Medical_LLM_Translation

We have installed the Gaia Node by following the documentation. We have used GaiaNet project is to enable each individual to create and run his or her own agent service node using finetuned LLMs and proprietary knowledge.

We have used LlamaParse to  parse the unstructured PDF file to a structured markdown file. It is a tool to parse files to create optimal RAGs.

The proprietary knowledge used here was survey papers on Medical LLM- Challenges faced by Medical LLM, Applications of Medical LLM  and different Usecases of it to supplement the LLM.

Each knowledge base is a snapshot file for a vector collection.  We have done the changes to the config file specified our customized embedding models. We have also customized our system prompts and rag prompts.

The system prompt option sets a system prompt. It provides the background and "personality" of the node. Each API request can set its own system prompt.

The rag prompt is the prompt to be appended after the system prompt (or user query). It introduces the RAG context retrieved from the vector database, which follows it.

The Medical LLM works as intended to help to understand the landscape of Medical LLM and what is the progress made in the field. We have successfully implemented the use case which would be beneficial for the end users including medical professionals, doctors, researchers , students etc. It would be a great tool to help medical professionals and researchers to understand the complexities involved very easily.