Solo Mode

annotation_task_name: "Sentiment Classification"
task_dir: "."
 
data_files:
  - "data/reviews.jsonl"
 
item_properties:
  id_key: id
  text_key: text
 
solo_mode:
  enabled: true
 
  # The models that label. A list: the first is used, the rest are fallbacks.
  labeling_models:
    - endpoint_type: openai
      model: "gpt-4o"
      api_key: ${OPENAI_API_KEY}
      temperature: 0.1
      max_tokens: 1024
 
  # When the project may stop asking the human
  thresholds:
    end_human_annotation_agreement: 0.92
    minimum_validation_sample: 50
    confidence_low: 0.5
 
  state_dir: "solo_state_sentiment"
 
annotation_schemes:
  - annotation_type: radio
    name: sentiment
    description: "What is the sentiment of this text?"
    labels:
      - Positive
      - Neutral
      - Negative
 
output_annotation_dir: "output/"
export_annotation_format: "jsonl"

solo_mode:
  enabled: true
 
  # Models that label, and models that revise. Both are lists; revision_models
  # defaults to labeling_models when omitted.
  labeling_models:
    - endpoint_type: openai       # openai, anthropic, ollama, vllm, ...
      model: "gpt-4o"
      api_key: ${OPENAI_API_KEY}
      temperature: 0.1
      max_tokens: 1024
  revision_models:
    - endpoint_type: anthropic
      model: "claude-sonnet-4-20250514"
      api_key: ${ANTHROPIC_API_KEY}
      max_tokens: 1024
 
  # Sentence embeddings, used for diversity and neighbour lookups
  embedding:
    model_name: "all-MiniLM-L6-v2"
 
  # How the LLM's uncertainty is measured
  uncertainty:
    strategy: direct_confidence
    sampling_diversity:
      num_samples: 5
      temperature: 1.0
 
  # When the human can stop, and what counts as agreement per scheme type
  thresholds:
    end_human_annotation_agreement: 0.90
    minimum_validation_sample: 50
    confidence_low: 0.5
    confidence_high: 0.8
    periodic_review_interval: 100
    likert_tolerance: 1
    multiselect_jaccard_threshold: 0.5
    textbox_embedding_threshold: 0.7
    span_overlap_threshold: 0.5
 
  # Weights for the pools that choose what the human sees next
  instance_selection:
    low_confidence_weight: 0.3
    disagreement_weight: 0.1
    diversity_weight: 0.2
    llm_predicted_weight: 0.3
    random_weight: 0.1
    cartography_weight: 0.0
    edge_case_rule_weight: 0.0
 
  batches:
    llm_labeling_batch: 50
    max_parallel_labels: 200
 
  labeling_functions:
    enabled: true
    auto_extract: true
    max_functions: 50
    min_confidence: 0.85
    min_coverage: 3               # instances, not a fraction
    vote_threshold: 0.5
 
  edge_case_rules:
    enabled: true
    auto_extract_on_labeling: true
    confidence_threshold: 0.75
    min_rules_for_clustering: 10
    target_cluster_size: 15
    reannotation_enabled: true
    reannotation_confidence_threshold: 0.60
    max_reannotations_per_instance: 2
 
  confusion_analysis:
    enabled: true
    min_instances_for_pattern: 3
    max_patterns: 20
    auto_suggest_guidelines: false
 
  prompt_optimization:
    enabled: true
    find_smallest_model: true
    target_accuracy: 0.85
    optimization_interval_seconds: 300
    accuracy_weight: 0.7
    length_weight: 0.2
 
