This documentation site is structured into the following sections.
- Multimodal API Documentation shares the latest update on performing content moderation on multi-modal content.
- Annotation API Documentation introduces a new capability to perform adapted annotation on harmful content according to specific guidelines.
- Ungroundedness (Hallucination) Detection API detects ungroundedness generated by the large language models (LLMs). Ungroundedness refers to instances where the LLMs produce information that is non-factual or inaccurate from what was present in the source materials provided by the users.
If you get stuck, shoot us an email or use the feedback widget on the upper right of any page. We're excited you're here!