dmatora

Results 43 issues of dmatora

### Version Command-line (Python) version ### Operating System MacOS ### What happened? 1. pointed default agent to groq 2. tried setting importer and code monkey to ollama (tried different spelling)...

bug

### Version Command-line (Python) version ### Suggestion Each time gpt-pilot asks a question, user should be getting a notification, so that he doesn't have to stare at gpt-pilot for hours,...

enhancement

- Name(s) of the device: Xiaomi Mijia Induction Cooker 2 - Link: https://aliexpress.com/item/3256803347773765.html - Model: MCL02M (chunmi.ihcooker.v2) - Hardware version: esp32 - Firmware version: 2.2.0_0014

enhancement

This PR attempts to add support for setting the K/V cache quantization type directly from a model’s Modelfile, building on the recently merged K/V cache quantization feature introduced in PR...

Is there a way to avoid using SERPER_API_KEY | SEARCHAPI_API_KEY ?

self-host

Running https://github.com/nickscamara/open-deep-research/ occasionally throws `AI_NoObjectGeneratedError: No object generated: the tool was not called` in firebase ``` at async generateCompletions (/app/dist/src/scraper/scrapeURL/transformers/llmExtract.js:233:24) at async singleAnswerCompletion (/app/dist/src/lib/extract/completions/singleAnswer.js:8:24) at async performExtraction (/app/dist/src/lib/extract/extraction-service.js:492:111) at async...

bug

I asked Void to write React Hello World app. It did and asked if I want him to run `npm install` to install dependancies he also asked me if I...

This doesn't necessarily should be merged (at this stage) - OpenAI models dropdown in UI are misleading when ollama is enabled. But this does work now.

Same topic research returns open-deep-research - 2K characters openAI DeepResearch - 50K characters Whole point of research is to see details of how agent came to conclusion, and these are...