API Support¶

GeneInsight supports two API services for topic refinement:

OpenAI API¶

The default option that works with models like gpt-4o-mini.

Configuration:¶

API Key Setup:

Set the environment variable:
```
export OPENAI_API_KEY=your_openai_key_here
```
Alternatively, create a .env file in your project directory with:
```
OPENAI_API_KEY=your_openai_key_here
```

Command Line Options:

geneinsight query_genes.txt background_genes.txt \
  --api_service openai \
  --api_model gpt-4o-mini \
  --api_temperature 0.2

Supported Models:¶

gpt-4o-mini (default)
gpt-3.5-turbo
gpt-4
gpt-4o
gpt-o3-mini
gpt-o1-mini

Ollama API¶

Local option for running models on your own hardware.

Requirements:¶

Ollama installed with models that support tool use (see supported models)
API base URL parameter set (typically to http://localhost:11434/v1)

Example Usage:¶

geneinsight query_genes.txt background_genes.txt \
  --api_service ollama \
  --api_model llama3:8.1b \
  --api_base_url "http://localhost:11434/v1"

Recommended Models:¶

llama3:8b
llama3:70b
mistral:7b

Custom API Configuration¶

For advanced users, additional API parameters can be adjusted:

--api_parallel_jobs: Control the number of concurrent API requests (default: 1)
--api_temperature: Adjust the randomness of the model’s output (default: 0.2)

Performance Considerations¶

OpenAI API typically provides higher quality summaries but incurs usage costs
Ollama offers cost-free local processing but may require significant hardware resources
Consider adjusting --api_temperature based on your needs: * Lower values (0.1-0.3) for more consistent, focused results * Higher values (0.5-0.8) for more diverse, creative summaries