OurCodesAreAllRight/FilesReadSystem
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

添加系统架构图

Browse Source
This commit is contained in:
dj
2026-04-16 23:08:21 +08:00
parent 38b0c7e62e
commit 975ebf536b
8 changed files with 339 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

171
backend/app/services/excel_ai_service.py
View File

@@ -223,6 +223,177 @@ class ExcelAIService:
}
}
async def analyze_excel_file_from_path(
self,
file_path: str,
filename: str,
user_prompt: str = "",
analysis_type: str = "general",
parse_options: Optional[Dict[str, Any]] = None
) -> Dict[str, Any]:
"""
从文件路径分析 Excel 文件（用于从数据库加载的文档）
Args:
file_path: Excel 文件路径
filename: 文件名
user_prompt: 用户自定义提示词
analysis_type: 分析类型
parse_options: 解析选项
Returns:
Dict[str, Any]: 分析结果
"""
# 1. 解析 Excel 文件
excel_data = None
parse_result_metadata = None
try:
parse_options = parse_options or {}
parse_result = self.parser.parse(file_path, **parse_options)
if not parse_result.success:
return {
"success": False,
"error": parse_result.error,
"analysis": None
}
excel_data = parse_result.data
parse_result_metadata = parse_result.metadata
logger.info(f"Excel 解析成功: {parse_result_metadata}")
except Exception as e:
logger.error(f"Excel 解析失败: {str(e)}")
return {
"success": False,
"error": f"Excel 解析失败: {str(e)}",
"analysis": None
}
# 2. 调用 LLM 进行分析
try:
if user_prompt and user_prompt.strip():
llm_result = await self.llm_service.analyze_with_template(
excel_data,
user_prompt
)
else:
llm_result = await self.llm_service.analyze_excel_data(
excel_data,
user_prompt,
analysis_type
)
logger.info(f"AI 分析完成: {llm_result['success']}")
return {
"success": True,
"excel": {
"data": excel_data,
"metadata": parse_result_metadata,
"saved_path": file_path
},
"analysis": llm_result
}
except Exception as e:
logger.error(f"AI 分析失败: {str(e)}")
return {
"success": False,
"error": f"AI 分析失败: {str(e)}",
"excel": {
"data": excel_data,
"metadata": parse_result_metadata
},
"analysis": None
}
async def batch_analyze_sheets_from_path(
self,
file_path: str,
filename: str,
user_prompt: str = "",
analysis_type: str = "general"
) -> Dict[str, Any]:
"""
从文件路径批量分析 Excel 文件的所有工作表（用于从数据库加载的文档）
Args:
file_path: Excel 文件路径
filename: 文件名
user_prompt: 用户自定义提示词
analysis_type: 分析类型
Returns:
Dict[str, Any]: 分析结果
"""
# 1. 解析所有工作表
try:
parse_result = self.parser.parse_all_sheets(file_path)
if not parse_result.success:
return {
"success": False,
"error": parse_result.error,
"analysis": None
}
sheets_data = parse_result.data.get("sheets", {})
logger.info(f"Excel 解析成功，共 {len(sheets_data)} 个工作表")
except Exception as e:
logger.error(f"Excel 解析失败: {str(e)}")
return {
"success": False,
"error": f"Excel 解析失败: {str(e)}",
"analysis": None
}
# 2. 批量分析每个工作表
sheet_analyses = {}
errors = {}
for sheet_name, sheet_data in sheets_data.items():
try:
if user_prompt and user_prompt.strip():
llm_result = await self.llm_service.analyze_with_template(
sheet_data,
user_prompt
)
else:
llm_result = await self.llm_service.analyze_excel_data(
sheet_data,
user_prompt,
analysis_type
)
sheet_analyses[sheet_name] = llm_result
if not llm_result["success"]:
errors[sheet_name] = llm_result.get("error", "未知错误")
logger.info(f"工作表 '{sheet_name}' 分析完成")
except Exception as e:
logger.error(f"工作表 '{sheet_name}' 分析失败: {str(e)}")
errors[sheet_name] = str(e)
# 3. 组合结果
return {
"success": len(errors) == 0,
"excel": {
"sheets": sheets_data,
"metadata": parse_result.metadata,
"saved_path": file_path
},
"analysis": {
"sheets": sheet_analyses,
"total_sheets": len(sheets_data),
"successful": len(sheet_analyses) - len(errors),
"errors": errors
}
}
def get_supported_analysis_types(self) -> List[str]:
"""获取支持的分析类型"""
return [

