ouyangyouzhang/QueryRewrite
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

新增对话处理功能，优化意图识别逻辑，添加结果保存至Excel的功能，更新依赖项以支持新的数据库驱动和ORM，重构代码以提高可读性和维护性，删除冗余文件以简化项目结构。

Browse Source
This commit is contained in:
ouyangyouzhang
2025-06-10 17:00:40 +08:00
parent ea705756fa
commit 2e91063ad1
11 changed files with 653 additions and 493 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rag2_0/dify/test_dify_chatapi.py
+57 -56
View File
@@ -2,7 +2,8 @@
# -*- coding: utf-8 -*-
import os
from rag2_0.dify.dify_client import ChatClient, DifyClient
from rag2_0.dify.dify_client import DifyClient
from rag2_0.dify.dify_tool import NewWorkflowChat, OldWorkFlowChat
import pandas as pd
# 使用线程池并发执行
from concurrent.futures import ThreadPoolExecutor, as_completed
@@ -44,8 +45,9 @@ class DifyComparisonTester:
max_workers: 最大工作线程数
"""
self.excel_path = excel_path
self.old_chat = ChatClient(api_key=old_workflow_api_key, base_url=baseurl)
self.new_chat = ChatClient(api_key=new_workflow_api_key, base_url=baseurl)
# 使用NewWorkflowChat和OldWorkFlowChat代替ChatClient
self.old_chat = OldWorkFlowChat(api_key=old_workflow_api_key, base_url=baseurl)
self.new_chat = NewWorkflowChat(api_key=new_workflow_api_key, base_url=baseurl)
# 评判相关参数
self.output_path = output_path or os.path.join(os.path.dirname(self.excel_path), "dify问答_综合评判结果.xlsx")
@@ -78,13 +80,13 @@ class DifyComparisonTester:
"""
def get_old_answer():
try:
return self.old_chat.create_chat_message(inputs={}, query=q, user="AutoTestDifyChat").json()
return self.old_chat.process_question(query=q)
except Exception as e:
return f"error: {str(e)}"
def get_new_answer():
try:
return self.new_chat.create_chat_message(inputs={}, query=q, user="AutoTestDifyChat").json()
return self.new_chat.process_question(query=q)
except Exception as e:
return f"error: {str(e)}"
@@ -95,14 +97,15 @@ class DifyComparisonTester:
try:
old_result = future_old.result()
new_result = future_new.result()
old_message_id = old_result["message_id"]
new_message_id = new_result["message_id"]
if isinstance(old_result, str) and old_result.startswith("error:"):
return None, None
if isinstance(new_result, str) and new_result.startswith("error:"):
return None, None
old_answer = old_result["answer"]
new_answer = new_result["answer"]
except Exception as e:
return None, None, None
return {"问题": q, "旧流程答案": old_answer, "新流程答案": new_answer}, old_message_id, new_message_id
return future_old, future_new
def find_wiki_link(self, query) -> str | None:
"""
@@ -407,22 +410,24 @@ content: "{content}"
Returns:
dict: 包含问题分类结果的字典
"""
retrieve_title=[]
retrieve_content=[]
max_score=0
min_score=0
avg_score=0
rewrite_query=""
vertical_classification=""
sub_classification=""
slot_info=""
try:
# 使用DifyTool直接获取消息信息
new_message_info = DifyTool.get_message_debug_info_by_id(message_id=new_message_id)
# 初始化变量
retrieve_title = []
retrieve_content = []
rewrite_query = ""
vertical_classification = ""
sub_classification = ""
slot_info = ""
# 解析工作流节点信息
for workflow_node in new_message_info["workflow_node_executions_info"]:
if workflow_node["title"] == "知识检索结果后处理":
outputs = json.loads(workflow_node["outputs"])
retrieve_title, max_score, min_score, avg_score = self.get_retrieve_info(query=query, outputs=outputs)
retrieve_content=outputs["result"]
retrieve_content = outputs["result"]
elif workflow_node["title"] == "问题优化结果解析":
outputs = json.loads(workflow_node["outputs"])
rewrite_query = outputs["optimize_query"]
@@ -430,20 +435,21 @@ content: "{content}"
json_result = json.loads(llm_result_json)
vertical_classification = json_result['vertical_classification']
sub_classification = json_result['sub_classification']
slot_info=json.dumps(json_result["slot_filling"],ensure_ascii=False,indent=2)
slot_info = json.dumps(json_result["slot_filling"], ensure_ascii=False, indent=2)
