> For the complete documentation index, see [llms.txt](https://docs.bcbi.brown.edu/codiac-for-health/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.bcbi.brown.edu/codiac-for-health/computing/python/large-language-models-llms.md). # Large Language Models (LLMs) More information to come! ## Overview Unstructured clinical text accounts for over 80% of health data. Traditional natural language processing (NLP) methods lack contextual flexibility and domain generalization. Large Language Models (LLMs) enable advanced capabilities: summarization, classification, translation, reasoning. ## Ollama Ollama is an open-source framework for managing, running, and serving large language models locally on host hardware. ### Prompt Engineering at Scale * Standardizes prompt templates and variables * Runs multiple prompts iteratively for evaluation or comparison * Logs inputs/outputs for reproducibility and auditability ### Input * Imports both structured data (like spreadsheets/CSVs) and standardized healthcare files (like FHIR patient records) * Cleans and extracts raw narrative text from unstructured sources, such as messy clinical notes * Clinical tables and free text can be combined in prompts. ### Output * LLM responses parsed and stored programmatically. * Results may be written to data frames or databases for downstream use. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.bcbi.brown.edu/codiac-for-health/computing/python/large-language-models-llms.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.