# Intel + Prediction Guard hackathon info

- To utilize SOTA LLMs along with important safeguard (like factual consistency checking, toxicity filters, PII filters, prompt injection detection, etc.), use the following Prediction Guard access token:
- `q1VuOjnffJ3NO2oFN8Q9m8vghYc84ld13jaqdF7E`
- (free to use for the hackathon)
- Prediction Guard provides an easy way for you to implement popular LLMs methodologies like RAG and agents. Here are some links that might help as you build out your solutions:
- Main docs: https://docs.predictionguard.com/
- "Using LLMs" learning pathway: https://docs.predictionguard.com/usingllms
- RAG example (PG + LanceDB): https://docs.predictionguard.com/usingllms/augmentation#retrieval-augmentated-generation-rag
- PG as a LangChain LLM: https://docs.predictionguard.com/guides/langchainllm
- ManyChat chatbot with PG LLMs: https://docs.predictionguard.com/guides/ManyChat
- Natural language queries to databases (PG + DuckDB): https://docs.predictionguard.com/guides/ada
- Find Prediction Guard reps at the Intel booth(s) for help!