Yoshiki Miura

Ollama AI Provider needs to support tool calls: https://github.com/sgomez/ollama-ai-provider/pull/11

Ollama's tools do not support streaming yet. > Ollama tooling does not support it in streams, but this provider can detect tool responses. https://github.com/sgomez/ollama-ai-provider?tab=readme-ov-file#tool-streaming I tested it with the llama3.1...

# Update Object generation and Tool usage with Ollama are now working stably, so we have implemented support for them. Ollama currently does not support tool streaming. Therefore, there is...

At the time of the search, it's not possible to determine if the information is outdated, so the LLM needs to select and respond with the appropriate information. It seems...

It can be enabled with the environment variable `enable_share`. Please see the PR for details: https://github.com/miurla/morphic/pull/142

> It seems that is only accessible by using the saved queries from the history panel. Sorry, I understood. Due to the removal of `router.refresh()`, the share button does not...

No-History Options is nice. The initial release didn't include History, and it was easy to build. Local storage is unnecessary since there's already a Local Redis option.

I tested both the app and API, confirming they work ✅ I also verified that existing search providers function correctly ✅ App | API -- | -- |

It would be good to implement caching for APIs other than SearXNG as well. https://github.com/miurla/morphic/pull/320/files#diff-1fbdc5f844dd8e711558152823d244f20fb8af1bf5d17137b950c4e74443979dR57

Hi @LCBO, You can customize which models appear by editing `public/config/models.json` - either setting `"enabled": false` for unwanted models or removing entries completely. For more information, please check our [Configuration...