Skip to main content
The playground lets you test your namespace from the dashboard without writing code. The chat playground answers questions with agentic search: the model searches your documents itself, deciding what to look for and when it has enough context to answer. The playground also includes a search tab for running queries directly.

How it works

When you send a message, the model runs a tool-calling loop of up to 20 steps with two tools:
ToolDescription
searchSearches the namespace with a query the model writes, in semantic or keyword mode. Keyword search is available on Turbopuffer-backed namespaces (the default for managed namespaces).
expandFetches roughly 10 surrounding chunks (5 before, 5 after by position in the document) when a retrieved chunk is cut off or needs nearby context. Available on Turbopuffer-backed namespaces; not yet supported on Pinecone-backed namespaces.
The chat shows the progress of each search and expand call as the model works, then streams the final answer.

Modes

The chat playground has two modes:
ModeBehavior
Accurate (default)Each semantic search fetches Top K chunks (default 30) and reranks them down to the Rerank Limit (default 10) with the configured re-ranker.
FastSkips reranking. Each search returns the Rerank Limit (default 10) chunks directly.

Citations

Answers cite sources with inline pills resolved from the retrieved chunks. Click a pill to view the source text and its metadata.

Parameters

Open the parameters dialog to tune retrieval and generation:
ParameterDescription
Top KNumber of chunks fetched per semantic search, before reranking (default 30)
Rerank LimitNumber of chunks the model sees per search (default 10)
System PromptInstructions for the assistant. Defaults to a prompt tuned for agentic search
Re-rankerModel used to rerank results in Accurate mode
TemperatureSampling temperature. Has no effect on reasoning models like GPT-5.5
Use the model picker to change the language model. GPT-5.5 is the default.

Next steps

  • Agentic Search — Build the same tool-calling loop in your own app
  • Search — Query your namespace through the API
  • Hosting UI — Share a prebuilt chat interface with your users