22 Commits

Author SHA1 Message Date
edmundhighcock
f663865186 Added nbconvert needed for rag indexing jupyter notebooks (#2862)
* Added nbconvert needed for rag indexing jupyter notebooks

* Allow rag service image to be configured

* [pre-commit.ci lite] apply automatic fixes

---------

Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>
2025-12-30 11:59:52 +08:00
SSDGADsss
5df39b480d fix rag-service requirements (#2843)
In response to the issue raised in # 281, I have added a dependency of
'nbconvert' to the Python dependency list of the avaent rag server,
hoping to fix the problem
2025-11-25 17:18:55 +08:00
doodleEsc
d87724e0f7 ci: configure Git for unsafe repositories in Docker (#2423) 2025-07-08 19:55:52 +08:00
doodleEsc
014010b022 fix: Avoid indexing temporary files (#2419)
Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>
2025-07-07 16:36:48 +08:00
doodleEsc
6bbf3d2004 refactor: remove redundant pathspec check (#2384) 2025-07-02 12:17:41 +08:00
doodleEsc
2dd4c04088 feat: Enhanced Model Provider Support and Configuration Flexibility For Rag Service (#2056)
Co-authored-by: doodleEsc <cokie@foxmail.com>
Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>
2025-06-06 23:07:07 +08:00
Peter Cardenas
b6a3c925a4 fix: support rag search on macos (#1928) 2025-05-12 16:54:48 +08:00
yetone
5b4bb47d6f feat: report more detailed err info (#1674) 2025-03-22 15:25:38 +08:00
Theo Ribeiro
4dde29f986 fix: rag-service error with go files (#1624)
* fix: switching from python to go

* fix: type casting error

* Fix import order
2025-03-22 02:58:51 +08:00
Omar Crespo
968d5fbd52 fix: RAG services improvements (#1565)
* fix: rag nix runner

* feat: improve rag default models

* fix: change log levels to avoid huge log files in rag service
2025-03-20 13:28:04 +08:00
yetone
008fe29de8 fix: use host network for rag service container (#1649) 2025-03-20 03:45:44 +08:00
Thomas Müller
64b919274e fix: skip more binary files than just audio/video in RAG scan (#1547) 2025-03-10 16:16:14 +08:00
wan
f9025ff415 fix: skip audio and video files during directory scan in RAG Service. (#1509) 2025-03-10 15:23:56 +08:00
yetone
a13e5dca1d fix: remove resource schema (#1512) 2025-03-07 00:43:57 +08:00
Francesco Tassi
2b0e7e09ae fix: ignore git crypt files (#1465)
* Exclude file patterns from git-crypt in pathspec

git-crypt could be used to encrypt files in a repository.
These files should be excluded from the pathspec to avoid
sending them to the RAG service.
git-crypt relies on a filter attribute in the .gitattributes so we can
use ls-files to get the files that are encrypted.

* Add some logging about ignored file

The logging is quite verbose, given it logs every ignored file but I
think it useful for the end user to have an explicit feedback about
sensitive files that are being ignored.

* Fix lint errors

* Avoid Shell=true for subprocess.run() (S604)

Removing S604 "Avoid Shell=true for subprocess.run()" we get S603 "subprocess call: check for execution of untrusted input"
I dit not found a way to fix this issue, so I'm putting it in the ignore list.
I also used shutil to retrieve the absolute git path to run the subprocess commands.
2025-03-06 18:34:12 +08:00
Jorge Luis Suarez
e408b820c8 feat: add Nix as Rag service runner option (#1480)
* feat: add nix as option for RAG runner

* fix: remove default embedding model

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* stylua format

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2025-03-04 23:50:24 +08:00
nzlov
de7cccd089 feat: add support for ollama RAG providers (#1427)
* fix: openai env

* feat: add support for multiple RAG providers

- Added provider, model and endpoint configuration options for RAG service

- Updated RAG service to support both OpenAI and Ollama providers

- Added Ollama embedding support and dependencies

- Improved environment variable handling for RAG service configuration

Signed-off-by: wfhtqp@gmail.com <wfhtqp@gmail.com>

* fix: update docker env

* feat: rag server add ollama llm

* fix: pre-commit

* feat: check embed model and clean

* docs: add rag server config docs

* fix: pyright ignore

---------

Signed-off-by: wfhtqp@gmail.com <wfhtqp@gmail.com>
2025-03-04 11:07:40 +08:00
João Inez
64a59f9560 fix(rag_service): ignore leading slash gitignore patterns (#1412) 2025-02-27 11:46:03 +08:00
nzlov
ef78c36e98 fix: openai env (#1400) 2025-02-26 17:35:49 +08:00
yetone
a1d1697400 feat: parse excel (#1383) 2025-02-25 12:06:50 +08:00
yetone
7255e16020 fix: rag resource must be a git repo (#1360) 2025-02-23 15:11:18 +08:00
yetone
fd84c91cdb feat: RAG service (#1220) 2025-02-23 01:37:26 +08:00