v2.2: updated filters, updated style for frontend

Author: HardMax71

backend/.env.example

@@ -33,18 +33,18 @@ EMBEDDING_MODEL=text-embedding-3-small
 # -----------------------------------------------------------------------------
 # Redis Configuration
 # -----------------------------------------------------------------------------
+REDIS_HOST=redis
 REDIS_PORT=6379
 REDIS_PASSWORD=
 REDIS_JOB_PREFIX=cv:job:
-REDIS_JOB_QUEUE=cv_processing_queue
 REDIS_CLEANUP_QUEUE=cv_cleanup_queue
 REDIS_JOB_TIMEOUT=1800
-REDIS_WORKER_TIMEOUT=3
 REDIS_MAX_RETRIES=3
 
 # -----------------------------------------------------------------------------
 # Neo4j Graph Database
 # -----------------------------------------------------------------------------
+NEO4J_HOST=neo4j
 NEO4J_PORT=7687
 NEO4J_USERNAME=neo4j
 NEO4J_PASSWORD=secure_default_password
@@ -56,6 +56,7 @@ NEO4J_CONNECTION_TIMEOUT=30
 # -----------------------------------------------------------------------------
 # Qdrant Vector Database
 # -----------------------------------------------------------------------------
+QDRANT_HOST=qdrant
 QDRANT_PORT=6333
 QDRANT_COLLECTION=cv_key_points
 VECTOR_SIZE=1536

backend/backend/settings.py

@@ -1,5 +1,6 @@
 import os
 import sys
+import uuid
 from pathlib import Path
 
 from dotenv import load_dotenv
@@ -184,10 +185,8 @@
 REDIS_PORT = int(os.getenv("REDIS_PORT", "6379"))
 REDIS_PASSWORD = os.getenv("REDIS_PASSWORD", "")
 REDIS_JOB_PREFIX = os.getenv("REDIS_JOB_PREFIX", "cv:job:")
-REDIS_JOB_QUEUE = os.getenv("REDIS_JOB_QUEUE", "cv_processing_queue")
 REDIS_CLEANUP_QUEUE = os.getenv("REDIS_CLEANUP_QUEUE", "cv_cleanup_queue")
 REDIS_JOB_TIMEOUT = int(os.getenv("REDIS_JOB_TIMEOUT", "1800"))
-REDIS_WORKER_TIMEOUT = int(os.getenv("REDIS_WORKER_TIMEOUT", "30"))
 REDIS_MAX_RETRIES = int(os.getenv("REDIS_MAX_RETRIES", "3"))
 
 # =============================================================================
@@ -255,6 +254,7 @@
 # WORKER
 # =============================================================================
 
+WORKER_ID = os.getenv("WORKER_ID", f"worker-{uuid.uuid4().hex[:8]}")
 WORKER_STORE_IN_DB = os.getenv("WORKER_STORE_IN_DB", "true").lower() == "true"
 WORKER_GENERATE_REVIEW = os.getenv("WORKER_GENERATE_REVIEW", "true").lower() == "true"
 WORKER_CONCURRENT_JOBS = int(os.getenv("WORKER_CONCURRENT_JOBS", "3"))

backend/backend/urls.py

@@ -8,12 +8,12 @@
 from processor.utils.redis_queue import RedisJobQueue
 
 
-def metrics_view(_request):
+async def metrics_view(_request):
     """Collect current metrics and return Prometheus format."""
     # Update queue metrics before generating output
     try:
         redis_queue = RedisJobQueue()
-        stats = redis_queue.get_queue_stats()
+        stats = await redis_queue.get_queue_stats()
         update_queue_metrics(stats)
     except Exception:
         # If Redis is down, metrics endpoint should still work

backend/core/domain/resume.py

@@ -1,3 +1,4 @@
+import re
 from enum import StrEnum
 
 from pydantic import BaseModel, Field, model_validator
@@ -118,11 +119,36 @@ class CompanyInfo(BaseModel):
 
 
 class EmploymentDuration(BaseModel):
-    date_format: str
-    start: str
-    end: str
+    start: str  # Format: YYYY.MM
+    end: str | None = None  # Format: YYYY.MM or None for ongoing
     duration_months: int
 
