Build and debug Groq API inference pipelines for chat and speech.
npx skills add https://github.com/syahravi/openclaw --skill groq-api-inference
Please help me install this Agent Skill. Skill: Groq API Inference Source: https://github.com/syahravi/openclaw/tree/main/groq-skill Command: npx skills add https://github.com/syahravi/openclaw --skill groq-api-inference
This Skill helps developers build, integrate, and troubleshoot Groq API inference workflows for chat, tool calling, and speech transcription, focusing on low-latency routing, structured outputs, and production-safe patterns.
Verify GROQ_API_KEY and run a models health check to select a low-latency model, configure a fallback, and confirm output validation rules in your memory file.
High-intent search queries and answers about installing and using this skill.
To implement Groq API inference, discover live models, keep short candidate sets per workload, and persist primary and fallback choices in memory. This ensures low-latency routing for chat and speech transcription pipelines.
The best way to handle Groq API rate limits and 5xx errors is using exponential backoff retries with jitter, capping attempts, and configuring automatic failover to fallback models for reliable chat completions.
To validate structured JSON outputs from Groq chat completions, enforce strict JSON schemas or parsing checks before executing downstream actions. This output validation safety pattern prevents malformed data from triggering automated write operations.
Yes, you need a GROQ_API_KEY environment variable to authenticate Groq API calls for audio transcription. This bearer authentication satisfies requirements for calling https://api.groq.com/openai/v1 endpoints securely.
Yes, you can use Groq API for both interactive chat and speech transcription in the same workflow. Route interactive chat to a fast model and transcriptions to a speech-optimized model, using runtime model selection to keep both workloads efficient.
Your Groq API inference pipeline fails on repeated rate limits because it lacks failover policies. Implementing exponential backoff retries with capped attempts and automatic failover to fallback models maintains pipeline reliability during rate limits.
devkit-stackConfigure Better Auth authentication for TypeScript/JavaScript applications.
zhnnky329Classify parsed subquestions into standard mathematical modeling problem types.
nguyenpv1980-wqValidate LLM structured output with schema and semantic checks before downstream use.
latestaiagentsRoute LLM tasks to models based on complexity, cost, and latency.
