fix sorted ranking so model uses overall sorted retrieved chunks

[NOTICKET][doc] add sheet-level leg and RRF voting for tabular retrieval

[NOTICKET][db] add sheet-level retrieval and focus LLM schema context to retrieved columns

[NOTICKET][doc] validate embedding vector for NaN/Infinity in manhattan retriever

fix fallback to fresh retrieval on corrupted Redis cache

[NOTICKET] now retrieve db tables first, then get column from the obtained tables. reduce k to 5

[NOTICKET] minor refactoring

[NOTICKET] rrf merge now at router level

fix: fix dedup logic

[KM-533] now also retrieves table level chunk

[KM-533] add table level schema, differentiate with chunk level. expand retrieval result with FK exploration

[KM-455][document] decided methods retrieval for document

[KM-507] now only uses hybrid (cosine and bm25)

[NOTICKET] fix-revert string change

[NOTICKET] db_executor: CTE DML check now walks entire AST root, schema: cast instead of string interpolation

[NOTICKET] minor fix in chat.py, add package for query, change schema used to hybrid (cosine+bm25)

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

[KM-507] add changes to methods

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

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

[KM-467] [DED][AI] Orchestration Agent - Init