except Exception as e:
return None
return {
"问题改写": rewrite_query,
"检索词条": "\n".join(retrieve_title) if retrieve_title else "未检索知识库",
"检索内容": retrieve_content,
"问题分类": f"{vertical_classification} - {sub_classification}",
"槽点信息":slot_info
"槽点信息": slot_info
}
def get_old_workflow_info(self, query:str, old_message_id:str) -> dict:
"""
获取新流程的问题分类
获取旧流程的问题分类
Args:
query (str): 用户问题
@@ -452,24 +458,27 @@ content: "{content}"
Returns:
dict: 包含问题分类结果的字典
"""
retrieve_title=[]
retrieve_content=[]
max_score=0
min_score=0
avg_score=0
rewrite_query=""
try:
# 使用DifyTool直接获取消息信息
old_message_info = DifyTool.get_message_debug_info_by_id(message_id=old_message_id)
# 初始化变量
retrieve_title = []
retrieve_content = []
rewrite_query = ""
# 解析工作流节点信息
for workflow_node in old_message_info["workflow_node_executions_info"]:
if workflow_node["title"] == "知识检索结果后处理":
outputs = json.loads(workflow_node["outputs"])
retrieve_title, max_score, min_score, avg_score = self.get_retrieve_info(query=query, outputs=outputs)
retrieve_content=outputs["result"]
retrieve_content = outputs["result"]
elif workflow_node["title"] == "问题优化结果解析":
outputs = json.loads(workflow_node["outputs"])
rewrite_query = outputs["optimize_query"]
except Exception as e:
return None
return {
"问题改写": rewrite_query,
"检索词条": "\n".join(retrieve_title) if retrieve_title else "未检索知识库",
@@ -512,13 +521,13 @@ content: "{content}"
dict: 包含问题、回答和评判结果的字典
"""
# 获取基本的问题和回答
basic_result, old_message_id, new_message_id = self.process_question(q)
if basic_result is None:
future_old, future_new = self.process_question(q)
if future_old is None or future_new is None:
return None
query = basic_result["问题"]
old_answer = basic_result["旧流程答案"]
new_answer = basic_result["新流程答案"]
query = future_old["问题"]
old_answer = future_old["旧流程答案"]
new_answer = future_new["新流程答案"]
# 获取词条链接和标准答案
wiki_url = self.find_wiki_link(query)
@@ -540,33 +549,23 @@ content: "{content}"
if judge_result is None:
judge_result = ""
# retrieve_title_score = self.get_retrieve_title_similarity(old_retrieve_content=old_workflow_info["检索内容"], new_retrieve_content=new_workflow_info["检索内容"])
# 并行获取新旧流程信息
with ThreadPoolExecutor(max_workers=2) as executor:
future_new = executor.submit(self.get_new_workflow_info, query=query, new_message_id=new_message_id)
future_old = executor.submit(self.get_old_workflow_info, query=query, old_message_id=old_message_id)
try:
new_workflow_info = future_new.result()
old_workflow_info = future_old.result()
except Exception as e:
print(f"处理问题 '{query}' 获取工作流信息时发生错误: {str(e)}")
return None
retrieve_title_score=self.get_retrieve_title_similarity(old_retrieve_content=old_workflow_info["检索内容"], new_retrieve_content=new_workflow_info["检索内容"])
# 返回结果
return {
"问题": query,
"新问题改写": new_workflow_info["问题改写"],
"旧问题改写": old_workflow_info["问题改写"],
"新问题分类": new_workflow_info["问题分类"],
"槽点信息":new_workflow_info["槽点信息"],
"新问题改写": future_new["问题改写"],
"旧问题改写": future_old["问题改写"],
"新问题分类": future_new["问题分类"],
"槽点信息": future_new["槽点信息"],
"新流程答案": new_answer,
"旧流程答案": old_answer,
"回答判断": judge_result,
"词条检索相似度": retrieve_title_score,
# "词条检索相似度": retrieve_title_score,
"答案词条": answer_title if answer_title else "",
"新检索词条": new_workflow_info["检索词条"],
"旧检索词条": old_workflow_info["检索词条"],
"新检索词条": future_new["检索词条"],
"旧检索词条": future_old["检索词条"],
}
def run_comparison(self, with_judge=False):
@@ -670,5 +669,7 @@ if __name__ == "__main__":
print(f"对比评判结果已保存至: {output_file}")
# 单个问题测试示例
# c = DifyChat(baseurl="http://172.20.0.145/v1", api_key="app-LjJaeLoAfqa6aoGzqU9UvxSf")
# c.chat("如何新建配电线路工程")
# 使用新的工作流类进行测试
# new_chat = NewWorkflowChat(api_key="app-qxsSybCs7ABiKlC1JabTYVn6", base_url="http://172.20.0.145/v1")
# result = new_chat.process_question("如何新建配电线路工程")
# print(json.dumps(result, ensure_ascii=False, indent=2))