How do I use local documents to inform my results?

You can incorporate external sources of information to provide specific context and thereby improve the accuracy and relevance of your model’s results. This is called RAG or “Retrieval-Augmented Generation”, a process to optimize the output of models by using provided data to supplement and enhance their pre-trained knowledge.

You can upload files to Dartmouth Chat from your local computer. Subsequent feedback from the model will begin by reviewing the uploaded files, using the context provided to inform the response.

To upload files, click on the + sign under the prompt window and select “Upload Files”. As files are uploded, file icons will appear in the prompt window. Note that image files can only be interpreted by models that list the “VISION” category.

Once those files have been successfully uploaded, you may create a prompt that references the document uploaded.

Didn’t find what you needed? Please reach out to research.computing@dartmouth.edu.