162 lines
6.8 KiB
Python
162 lines
6.8 KiB
Python
import logging
|
|
import httpx,os
|
|
from fastapi import HTTPException
|
|
from inbox.models import Inbox_Messages
|
|
from inbox.file_decoder import decode_attachment, AttachmentDecodeError
|
|
from inbox.serializers import serialize_message
|
|
from inbox.plugins import load_message_files, extract_resume_text
|
|
from dotenv import load_dotenv
|
|
load_dotenv()
|
|
from sqlalchemy.ext.asyncio import AsyncSession
|
|
from pydantic import BaseModel
|
|
|
|
from db_setup import session_scope
|
|
from job.job_post.models import JobPosts
|
|
from job.job_post.serializers import serialize_job_post
|
|
|
|
logger = logging.getLogger("inbox.match")
|
|
|
|
|
|
class Email:
|
|
def __init__(self,session:AsyncSession,token=None):
|
|
self.session=session
|
|
self.get_url=os.getenv("EMAIL_URL")
|
|
self.token=token
|
|
self.pending_match_ids: list[str] = []
|
|
|
|
@staticmethod
|
|
async def run_inbox_matching(inbox_ids: list[str], *, force: bool = False) -> None:
|
|
"""Background worker: extract CV text, run the matching agent, persist results.
|
|
|
|
Uses its own session_scope per message - never the request session.
|
|
"""
|
|
if not inbox_ids:
|
|
return
|
|
|
|
# Local import so inbox routes still load when langgraph/openai are missing.
|
|
from agent.execute_agent import run_agent
|
|
|
|
cached_posts = None
|
|
for record_id in inbox_ids:
|
|
try:
|
|
async with session_scope() as session:
|
|
row = await Inbox_Messages.get_inbox_message_by_id(session, record_id)
|
|
if not row:
|
|
continue
|
|
if not force and row.match_status is not None:
|
|
continue
|
|
|
|
paths = [p.strip() for p in (row.file_path or "").split(",") if p.strip()]
|
|
text, extract_err = await extract_resume_text(paths)
|
|
if not text:
|
|
await Inbox_Messages.set_match_result(
|
|
session,
|
|
record_id,
|
|
status="no_text",
|
|
error=extract_err or "no text extracted",
|
|
)
|
|
continue
|
|
|
|
if cached_posts is None:
|
|
posts = await JobPosts.get_active_job_posts(session)
|
|
cached_posts = [serialize_job_post(p) for p in posts]
|
|
|
|
result = await run_agent(
|
|
subject=row.message_subject or "",
|
|
resume_text=text,
|
|
job_posts=cached_posts,
|
|
)
|
|
await Inbox_Messages.set_match_result(
|
|
session,
|
|
record_id,
|
|
resume_text=text,
|
|
suggested_job_post_ids=result.get("suggested_job_post_ids") or [],
|
|
summary=result.get("summary") or "",
|
|
reasoning=result.get("reasoning") or "",
|
|
status=result.get("status") or "failed",
|
|
error=result.get("error") or "",
|
|
)
|
|
logger.info(
|
|
"matched inbox %s status=%s ids=%s",
|
|
record_id,
|
|
result.get("status"),
|
|
result.get("suggested_job_post_ids"),
|
|
)
|
|
except Exception as exc:
|
|
logger.exception("inbox matching failed for %s", record_id)
|
|
try:
|
|
async with session_scope() as session:
|
|
await Inbox_Messages.set_match_result(
|
|
session, record_id, status="failed", error=str(exc)
|
|
)
|
|
except Exception:
|
|
logger.exception("failed to persist match failure for %s", record_id)
|
|
|
|
async def service_email(self,top,skip):
|
|
async with httpx.AsyncClient() as client:
|
|
try:
|
|
response=await client.get(f"{self.get_url}/emails",
|
|
params={"skip":skip,"top":top},
|
|
headers={"Authorization":f"Bearer {self.token}"}
|
|
)
|
|
if response.status_code==200:
|
|
return response.json()
|
|
else:
|
|
raise HTTPException(status_code=response.status_code,detail=response.text)
|
|
except Exception as e:
|
|
raise HTTPException(status_code=500,detail=str(e))
|
|
|
|
async def get_email_by_id(self,message_id):
|
|
async with httpx.AsyncClient() as client:
|
|
try:
|
|
response=await client.get(f"{self.get_url}/emails/{message_id}",
|
|
headers={"Authorization":f"Bearer {self.token}"}
|
|
)
|
|
if response.status_code==200:
|
|
data=response.json()
|
|
re_create_file=await decode_attachment(data.get("attachments"))
|
|
insert_func=await Inbox_Messages.insert_email(session=self.session,email_data=data,file_path=re_create_file)
|
|
if (
|
|
insert_func.attachment
|
|
and insert_func.file_path
|
|
and insert_func.match_status is None
|
|
):
|
|
self.pending_match_ids.append(str(insert_func.id))
|
|
return response.json()
|
|
else:
|
|
raise HTTPException(status_code=response.status_code,detail=response.text)
|
|
except Exception as e:
|
|
raise HTTPException(status_code=500,detail=str(e))
|
|
|
|
async def get_inbox_messages(self,top,skip,search=None):
|
|
messages=await Inbox_Messages.get_inbox_messages(self.session,top,skip,search)
|
|
items=[]
|
|
for m in messages:
|
|
item=serialize_message(m)
|
|
files=load_message_files(m)
|
|
if files:
|
|
item["files"]=files
|
|
items.append(item)
|
|
return items
|
|
|
|
async def get_inbox_message_by_id(self,record_id):
|
|
message=await Inbox_Messages.get_inbox_message_by_id(self.session,record_id)
|
|
if not message:
|
|
raise HTTPException(status_code=404,detail="Message not found")
|
|
item=serialize_message(message)
|
|
files=load_message_files(message)
|
|
if files:
|
|
item["files"]=files
|
|
return item
|
|
|
|
async def queue_rematch(self,record_id):
|
|
message=await Inbox_Messages.get_inbox_message_by_id(self.session,record_id)
|
|
if not message:
|
|
raise HTTPException(status_code=404,detail="Message not found")
|
|
if not message.attachment or not message.file_path:
|
|
raise HTTPException(status_code=400,detail="Message has no attachment to match")
|
|
return str(message.id)
|
|
|
|
async def count_inbox_messages(self,search=None):
|
|
return await Inbox_Messages.count_inbox_messages(self.session,search)
|