llm.sdk.providers.perplexity.chat — net.clojars.deadmeme5441/clojure-llm-sdk 0.1.0

Perplexity transport — OpenAI-shape body + citation/search-results surfacing.

Request building is identical to openai-chat. Response parsing extends the OpenAI parser with two extractions:

• :search_results [{:url :title :snippet}, ...] → richer CitationPart per result
• :citations ["url", ...] → URL-only CitationPart when search_results isn't present

Usage normalization delegates to normalize-openai-usage, which already picks up Perplexity's :citation_tokens and :num_search_queries when present.

Streaming: the final SSE chunk on /chat/completions carries :citations alongside :usage and :finish_reason. parse-stream-event returns a vector of events in that case — sdk/complete flattens multi-event return values.

build-request-perplexity clj

(build-request-perplexity profile request)

extract-citation-parts clj

(extract-citation-parts raw)

Return a vector of CitationPart maps from a Perplexity raw response. Prefers :search_results (carries title + snippet); falls back to :citations (URL-only).

make-transport clj

(make-transport)

parse-error-perplexity clj

(parse-error-perplexity _profile status body)

parse-response-perplexity clj

(parse-response-perplexity profile raw)

parse-stream-event-perplexity clj

(parse-stream-event-perplexity _profile line)

Parse a Perplexity SSE line into one or more StreamEvents.

Perplexity streams the same shape as OpenAI for content deltas. The final chunk packs citations, usage, and finish_reason together, so this returns a vector of events for that line (and a single event for the rest).

perplexity-cost-calculator clj

(perplexity-cost-calculator {:keys [_provider _model usage pricing]})

Reads canonical token + search-query usage and produces a cost-result. Falls back to the default token cost when no :search-cost-per-call is set.