Phoenix's Prompt Playground does not currently support direct file uploads (e.g., images, PDFs) via the UI for prompts, unlike Google AI Studio. However, you can work with multimodal inputs (such as images or audio) by encoding files as base64 and programmatically constructing prompts using the Python SDK or API, especially for Gemini models. This approach is documented for code-based workflows, but not exposed as a UI feature in the playground yet. File upload support in the UI is a requested and planned enhancement, but not available as of now <https://github.com/Arize-ai/phoenix/issues/8814|[source 1]> <https://github.com/Arize-ai/phoenix/issues/7528|[source 2]> <https://arize.com/docs/phoenix/integrations/llm-providers/google-gen-ai/google-gen-ai-evals#芦R4l38ut1letrnb禄|[source 3]>.
Would you like more detail on how to use file attachments programmatically with Gemini in Phoenix?
Sources:
- <https://github.com/Arize-ai/phoenix/issues/8814|https://github.com/Arize-ai/phoenix/issues/8814>
- <https://github.com/Arize-ai/phoenix/issues/7528|https://github.com/Arize-ai/phoenix/issues/7528>
- <https://arize.com/docs/phoenix/integrations/llm-providers/google-gen-ai/google-gen-ai-evals#芦R4l38ut1letrnb禄|https://arize.com/docs/phoenix/integrations/llm-providers/google-gen-ai/google-gen-ai-evals#芦R4l38ut1letrnb禄>
