Spaces:

DataEyond
/

Agentic-Service-Data-Eyond

Paused

App Files Files Community

Agentic-Service-Data-Eyond

Commit History

May 5

02:07
merge dev_new to main

Rifqi Hafizuddin

9257b7b

May 4

07:45
fix sorted ranking so model uses overall sorted retrieved chunks

Rifqi Hafizuddin

3e7924d
04:24
make executors self-contained, remove redundant pre-filter

sofhiaazzhr

73b7fe3
01:47
NOTICKET] add dev dependency group and update gitignore

sofhiaazzhr

36ffff4
01:34
[NOTICKET][doc] correct metadata key path in _format_context

sofhiaazzhr

16ab916
01:34
[NOTICKET][doc] remove column filter and fallback cap for full-schema approach

sofhiaazzhr

959b1b0
01:33
[NOTICKET][doc] add sheet-level leg and RRF voting for tabular retrieval

sofhiaazzhr

5f86993

Apr 30

08:09
fix: minor returned type if sql writes limit yang melebihi batas

Rifqi Hafizuddin

b4df8b1
07:19
[NOTICKET][db] add sheet-level retrieval and focus LLM schema context to retrieved columns

sofhiaazzhr

a205d0c
03:24
[NOTICKET] pass orchestrator search_query to sql executor for multi-turn context⁠

Rifqi Hafizuddin +1: Claude Sonnet 4.6

23eeb2d
02:28
[NOTICKET][doc] validate embedding vector for NaN/Infinity in manhattan retriever

sofhiaazzhr

2167a5b

Apr 29

08:02
fix fallback to fresh retrieval on corrupted Redis cache

sofhiaazzhr

9cb950f
07:56
[NOTICKET][doc] add guard if filename None

sofhiaazzhr

b7fbaeb
03:49
[NOTICKET] now retrieve db tables first, then get column from the obtained tables. reduce k to 5

Rifqi Hafizuddin

bb29492
02:38
[NOTICKET][doc] fix aggregate count operation when value_col is not specified

sofhiaazzhr

00aa61d

Apr 28

09:41
fix: 5 bug fixes on tabular executor⁠

sofhiaazzhr +1: Claude Sonnet 4.6

a49dc1b
09:41
feat: add sheet-level chunk on CSV/XLSX ingestion⁠

sofhiaazzhr +1: Claude Sonnet 4.6

8daf9b5
09:13
fix: increase K in chat endpoint to 10

Rifqi Hafizuddin

b59ef76
08:56
fix: query executor now use user question as prompt (sebelumnya pakai hasil orchestrator)

Rifqi Hafizuddin

0935ede
08:32
[NOTICKET] minor refactoring

Rifqi Hafizuddin

e4f62b8
08:26
[NOTICKET] rrf merge now at router level

Rifqi Hafizuddin

de32ab0
08:21
fix: fix dedup logic

Rifqi Hafizuddin

c9d3b33
04:07
[KM-533] now also retrieves table level chunk

Rifqi Hafizuddin

4150ba7
02:59
[KM-533] add table level schema, differentiate with chunk level. expand retrieval result with FK exploration

Rifqi Hafizuddin

fc1239a
01:41
Make a query for tabular (XLSX and CSV) (#14)⁠

ishaq101 +1: sofhiaazzhr

8802920

Apr 27

10:48
[KM-455][document] decided methods retrieval for document

sofhiaazzhr

cf77d20
10:44
[KM-515][document] Make Query for Tabular Type (XLSX & CSV)

sofhiaazzhr

3604994
10:42
[NOTICKET] add pyarrow

sofhiaazzhr

7ff66c9
10:42
[NOTICKET] add pyarrow

sofhiaazzhr

432c1fa
10:41
[NOTICKET]untrack software/ folder (ignored via .gitignore)

sofhiaazzhr

0931c10
02:52
[KM-507] now only uses hybrid (cosine and bm25)

Rifqi Hafizuddin

40925b4
02:49
Merge dev_new to main (improve retriever and add querying) (#13)⁠

ishaq101 +1: sofhiaazzhr

52999bc
01:42
[NOTICKET] fix query now use orchestrator msg, rework db pipeline replace ingestion logic

