multi query enhancement

tracepilot pipeline config initialization and gaugepilot expsetup frontend fix

fix tesseract local file access

added delete benchmark(s) endpoints and exposed them in frontend

gaugepilot benchmarks persistance stage 1

fixed gaugepilot upload routes

uploading routing for benchmarking

benchmark initial backend and frontend

fixed bm25

tracepilot trace data and reset traces button behavior decoupled between experimental and production modes, added clear all button to clear conversations/chats from docpilot with decoupled behavior

docpilot chat data decoupled between experimental and production mode, selector behavior fixed

assigning re-ranker its own dropdown

AWS deployment using EC2 and dropdown selector initial mapping

initial benchmark and improve query rewriting

ingestion and expire time

empty

paddleocr removed

Use rec_texts from PaddleOCR v3 OCRResult

debug ingestion ocr

requirements paddle

mkldnn

fix: normalize OCR images to RGB before PaddleOCR

ingestion mod

ingestion indent

packages

feat: improve retrieval evaluation and document ingestion

code files ingestion capability

Added multi model selector capability in chat

feat(metadata): add section-title extraction and trace visibility

feat(docpilot): improve dashboard UX and document management

background optimization

file type optimization for hf and ocr support

Stabilize chunk traversal and prevent premature termination

stabilize chunk size

Improve vector store observability and ingestion tracing

Infinite hanging check

Improve RAG chunking and retrieval observability

debug

Normalize backend imports for production deployment

fix imports

Fix Neon SSL connection handling

Initial PilotMaster deployment