Dataset Formats and Schemas

Datasets can be created from captured traffic or uploaded as JSONL files. This page covers the supported formats.

Supported formats

The system auto-detects the format from the first valid line. All rows in a file must use the same format.

Source-backed format

Each line has a top-level request and optional response object containing raw provider bodies.

Validation notes:

• The request must include a usable model value.
• response may be omitted or set to null if you only have request-side data.

{"request":{"model":"gpt-4","messages":[{"role":"user","content":"Hello"}],"temperature":0.7,"max_tokens":100},"response":{"id":"chatcmpl-123","object":"chat.completion","created":1700000000,"model":"gpt-4","choices":[{"index":0,"message":{"role":"assistant","content":"Hi there!"},"finish_reason":"stop"}]}}

Tag rows with a task

Source-backed rows can be assigned to a task by setting x-inference-task-id inside request.metadata. Rows that share a task ID are grouped under that task in the dashboard, exactly like live gateway traffic tagged with the x-inference-task-id header.

{"request":{"model":"gpt-4","messages":[{"role":"user","content":"Hello"}],"metadata":{"x-inference-task-id":"support-summaries"}},"response":{"choices":[{"index":0,"message":{"role":"assistant","content":"Hi there!"},"finish_reason":"stop"}]}}

Multimodal rows

Requests may include image content using standard OpenAI-style image_url content parts — either data: base64 URLs or public HTTPS URLs. Image parts are preserved through the import unchanged.

{"request":{"model":"google/gemma-3-27b-instruct/bf-16","messages":[{"role":"user","content":[{"type":"text","text":"Describe this image"},{"type":"image_url","image_url":{"url":"data:image/jpeg;base64,/9j/4AAQ..."}}]},"metadata":{"x-inference-task-id":"image-descriptions"}},"response":{"choices":[{"index":0,"message":{"role":"assistant","content":"A photo of ..."},"finish_reason":"stop"}]}}

Hugging Face format

Each line has a top-level messages array with role/content objects.

Valid roles: system, user, assistant, tool.

Additional supported fields:

• content may be a string or an array of content parts for multimodal rows.
• Assistant messages may include tool_calls.
• Tool messages must include tool_call_id.
• Top-level tools are preserved on import.

{"messages":[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is 2+2?"},{"role":"assistant","content":"4"}]}

When importing Hugging Face-format rows, the system:

• Treats the last assistant turn as the imported response and earlier turns as request context
• Synthesizes request/response payloads so evals and detail views work
• Sets request_model to unknown-imported-model
• Sets token usage and costs to zero
• Stores the original row id in metadata as importOriginalRowId

Validation behavior

• Files must be valid JSONL.
• Invalid rows are reported with line numbers in the upload status details.
• Uploads can complete with partial failures if at least one row imports successfully.
• If every row fails validation, the upload status is failed.

Upload limits

Download formats

Datasets can be downloaded in two formats:

In the UI, click Download and choose the format. In the CLI:

# Default (Hugging Face)
inf dataset download my-dataset

# Source-backed format

inf dataset download my-dataset --format source-backed