Piero Savastano

Looks to me Langchain [is already doing this](https://github.com/langchain-ai/langchain/blob/4321d192eae441409485b9926013da2c1e275d29/libs/langchain/langchain/chat_models/ollama.py#L58), we probably can rely on it by passing chat history and system prompt as `HumanMessage`, `AIMessage` and `SystemMessage` objects from within `cat.llm`....

@valentimarco thanks for the diagram looks reasonable, also the `PromptTemplateTags`. To be totally honest I am scared about all this fragmentation we have to deal with. Here a few consideration:...

Also Ollama now supports the OpenAI pseudo standard https://github.com/ollama/ollama/blob/main/docs/openai.md

Work in progress in PR #783

Merged into `develop`

> 1. Abstract API for the Vectory Memory (so in future we are able to attach different dbs) Not strictly necessary to be honest, we fly well with Qdrant. Abstracting...

Awesome, agree with @nicola-corbellini on having a custom class to throw memories/points/documents around. Step 1: Follow the same output as `StrayCat.recall_memories_to_working_memory` Step 2: standardize with internal class About the method,...

> Hi guys, can I help you on this task? Hi @nickprock thanks There is already a PR #848 on the `recall` function, what of the other topics would you...

> Thanks @pieroit but I think I was too far behind on the project, I couldn't get anything right Available anytime for a code tour!

PR in review, merging soon