Over the past week, I have been working on my DevSandbox (https://github.com/jprogramista/devsandbox) to make it even easier to use. My main assumption was that it should be fully remote, with minimal reliance…
Category: Open Source
Ollama, DeepSeek News, AI Agents lists
Ollama Search Integration which is available at https://github.com/nik549/ollama-search turns my sight to Searxng I already saw it in some solutions, but with that project I can see it’s potential in my projects….
Zyphra/Zonos
Zonos-v0.1 is open-weight text-to-speech model, is trending on HF. It was trained on over 200k hours of diverse multilingual speech, resulting in expressiveness and quality comparable to — or even surpassing —…
DeepSeek R1 – model quantization for customer grade cards
This model has shaken the NASDAQ, so it is not a big surprise that people started to adapt it further. The requirements are very high for home / hobby usage, but already…
DeepSeek R1
DeepSeek R1 is available for regular users, in examples it beats o1 reasoning, there are also smaller models available 1.5B so quite a good potential to be tested. Exolabs of course tested…
Chat from LangChain
This is a significantly different RAG we used to think of: https://chat.langchain.com/. Take a look at the sample questions and observe how agents from LangChain and LangGraph utilize them to construct responses….
Genie 2, DeepThought-8B, snowflake-arctic-embed2
Google has recently released Genie 2, their most advanced large-scale foundation model capable of generating consistent and playable worlds for a minute. This advancement could be particularly beneficial for game developers, but…
DeepSeek-R1-Lite-Preview Challenges US AI Models
DeepSeek-R1-Lite-Preview is Now Live DeepSeek-R1-Lite-Preview is a new model from China, which is a direct competitor to the best US models like OpenAI’s o1 and Claude 3.5 Sonnet, beating them in some…
Ollama Tools Support merged to langchain4j
Just quick news: finally great community work in main branch , so next release will be something we wait for a long time (joking just from 3.1). For now we can probably…