starred/karakeep

Fork 0

mirror of https://github.com/karakeep-app/karakeep.git synced 2026-04-25 07:56:05 +03:00

[GH-ISSUE #3] [Feature Request] Add support for Ollama #1

New issue

Closed

opened 2026-03-02 11:45:25 +03:00 by kerem · 4 comments

kerem commented

2026-03-02 11:45:25 +03:00

Owner

Originally created by @MohamedBassem on GitHub (Mar 26, 2024).
Original GitHub issue: https://github.com/karakeep-app/karakeep/issues/3

This issue to track supporting ollama as an alternative to openai.

Originally created by @MohamedBassem on GitHub (Mar 26, 2024). Original GitHub issue: https://github.com/karakeep-app/karakeep/issues/3 This issue to track supporting ollama as an alternative to openai.

kerem

2026-03-02 11:45:25 +03:00

closed this issue
added the
feature request
label

kerem commented

2026-03-02 11:45:26 +03:00

Author

Owner

@MohamedBassem commented on GitHub (Mar 27, 2024):

Just landed the ollama support, it'll be included in the next release (happing later today)!

@MohamedBassem commented on GitHub (Mar 27, 2024): Just landed the ollama support, it'll be included in the next release (happing later today)!

kerem commented

2026-03-02 11:45:26 +03:00

Author

Owner

@dillfrescott commented on GitHub (Mar 27, 2024):

Yes!!!!

@dillfrescott commented on GitHub (Mar 27, 2024): Yes!!!!

kerem commented

2026-03-02 11:45:26 +03:00

Author

Owner

@MohamedBassem commented on GitHub (Mar 27, 2024):

Ollama support is now available in the 0.10.0 release! 🎉 You can check the new configuration arguments here!

Basically add the following to the env file (make sure you remove the OPENAI_API_KEY otherwise it takes precedence):

OLLAMA_BASE_URL=<ollama_addr>
INFERENCE_TEXT_MODEL=mistral
INFERENCE_IMAGE_MODEL=llava

Make sure that those two models are pulled in ollama with ollama pull mistral and ollama pull llava.

@MohamedBassem commented on GitHub (Mar 27, 2024): Ollama support is now available in the `0.10.0` release! 🎉 You can check the new configuration arguments [here](https://docs.hoarder.app/configuration#inference-configs-for-automatic-tagging)! Basically add the following to the env file (make sure you remove the `OPENAI_API_KEY` otherwise it takes precedence): ``` OLLAMA_BASE_URL=<ollama_addr> INFERENCE_TEXT_MODEL=mistral INFERENCE_IMAGE_MODEL=llava ``` Make sure that those two models are pulled in ollama with `ollama pull mistral` and `ollama pull llava`.

kerem commented

2026-03-02 11:45:27 +03:00

Author

Owner

@dillfrescott commented on GitHub (Mar 27, 2024):

Id recommend the openchat 0106 model for text, that thing is impressive for a 7b model!

@dillfrescott commented on GitHub (Mar 27, 2024): Id recommend the openchat 0106 model for text, that thing is impressive for a 7b model!

kerem referenced this issue

2026-03-02 11:48:08 +03:00

[GH-ISSUE #392] Unable to login in Fifrefox addon behind reverse proxy - NetworkError when attempting to fetch resource. #257

kerem referenced this issue

2026-03-02 11:50:36 +03:00

[GH-ISSUE #813] [Bug/maybe Feat. Extension] Icon visually vanishing in browser extension bar using full black Chrome theme #530

kerem referenced this issue

2026-03-02 11:58:00 +03:00

[PR #1] [MERGED] Restructure the repo to follow the t3-turbo repo format #1519

kerem referenced this issue

2026-03-02 11:59:51 +03:00

[PR #1971] feat: Improved MCP functionality #1939