llm_fn: unstructured (DeepSeek) | llm_fn: unstructured (Groq) | llm_fn_structured: schema-first (DeepSeek) | llm_mutate: unstructured (Groq) | llm_mutate: shorthand syntax (NEW in v0.6.2) | llm_mutate with .structured flag (NEW in v0.6.2) | Soft structured output with tags | Row batching: many rows per call | llm_mutate_structured: structured with shorthand (Groq)

Designing the Experiment | Vectorised Execution with Soft Structuring | Conclusion

TL;DR | What the major providers actually support | Why prefer schema output? | Why JSON-only still matters | Quirks you will hit in practice | LLMR helpers to blunt those edges | Minimal patterns (guarded code) | 1) JSON mode, no schema (works across OpenAI-compatible providers) | 2) Schema mode that actually works (Groq, open model) | 3) DeepSeek: force a schema | 4) Groq: another structured output example | Defensive patterns (no API calls) | Pro tip: Combine with parallel execution | Choosing the mode | References

Prepare the Text Data | Configure Embedding Model | Generate Embeddings | Analyze Similarity | Expected Results

DeepSeek: deepseek-chat | DeepSeek: deepseek-reasoner | Groq: llama-3.1-8b-instant | Groq: openai/gpt-oss-20b | Using the chat history | Inspect the full conversation | Structured chat in one call (DeepSeek example)

Overview | Build a factorial design | Run unstructured | Structured version