+    @model_validator(mode="before")
+    @classmethod
+    def normalize_dates(cls, v: dict):
+        """Convert MM.YYYY or MMM YYYY to YYYY.MM format"""
+        if isinstance(v, dict):
+            for field in ["start", "end"]:
+                if field in v and isinstance(v[field], str):
+                    val = v[field].strip()
+                    if val.lower() in ("present", "current", ""):
+                        v[field] = None
+                    elif match := re.match(r'(\d{2})\.(\d{4})', val):  # MM.YYYY
+                        month, year = match.groups()
+                        v[field] = f"{year}.{month}"
+                    elif match := re.match(r'([A-Za-z]{3})\s+(\d{4})', val):  # MMM YYYY
+                        month_name, year = match.groups()
+                        month_map = {
+                            'jan': '01', 'feb': '02', 'mar': '03', 'apr': '04',
+                            'may': '05', 'jun': '06', 'jul': '07', 'aug': '08',
+                            'sep': '09', 'oct': '10', 'nov': '11', 'dec': '12'
+                        }
+                        month = month_map.get(month_name.lower()[:3], '01')
+                        v[field] = f"{year}.{month}"
+                    elif match := re.match(r'(\d{4})', val):  # YYYY only
+                        v[field] = f"{val}.01"
+        return v
+
 
 class KeyPoint(BaseModel):
     text: str
@@ -202,8 +228,8 @@ class EducationItem(BaseModel):
     field: str
     institution: InstitutionInfo
     location: Location | None = None
-    start: str | None = None
-    end: str | None = None
+    start: str | None = None  # Format: YYYY.MM
+    end: str | None = None  # Format: YYYY.MM or None for in-progress
     status: EducationStatus
     coursework: list[Coursework] = Field(default_factory=list)
     extras: list[EducationExtra] = Field(default_factory=list)
@@ -213,6 +239,27 @@ class EducationItem(BaseModel):
     def accept_legacy_education(cls, v: dict):
         if "institution" in v and isinstance(v["institution"], str):
             v["institution"] = {"name": v["institution"]}
+
+        # Normalize dates to YYYY.MM format
+        for field in ["start", "end"]:
+            if field in v and isinstance(v[field], str):
+                val = v[field].strip()
+                if val.lower() in ("present", "current", ""):
+                    v[field] = None
+                elif match := re.match(r'(\d{2})\.(\d{4})', val):  # MM.YYYY
+                    month, year = match.groups()
+                    v[field] = f"{year}.{month}"
+                elif match := re.match(r'([A-Za-z]{3})\s+(\d{4})', val):  # MMM YYYY
+                    month_name, year = match.groups()
+                    month_map = {
+                        'jan': '01', 'feb': '02', 'mar': '03', 'apr': '04',
+                        'may': '05', 'jun': '06', 'jul': '07', 'aug': '08',
+                        'sep': '09', 'oct': '10', 'nov': '11', 'dec': '12'
+                    }
+                    month = month_map.get(month_name.lower()[:3], '01')
+                    v[field] = f"{year}.{month}"
+                elif match := re.match(r'(\d{4})', val):  # YYYY only
+                    v[field] = f"{val}.01"
         if "start_date" in v and "start" not in v:
             v["start"] = v.pop("start_date")
         if "end_date" in v and "end" not in v:

backend/core/domain/search.py

@@ -1,6 +1,8 @@
 from dataclasses import dataclass, field
 from enum import StrEnum
 
+from core.domain.resume import EducationStatus
+
 
 class SearchType(StrEnum):
     SEMANTIC = "semantic"
@@ -15,6 +17,8 @@ class SearchFilters:
     company: str | None = None
     location: str | None = None
     years_experience: int | None = None
+    education_level: str | None = None  # Bachelor, Master, PhD, etc.
+    education_status: EducationStatus | None = None
 
 
 @dataclass
@@ -29,6 +33,8 @@ class FilterOptionsResult:
     roles: list[FilterOption] = field(default_factory=list)
     companies: list[FilterOption] = field(default_factory=list)
     locations: list[FilterOption] = field(default_factory=list)
+    education_levels: list[FilterOption] = field(default_factory=list)
+    education_statuses: list[FilterOption] = field(default_factory=list)
 
 
 @dataclass

backend/processor/services/cleanup_service.py

@@ -25,7 +25,7 @@ async def cleanup_job(self, job_id: str) -> bool:
         else:
             file_ext = None
 
-        FileService.cleanup_all_job_files(job_id, file_ext)
+        await FileService.cleanup_all_job_files(job_id, file_ext)
         self.graph_db.delete_resume(resume_id=job_id)
         self.vector_db.delete_resume_vectors(job_id)
         return await self.job_service.delete_job(job_id)