dokimi answers

usage: dokimi answers [-h] {generate} ...

positional arguments:
  {generate}
    generate  Generate context-arm and baseline answers

options:
  -h, --help  show this help message and exit

dokimi answers generate

usage: dokimi answers generate [-h] --product PRODUCT --questions QUESTIONS [--run-id RUN_ID]
                               [--output OUTPUT] [--model MODEL]
                               [--provider {openai,anthropic,amazon-bedrock,google-vertex,openrouter,openai-codex}]
                               [--max-tokens MAX_TOKENS] [--top-k TOP_K]
                               [--rerank-threshold RERANK_THRESHOLD] [--debug-retrieval]
                               [--concurrency CONCURRENCY] [--doc-source DOC_SOURCE]
                               [--context7-id CONTEXT7_ID] [--ragas] [--ragas-model RAGAS_MODEL]
                               [--ragas-provider {openai,anthropic}]

options:
  -h, --help            show this help message and exit
  --product PRODUCT     Product name (e.g., oneTBB)
  --questions QUESTIONS
                        Path to questions JSON file
  --run-id RUN_ID       Run tag for multi-model comparison (e.g. gpt4o). Sets output to
                        results/{product}_{run_id}/answers/{product}.json
  --output OUTPUT       Output file (default: answers/{product}.json)
  --model MODEL         LLM model for answering
  --provider {openai,anthropic,amazon-bedrock,google-vertex,openrouter,openai-codex}
  --max-tokens MAX_TOKENS
                        Max tokens to retrieve per question
  --top-k TOP_K         Number of docs to retrieve before reranking (default from
                        config/products.yaml retrieval.top_k or 3)
  --rerank-threshold RERANK_THRESHOLD
                        Min relevance score (0-1) to keep docs
  --debug-retrieval     Include retrieval metadata in output
  --concurrency CONCURRENCY
                        Parallel API calls (default: 5)
  --doc-source DOC_SOURCE
                        Documentation source: 'context7' (default), 'local:<path>', 'url:<url>'
  --context7-id CONTEXT7_ID
                        Explicit Context7 library ID. Overrides auto-resolution.
  --ragas               Run RAGAS meta-evaluation after answer generation and save alongside
                        answers.
  --ragas-model RAGAS_MODEL
                        LLM for RAGAS judge (default: claude-sonnet-5-5)
  --ragas-provider {openai,anthropic}
                        Provider for RAGAS judge LLM (default: anthropic)