[KM-512] create folder for querying from bd/tabular docs

[KM-507] add different methods, now using dense cosine

add to gitignore

[NOTICKET] add db_client for querying

[KM-507] add changes to methods

[KM-507] add multiple retrieval method to compare (dense, mmr, bm25, hybrid)

[NOTICKET] fixed multiple sources

[NOTICKET] fix single source to multiple sources

Merge branch 'main' of https://huggingface.co/spaces/DataEyond/Agentic-Service-Data-Eyond into dev_new

[KM-438][KM-439] framework for knowledge retriever

[NOTICKET][document]: make a clean output to status error unsupported file type

[NO TICKET][document]: delete vector embedding on table langchain_pg_embedding if user delete document on knowledge

[NO TICKET][document]: add updated_at on metadata

[NOTICKET] add updated_at field for metadata & delete old embedding before appending

[NOTICKET] add total token logging (#9)

[NOTICKET] add total token logging

Merge branch 'dev_new' of https://huggingface.co/spaces/DataEyond/Agentic-Service-Data-Eyond into dev_new

Merge branch 'main' of https://huggingface.co/spaces/DataEyond/Agentic-Service-Data-Eyond into dev_new

Merge branch 'main' of https://huggingface.co/spaces/DataEyond/Agentic-Service-Data-Eyond into dev_new

test-pr (#8)

Merge branch 'main' of https://huggingface.co/spaces/DataEyond/Agentic-Service-Data-Eyond into dev_new

[KM-496] [DED][AI] Fix Response data structure for field sources (db flow)

[NOTICKET] [document]: add doctypes endpoint (#7)

[NOTICKET]: add to gitignore

[NOTICKET]: add comments to flag that file type lists must stay in sync

[NOTICKET]: add doctypes endpoint & 10MB file size limit

[NOTICKET][DB] add endpoints for dbtypes (#6)

[NOTICKET][DB] add supported dbtype for frontend

[NOTICKET] add duplicate check for storing database

[NOTICKET] minor code refactor

[KM-493] [DED][AI] Fix source extraction in chat

[NOTICKET] edit imports

[NOTICKET] fix error in imports

[NOTICKET] add software folder (#4)

[KM-436][KM-437] add and modify for database and document pipeline (#3)

[NOTICKET][DB] fix mysql pipeline

[NOTICKET]: fix merge conflict

[NOTICKET]: adjusted pyproject.toml for OCR PDF

[KM-437][DB] add mysql, sqlserver, bigquery, snowflake connections

[NOTICKET] update settings

[NOTICKET][DB] update credential & databaseclient. update settings

[NOTICKET]: update uv.lock

[NOTICKET]: add Tesseract and Poppler binaries via Git LFS

[NOTICKET]: use tesseract for extract PDF

[NOTICKET][DB] pisahin db credential ke folder model. add ingestion endpoint at db_client to use db pipeline. add router db_client di main.

[NOTICKET][DB] menyesuaikan format struktur db_pipeline sesuai dengan file lain

[DB] fix/rename db_pipeline.py

[NOTICKET]: add CSV and XLSX file type

edit document for new pipeline

delete duplicate file