Changelog

Native File Processing in Chat: Process Images, PDFs, Audio and Videos Directly in Your Conversations

You can now work with files directly in your agents with intuitive file naming and broad model compatibility!

Native File Processing transforms how you handle documents, images, videos, and audio in your AI workflows. Files are now automatically associated with their original names, making references natural and intuitive. Best of all, this feature works seamlessly across OpenAI, Anthropic, and Gemini models with extensive file format support.

➡️ Reference files by name – Simply mention the file name in your prompts for more natural conversations

➡️ OpenAI compatibility – Process images (PNG, JPG, JPEG, WEBP, GIF) and PDFs across 20+ models including GPT-4o, O1, O3, O4 Mini, and GPT-4.1 series

➡️ Anthropic integration – Work with images (PNG, JPG, JPEG, WEBP, GIF) across all Claude models including v3 Opus, v3.5/v3.7/v4 Sonnet, and v4 Opus

➡️ Gemini versatility – Handle the widest range of files including images, videos (MP4, MPEG, MOV, etc.), PDFs, and audio (WAV, MP3, etc.) with all Gemini 2.0/2.5 models

➡️ Backward compatibility – All existing workflows continue to function as expected

With Native File Processing, you can create more intuitive, powerful workflows that leverage the unique capabilities of each AI model while maintaining a consistent user experience across your entire agent ecosystem.

To use this feature, simply upload supported files when interacting with your agents. The system will automatically handle the file processing based on the model you're using.

Start creating more natural, file-rich experiences with your AI agents today!