("event") in [workflow_started, node_started, node_finished]:
                data = ans.get("data", {})
                data["inputs"] = []
                data["outputs"] = []
                data["inputs"] = await data_process(data.get("inputs", {}))
                data["outputs"] = await data_process(data.get("outputs", {}))
                data["files"] = await data_process(data.get("files", []))
                data["process_data"] = ""
                if data.get("status") == "failed":
                    status = http_500
                    error = data.get("error", "")
                node_list.append(ans)
                event = [smart_workflow_started, smart_node_started, smart_node_finished][
                    [workflow_started, node_started, node_finished].index(ans.get("event"))]
            elif ans.get("event") == workflow_finished:
                data = ans.get("data", {})
                answer_workflow = data.get("outputs", {}).get("output")
                download_url = data.get("outputs", {}).get("download_url")
                event = smart_workflow_finished
                if data.get("status") == "failed":
                    status = http_500
                    error = data.get("error", "")
                node_list.append(ans)

            elif ans.get("event") == message_end:
                event = smart_message_end
            else:
@@ -182,17 +235,18 @@
        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:
            ...
    finally:
        await update_session_log(db, session_id, {"role": "assistant", "answer": answer_event or answer_agent,
        await update_session_log(db, session_id, {"role": "assistant", "answer": answer_event or answer_agent or answer_workflow or error,
                                                  "download_url":download_url,
                                                  "node_list": node_list, "task_id": task_id, "id": message_id,
                                                  "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):
    ...


@@ -200,22 +254,7 @@
    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

async def service_chat_sessions(db, chat_id, name):
    token = await get_chat_token(db, rg_api_token)
@@ -224,3 +263,83 @@
    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_sessions_list(db, chat_id, current, page_size, user_id, keyword):
    total, session_list = await ChatSessionDao(db).get_session_list(
        user_id=user_id,
        agent_id=chat_id,
        keyword=keyword,
        page=current,
        page_size=page_size
    )
    return json.dumps({"total":total, "rows": [session.to_dict() for session in session_list]})



async def service_chat_session_log(db, session_id):
    session_log = await ChatSessionDao(db).get_session_by_id(session_id)
    return json.dumps(session_log.log_to_json())



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):
    # 获取tokenizer对象，目前只支持通义千问系列模型
    tokenizer = get_tokenizer('qwen-turbo')
    # 将字符串切分成token并转换为token id
    tokens = tokenizer.encode(input_str)
    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):
    # 使用 python-docx 打开 Word 文件流
    doc = Document(io.BytesIO(word_stream))

    # 提取每个段落的文本
    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'):

        # 提取 PDF 内容
        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)