Skip to content

LLM_Setup.md

Latest commit

 

History

History
87 lines (51 loc) · 2 KB

LLM_Setup.md

File metadata and controls

87 lines (51 loc) · 2 KB
Raw

🧬 Gene Expression Explanation – README

You can get LLM explanations from our .explain step by setting llm_explain=True. Therefore you need to setup LLM Clients

You can use either:

  • Mistral API (cloud-based)
  • Ollama (local models running on your machine)

Requirements

Depending on if you want to use Mistral or Ollama you need to have:

  • a Mistral API key
  • Ollam installed and at least one model served

⚙️ Environment Setup

1. Using Mistral API

Set an API key in your .env file in the root of the repository

MISTRAL_API_KEY=your_api_key_here

Models

You may use any model served by Mistral, for example:

  • mistral-small-latest
  • mistral-medium-latest
  • mistral-large-latest

Make sure the model_name you pass to .explain matches an available Mistral model.

2. Using Ollama

Ollama runs models locally. You must first install Ollama and pull the model you want:

ollama pull <model-name>

Your model_name must match exactly the name of the model served by Ollama:

  • qwen2.5:0.5b
  • deepseek-r1:8b

3. Using Openrouter

To use a widespread options of models you can use Openrouter. For this simply set a environment variable in your terminal with:

export OPENROUTER_PREMIUM_API_KEY="sk-my-key"

4. Using ScaDS-LLM server

If you are a ScaDS.AI member or have a ZIH TU Dresden account, you can use our self-hosted LLM server (https://llm.scads.ai/docs/).

To enable this, set an environment variable like this:

export SCADS_LLM_API_KEY="sk-my-key"

``

🧬 Using .explain() for Gene Expression Interpretation

The .explain() method can generate a short biological explanation and hypothesis about what is happening in disease vs healthy samples given a list of altered genes.

Example

varix.explain(explainer="", llm_explain=True, llm_client="ollama", llm_model="qwen2.5:0.5b")

or

varix.explain(explainer="", llm_explain=True, llm_client="mistral", llm_model="mistral-small-latest")