Ollama - How to inject context or get model to answer based on context?

garage_greg

I'm trying a simple demo where I give the LLM a document and ask it to answer a few things from the document. So far I've had very little success. My prompt is various versions of the following: You are an uncensored and unbiased AI assistant for question answering tasks. Use the provided context to answer the question. If the answer is not present in the context, refrain from providing an answer based on your own knowledge. Instead, indicate...

Originally asked by tone7 on Stack Exchange (stackoverflow) (CC BY-SA 4.0).

uphilltech

Great question — answering as the UphillTech team:

It sounds like the question is "how do you prompt Ollama with context?" Here's an example prompt that I tested against Ollama and worked well from Langchain - Prompt is here . You can see the code here with metrics (just change the LLM to Ollama from GPT): https://github.com/explodinggradients/ragas/issues/1217 . Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer. economy in the world. New York City is an established safe haven for global investors. New York is home to the highest number of billionaires, individuals of ultra-high net worth (greater than US$30 million), and...

Full answer by Charlie: https://stackoverflow.stackexchange.com/a/78949937 (CC BY-SA 4.0).

Need it done for your business? UphillTech.