4
backend/app/services/llm_service.py
View File

@@ -58,7 +58,7 @@ class LLMService:
_start_time = time.time()
logger.info(f"🤖 [LLM] 正在调用 DeepSeek API... 模型: {self.model_name}")
try:
async with httpx.AsyncClient(timeout=60.0) as client:
async with httpx.AsyncClient(timeout=120.0) as client:
response = await client.post(
f"{self.base_url}/chat/completions",
headers=headers,
@@ -84,7 +84,7 @@ class LLMService:
pass
raise
except Exception as e:
logger.error(f"LLM API 调用异常: {str(e)}")
logger.error(f"LLM API 调用异常: {repr(e)} - {str(e)}")
raise
def extract_message_content(self, response: Dict[str, Any]) -> str:

5
backend/app/services/txt_ai_service.py
View File

@@ -19,6 +19,7 @@ class TxtAIService:
def __init__(self):
self.parser = TxtParser()
self.llm = llm_service
async def analyze_txt_with_ai(
self,
@@ -114,7 +115,7 @@ class TxtAIService:
response = await self.llm.chat(
messages=messages,
temperature=0.1,
max_tokens=50000
max_tokens=8000
)
content_text = self.llm.extract_message_content(response)
@@ -220,7 +221,7 @@ class TxtAIService:
response = await self.llm.chat(
messages=messages,
temperature=0.1,
max_tokens=50000
max_tokens=8000
)
content_text = self.llm.extract_message_content(response)

14
backend/app/services/visualization_service.py
View File

@@ -53,7 +53,11 @@ class VisualizationService:
}
# 转换为 DataFrame
df = pd.DataFrame(rows, columns=columns)
# 过滤掉行数与列数不匹配的数据
valid_rows = [row for row in rows if len(row) == len(columns)]
if len(valid_rows) < len(rows):
logger.warning(f"过滤了 {len(rows) - len(valid_rows)} 行无效数据（列数不匹配）")
df = pd.DataFrame(valid_rows, columns=columns)
# 根据列类型分类
numeric_columns = df.select_dtypes(include=[np.number]).columns.tolist()
@@ -141,18 +145,18 @@ class VisualizationService:
charts = {}
# 1. 数值型列的直方图
charts["histograms"] = []
charts["numeric_charts"] = []
for col in numeric_columns[:5]: # 限制最多 5 个数值列
chart_data = self._create_histogram(df[col], col)
if chart_data:
charts["histograms"].append(chart_data)
charts["numeric_charts"].append(chart_data)
# 2. 分类型列的条形图
charts["bar_charts"] = []
charts["categorical_charts"] = []
for col in categorical_columns[:5]: # 限制最多 5 个分类型列
chart_data = self._create_bar_chart(df[col], col)
if chart_data:
charts["bar_charts"].append(chart_data)
charts["categorical_charts"].append(chart_data)
# 3. 数值型列的箱线图
charts["box_plots"] = []

13
backend/app/services/word_ai_service.py
View File

@@ -184,7 +184,7 @@ class WordAIService:
response = await self.llm.chat(
messages=messages,
temperature=0.1,
max_tokens=50000
max_tokens=8000
)
content = self.llm.extract_message_content(response)
@@ -276,7 +276,7 @@ class WordAIService:
response = await self.llm.chat(
messages=messages,
temperature=0.1,
max_tokens=50000
max_tokens=8000
)
content = self.llm.extract_message_content(response)
@@ -849,10 +849,12 @@ class WordAIService:
# 提取可用于图表的数据
chart_data = None
logger.info(f"准备提取图表数据，structured_data type: {structured_data.get('type')}, keys: {list(structured_data.keys())}")
if structured_data.get("type") == "table_data":
headers = structured_data.get("headers", [])
rows = structured_data.get("rows", [])
logger.info(f"table_data类型: headers数量={len(headers)}, rows数量={len(rows)}")
if headers and rows:
chart_data = {
"columns": headers,
@@ -860,15 +862,19 @@ class WordAIService:
}
elif structured_data.get("type") == "structured_text":
tables_data = structured_data.get("tables", [])
logger.info(f"structured_text类型: tables数量={len(tables_data)}")
if tables_data and len(tables_data) > 0:
first_table = tables_data[0]
headers = first_table.get("headers", [])
rows = first_table.get("rows", [])
logger.info(f"第一个表格: headers={headers[:5]}, rows数量={len(rows)}")
if headers and rows:
chart_data = {
"columns": headers,
"rows": rows
}
else:
logger.warning(f"无法识别的structured_data类型: {structured_data.get('type')}")
# 生成可视化图表
if chart_data:
@@ -904,3 +910,6 @@ class WordAIService:
"success": False,
"error": str(e)
}
word_ai_service = WordAIService()