Frequently Asked Questions

Do I need to know programming to use PaleoPAL?

While PaleoPAL can help generate code, some familiarity with Python and data analysis concepts is helpful. The system is designed to assist researchers who already work with paleoclimate data, making their workflows more efficient.

Which LLM providers are supported?

• OpenAI (GPT-4o / GPT-5.5)
• Anthropic (Claude 3.5)
• Google (Gemini 2.5)
• xAI (Grok 3)
• Ollama (DeepSeek-R1, for local deployment)

You need at least one API key to use PaleoPAL.

How does the knowledge base work?

PaleoPAL uses semantic search (via Qdrant vector database) to retrieve relevant context from notebook snippets, API documentation, ontology entities, and SPARQL query templates. This context augments the AI’s responses, ensuring domain-specific accuracy.

Can I use PaleoPAL offline?

Partially. You can run PaleoPAL locally with Ollama for LLM inference, but you’ll still need internet access for initial setup, accessing LinkedEarth GraphDB, and downloading embedding models (first time only).

Is PaleoPAL free to use?

PaleoPAL is open-source software. However, you’ll need API keys from LLM providers, which may have usage costs depending on your provider and volume. Some providers offer free tiers for research.