  # Send cheap cases to a small model and hard ones to a larger one
  confidence_routing:
    enabled: false
    tiers:
      - name: cheap
        confidence_threshold: 0.8
        model:
          endpoint_type: ollama
          model: "llama3.2"
 
  refinement_loop:
    enabled: true
    trigger_interval: 50
    min_improvement: 0.02
    max_cycles: 5
    patience: 2
 
  state_dir: "solo_state_sentiment"

solo_mode:
  revision_models:
    - endpoint_type: anthropic
      model: "claude-sonnet-4-20250514"
      api_key: ${ANTHROPIC_API_KEY}
 
  refinement_loop:
    enabled: true
    trigger_interval: 50           # run a cycle every 50 new human labels
    min_improvement: 0.02          # stop if a cycle gains less than 2%
    max_cycles: 5
    patience: 2                    # cycles below min_improvement before stopping

# Auto-generated labeling function 1
# Precision: 0.96, Coverage: 0.08
def lf_strong_positive_words(text):
    positive = {"excellent", "amazing", "fantastic", "outstanding", "perfect"}
    if any(w in text.lower() for w in positive):
        if not any(neg in text.lower() for neg in {"not", "never", "no"}):
            return "Positive"
    return None  # abstain
 
# Auto-generated labeling function 2
# Precision: 0.93, Coverage: 0.05
def lf_explicit_negative(text):
    negative = {"terrible", "awful", "horrible", "worst", "disgusting"}
    if any(w in text.lower() for w in negative):
        return "Negative"
    return None

solo_mode:
  labeling_functions:
    enabled: true
    auto_extract: true
    max_functions: 50
    min_confidence: 0.85
    min_coverage: 3          # minimum instances a function must cover
    vote_threshold: 0.5      # agreement needed when functions disagree

solo_mode:
  # Disagreement is a phase, not a configurable block. What you control is how
  # heavily disagreement weighs when Potato picks the next instance.
  instance_selection:
    disagreement_weight: 0.3
    low_confidence_weight: 0.3
    diversity_weight: 0.2
    llm_predicted_weight: 0.1
    random_weight: 0.1

solo_mode:
  thresholds:
    confidence_low: 0.5           # below this, the human sees it
    confidence_high: 0.8          # above this, the LLM's label stands
    periodic_review_interval: 100 # surface low-confidence labels this often
 
  batches:
    llm_labeling_batch: 50
    max_parallel_labels: 200

solo_mode:
  labeling_models:
    - endpoint_type: laya
      model: convaiinnovations/laya
  revision_models:                     # required: decision models cannot write text
    - endpoint_type: vllm
      model: google/gemma-4-12B-it-qat-w4a16-ct
      base_url: http://localhost:8001/v1
  confidence_routing:
    enabled: true
    tiers:
      - name: laya
        confidence_threshold: 0.9
        model:
          endpoint_type: laya
          model: convaiinnovations/laya
          device: cpu
      - name: llm
        confidence_threshold: 0.5
        model:
          endpoint_type: vllm
          model: google/gemma-4-12B-it-qat-w4a16-ct
          base_url: http://localhost:8001/v1

solo_mode:
  suggestions:
    display: blind_sample      # before_label | after_label | blind_sample
    blind_rate: 0.2
    minimum_blind_sample: 20

solo_mode:
  instance_selection:
    low_confidence_weight: 0.3
    diversity_weight: 0.2
    llm_predicted_weight: 0.3
    disagreement_weight: 0.1
    random_weight: 0.1
    cartography_weight: 0.0
    edge_case_rule_weight: 0.0

solo_mode:
  edge_case_rules:
    enabled: true
    auto_extract_on_labeling: true   # derive rules as you label
    confidence_threshold: 0.75
    min_rules_for_clustering: 10
    target_cluster_size: 15
    reannotation_enabled: true       # revisit items a new rule contradicts
    reannotation_confidence_threshold: 0.60
    max_reannotations_per_instance: 2

solo_mode:
  prompt_optimization:
    enabled: true
    find_smallest_model: true          # prefer the cheapest model that holds up
    target_accuracy: 0.85
    optimization_interval_seconds: 300
    accuracy_weight: 0.7               # how the candidates are scored
    length_weight: 0.2