Use “Perplexity embedding readiness brief” in Recued. It provides a read-only Perplexity embedding workflow.

How it works 6 steps

Inspect the data fetches, transforms, gates, and output this recipe runs.

Process (6 steps)

◆ embed recued-core.perplexity.embedding.create

Create embedding on perplexity

■ vectors default

Apply default

■ vector_count count

Count items in vectors

✦ summarize core.ai.summarize

AI generates a concise summary

■ vector_table to_table

Format results as a data table

■ card to_summary

Format results as a summary card

▼

Output

summary card

table vector_table

Settings 6 configurable

Configurable at install. Defaults shown — change them anytime in Recued.

focus setting = Summarize whether the selected Perplexity embedding setup is ready for semantic search or RAG. Cover model, dimensions, encoding, returned vector rows, token usage, cost metadata when present, and practical next steps.

texts setting = [object Object]

dimensions setting = 1024

max length setting = 800

embedding model setting = pplx-embed-v1-0.6b

encoding format setting = base64_int8