feat: implement multi-stage candidate ingestion and matching pipeline with UI tracking and backend schema support

feat: implement stage 1 candidate retrieval and scoring logic using Qdrant and multi-factor heuristics

feat: implement matching router and stage 2 neural reranking logic

feat: slider max dynamically set from CSV row count (header excluded)

fix: use real candidate count, remove stage2 cap, add full error logging

fix(ml): restrict cross-encoder batch_size to prevent OOM kills on uncapped arrays

feat: implement matching router with two-stage retrieval, reranking, and async explanation generation

fix(ui): add navbar link to API Docs alongside system reset

fix: replace backend RRF with true percentage math so Stage2 final score aligns with frontend weights

fix: growth_velocity always 60% bug - handle JSON string and empty work_exp

feat: user-controlled pipeline depth sliders for stage1/stage2 retrieval caps

fix: cap reranker input to top-40 and fix nginx send timeout to prevent 504

feat: implement matching router with support for retrieval, reranking, and candidate explanation workflows

feat: add admin endpoint to reset Postgres schema and Qdrant collection via Alembic migrations

feat: implement admin endpoint and UI for database and vector store reset

feat: initialize SQLAlchemy async database engine and session management with Neon-compatible configuration

feat: implement backend matching pipeline and update project documentation

feat: implement async SQLAlchemy database engine and session management with Neon-compatible configurations

feat: add frontend system health diagnostics and mute HF Celery gossip

feat: implement backend ingestion pipeline with Celery workers, Qdrant integration, and session management

feat: implement FastAPI application with Pinecone/Redis integration and candidate matching router

feat: implement backend candidate matching pipeline with Pinecone integration, FastAPI routers, and ingestion workers.

feat: implement automated ingestion pipeline with state persistence and add database maintenance utilities

feat: stabilize celery loops, add redis caching, and scale stage 2 neural limit to 250

refactor: unified session view, pipeline polling, db wipe

feat: add pipeline page, session delete with Qdrant cleanup, explain worker, and final frontend polish

fix: resolve asyncpg ssl connection errors and Qdrant strict payload filtering

feat: implement session-based candidate matching architecture

feat: add gap analysis, LLM explainer via Groq, and all API routes

feat: implement Stage 2 reranker with BGE cross-encoder and RRF fusion

feat: implement Stage 1 retriever - ANN search + structured weighted scorer

feat: implement feature builder with growth velocity and JD quality scoring

feat: add embedding singleton and batch ingest Celery worker

feat: define ORM models for JD, Candidate, MatchResult with Alembic migration

feat: scaffold FastAPI app with async Postgres and Qdrant connection