Langchain project aiming at achieving perpetual research with the help of a chain of ai researching agents.
- Install and launch Ollama:
ollama serve
- Create new environment:
conda env create -f environment.yml
- Activate the new environment:
conda activate NewsSumoriser
- Pull the model you intend to use:
ollama pull mixtral:8x7b-instruct-v0.1-q5_K_M
- Run:
python3 main.py
The default model is hardcoded into the lookup.py
file.
A set of tools to give LLMs research capabilities.
A recursive tree structure granting Research Chain the ability to create large hierarchical structures of LLMs and the tools they are using
A service launching for a set period of time, and then allowing the user to summarize either the entire output of the tree, or a small, selected subset of it's structure.