feat: add Perplexity as a provider - #4395
Closed
123mikeyd wants to merge 2 commits into
Closed
Conversation
Major update to meme-generation skill: - Path D: Veo/Gemini video memes (text-to-video, image-to-video) - Chained scenes for sequential narrative generation - Frame interpolation for transition effects - Video extension up to 148 seconds - Path E: Kling AI video memes (image-to-video) - Camera control, motion brush, multi-shot storyboarding - Voice integration for dialogue - Path F: Hedra lip-sync video (character singing/speaking) - Audio-driven lip sync from still images - Music video production workflow - Stylized art preservation tips - Video post-processing section (ffmpeg) - Text burn-in, audio overlay, GIF conversion, concatenation - Provider credential check table - Video-specific pitfalls Also includes all prior improvements: - Path B: Custom Pillow composites (object labels, avatars, memorials) - Path C: AI-generated art memes - Nous Research team assets and branding - Font preferences (Courier New / Liberation Mono Bold) Co-authored-by: 123mikeyd
Add Perplexity (Sonar API) as a first-class provider. Perplexity offers OpenAI-compatible chat completions with built-in web search grounding. Changes: - auth.py: Add ProviderConfig entry (api_key auth, https://api.perplexity.ai) - models.py: Add model list (sonar, sonar-pro, sonar-reasoning-pro, sonar-deep-research), provider label, aliases (pplx, sonar), provider order - config.py: Add PERPLEXITY_API_KEY and PERPLEXITY_BASE_URL env var definitions, update fallback provider comment templates - setup.py: Add to setup wizard provider choices and default model list Usage: hermes setup # select Perplexity from provider list hermes -m perplexity:sonar-pro hermes -m pplx:sonar-reasoning-pro
alt-glitch
added
type/feature
Collaborator
Collaborator
|
related |
Contributor
|
Thanks for the Perplexity integration work. Current
Automated hermes-sweeper review. |
teknium1
added
the
sweeper:implemented-on-main
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add Perplexity (Sonar API) as a first-class provider.\n\nPerplexity offers OpenAI-compatible chat completions with built-in web search grounding.\n\n## Changes\n- auth.py: ProviderConfig entry (api_key auth, https://api.perplexity.ai)\n- models.py: Model list (sonar, sonar-pro, sonar-reasoning-pro, sonar-deep-research), labels, aliases (pplx, sonar)\n- config.py: PERPLEXITY_API_KEY and PERPLEXITY_BASE_URL env var definitions\n- setup.py: Setup wizard provider choice and handler\n\n## Usage\n
\nhermes setup # select Perplexity from provider list\nhermes -m perplexity:sonar-pro\nhermes -m pplx:sonar-reasoning-pro\n\n\nRequested by a community member in Discord. Perplexity uses standard OpenAI-compatible chat completions so no special adapter needed -- just key + base URL.