修复一次
This commit is contained in:
parent
dbe2f9202d
commit
36f08f93e0
@ -0,0 +1,9 @@
|
|||||||
|
{
|
||||||
|
"_data": {},
|
||||||
|
"_meta": {
|
||||||
|
"cacheVersion": 3,
|
||||||
|
"originalFile": "5429f024_计划书(1).pdf",
|
||||||
|
"extractedAt": "2026-07-24T12:50:28.325762",
|
||||||
|
"fileHash": "159aa3c49aebe185a3dc2af7f0b50e335f9a8e00a6998d84a7a259eb754ed4cd"
|
||||||
|
}
|
||||||
|
}
|
||||||
@ -0,0 +1,9 @@
|
|||||||
|
{
|
||||||
|
"_data": {},
|
||||||
|
"_meta": {
|
||||||
|
"cacheVersion": 3,
|
||||||
|
"originalFile": "372e0293_MLS_SIUL3_F-48-N-CN-USD-S3m-10x_coi__SC_.pdf",
|
||||||
|
"extractedAt": "2026-07-24T12:54:05.604558",
|
||||||
|
"fileHash": "60e9e349a2169511dd85ce7fecc3c1bc9ab69a7c9f254a03ca75a29625f5e9d4"
|
||||||
|
}
|
||||||
|
}
|
||||||
Binary file not shown.
@ -194,7 +194,7 @@ class ExtractionOrchestrator:
|
|||||||
self.use_cache = use_cache
|
self.use_cache = use_cache
|
||||||
self.cache_dir = cache_dir
|
self.cache_dir = cache_dir
|
||||||
|
|
||||||
async def extract_plan(self, pdf_path: str, plan_type: str = "savings") -> ExtractionResult:
|
async def extract_plan(self, pdf_path: str, plan_type: str = "savings", force_reparse: bool = False) -> ExtractionResult:
|
||||||
"""从 PDF 提取结构化数据。"""
|
"""从 PDF 提取结构化数据。"""
|
||||||
from insurance.ppt.llm_client import llm_client
|
from insurance.ppt.llm_client import llm_client
|
||||||
from insurance.ppt.prompts import (
|
from insurance.ppt.prompts import (
|
||||||
@ -213,7 +213,7 @@ class ExtractionOrchestrator:
|
|||||||
)
|
)
|
||||||
|
|
||||||
# 检查缓存
|
# 检查缓存
|
||||||
if self.use_cache:
|
if self.use_cache and not force_reparse:
|
||||||
cached = self._load_from_cache(abs_path)
|
cached = self._load_from_cache(abs_path)
|
||||||
if cached:
|
if cached:
|
||||||
cached.duration_ms = (time.time() - start) * 1000
|
cached.duration_ms = (time.time() - start) * 1000
|
||||||
|
|||||||
@ -135,7 +135,7 @@ def parse_session(session_id):
|
|||||||
filepath = file_info.get("path", "")
|
filepath = file_info.get("path", "")
|
||||||
plan_type = file_info.get("type", "savings")
|
plan_type = file_info.get("type", "savings")
|
||||||
try:
|
try:
|
||||||
result = asyncio.run(orchestrator.extract_plan(filepath, plan_type))
|
result = asyncio.run(orchestrator.extract_plan(filepath, plan_type, force_reparse=True))
|
||||||
extractions.append({
|
extractions.append({
|
||||||
"pdfName": file_info.get("name", ""),
|
"pdfName": file_info.get("name", ""),
|
||||||
"pdfPath": filepath,
|
"pdfPath": filepath,
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user