Rifqi Hafizuddin

be9bbd9

Apr 24

01:18
[KM-516][KM-517] add new feature; ai can now see table & column names that have fk relationship with retrieved result

Rifqi Hafizuddin

f86da27

Apr 23

08:35
[KM-520] Integrate db query executor pipeline with existing rag retrieve pipeline

Rifqi Hafizuddin

a25febe
08:16
[NOTICKET] fix-revert string change

Rifqi Hafizuddin

110ee34
07:04
[NOTICKET] db_executor: CTE DML check now walks entire AST root, schema: cast instead of string interpolation

Rifqi Hafizuddin

bd2b1d9
06:59
[NOTICKET] fix delete, now can filter by user

Rifqi Hafizuddin

f273db0
04:41
[KM-512] connect query executor to user question. add logging for db_executor

Rifqi Hafizuddin

abc494f
04:40
add to gitignore

Rifqi Hafizuddin

1fef470
04:05
[KM-513][document] add convert to parquet if type file is XLSX and CSV

sofhiaazzhr

770f26b
04:02
Merge branch 'dev_new' of https://huggingface.co/spaces/DataEyond/Agentic-Service-Data-Eyond into dev_new

sofhiaazzhr

29efec6
03:59
[NOTICKET] update .gitignore

sofhiaazzhr

240251c
03:41
[NOTICKET] rename file name, updated after uv sync

Rifqi Hafizuddin

948d6dd
03:28
[KM-512] add Pydantic model the LLM fills via function calling in sql_query, and add same signature for db and tabular

Rifqi Hafizuddin

220f59e
03:21
[NOTICKET] minor fix in chat.py, add package for query, change schema used to hybrid (cosine+bm25)

Rifqi Hafizuddin

15cd3a7

Apr 22

09:05
[KM-512] create folder for querying from bd/tabular docs

Rifqi Hafizuddin

2c8a3e8
08:58
[KM-507] add different methods, now using dense cosine

Rifqi Hafizuddin

145bca3
08:57
add to gitignore

Rifqi Hafizuddin

83ed744
08:56
[NOTICKET] add db_client for querying

Rifqi Hafizuddin

e49db60

Commit History

May 5

merge dev_new to main

May 4

fix sorted ranking so model uses overall sorted retrieved chunks

make executors self-contained, remove redundant pre-filter

NOTICKET] add dev dependency group and update gitignore

[NOTICKET][doc] correct metadata key path in _format_context

[NOTICKET][doc] remove column filter and fallback cap for full-schema approach

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

Apr 30

fix: minor returned type if sql writes limit yang melebihi batas

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

[NOTICKET] pass orchestrator search_query to sql executor for multi-turn context⁠

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

Apr 29

fix fallback to fresh retrieval on corrupted Redis cache

[NOTICKET][doc] add guard if filename None

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

[NOTICKET][doc] fix aggregate count operation when value_col is not specified

Apr 28

fix: 5 bug fixes on tabular executor⁠

feat: add sheet-level chunk on CSV/XLSX ingestion⁠

fix: increase K in chat endpoint to 10

fix: query executor now use user question as prompt (sebelumnya pakai hasil orchestrator)

[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

Make a query for tabular (XLSX and CSV) (#14)⁠

Apr 27

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

[KM-515][document] Make Query for Tabular Type (XLSX & CSV)

[NOTICKET] add pyarrow

[NOTICKET] add pyarrow

[NOTICKET]untrack software/ folder (ignored via .gitignore)

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

Merge dev_new to main (improve retriever and add querying) (#13)⁠

[NOTICKET] fix query now use orchestrator msg, rework db pipeline replace ingestion logic

Apr 24

[KM-516][KM-517] add new feature; ai can now see table & column names that have fk relationship with retrieved result

Apr 23

[KM-520] Integrate db query executor pipeline with existing rag retrieve pipeline

[NOTICKET] fix-revert string change

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

[NOTICKET] fix delete, now can filter by user

[KM-512] connect query executor to user question. add logging for db_executor

add to gitignore

[KM-513][document] add convert to parquet if type file is XLSX and CSV

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

[NOTICKET] update .gitignore

[NOTICKET] rename file name, updated after uv sync

[KM-512] add Pydantic model the LLM fills via function calling in sql_query, and add same signature for db and tabular

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

Apr 22

[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