active_learning:
  enabled: true
  schema_names:
    - sentiment  # Which annotation schemes to use
 
  min_annotations_per_instance: 1
  min_instances_for_training: 20
  update_frequency: 50  # Retrain after every 50 annotations
  max_instances_to_reorder: 1000

active_learning:
  enabled: true
 
  # Which schemas to use for training
  schema_names:
    - sentiment
 
  # Minimum requirements
  min_annotations_per_instance: 1
  min_instances_for_training: 20
 
  # Retraining frequency
  update_frequency: 50
 
  # How many instances to reorder
  max_instances_to_reorder: 1000
 
  # Classifier configuration
  classifier:
    type: LogisticRegression
    params:
      C: 1.0
      max_iter: 1000
 
  # Feature extraction
  vectorizer:
    type: TfidfVectorizer
    params:
      max_features: 5000
      ngram_range: [1, 2]
 
  # Model persistence
  model_persistence:
    enabled: true
    save_dir: "models/"
    max_saved_models: 5

# Logistic Regression (recommended starting point)
classifier:
  type: LogisticRegression
  params:
    C: 1.0
    max_iter: 1000
 
# Random Forest
classifier:
  type: RandomForestClassifier
  params:
    n_estimators: 100
    max_depth: 10
 
# Support Vector Classifier
classifier:
  type: SVC
  params:
    kernel: rbf
    probability: true
 
# Naive Bayes
classifier:
  type: MultinomialNB
  params:
    alpha: 1.0

# TF-IDF (recommended)
vectorizer:
  type: TfidfVectorizer
  params:
    max_features: 5000
    ngram_range: [1, 2]
    stop_words: english
 
# Count Vectorizer
vectorizer:
  type: CountVectorizer
  params:
    max_features: 3000
    ngram_range: [1, 1]
 
# Hashing Vectorizer (for large datasets)
vectorizer:
  type: HashingVectorizer
  params:
    n_features: 10000

active_learning:
  enabled: true
  schema_names:
    - sentiment
 
  # LLM-based selection
  llm_integration:
    enabled: true
    endpoint_type: vllm
    base_url: http://localhost:8000/v1
    model: meta-llama/Llama-2-7b-chat-hf
 
    # Mock mode for testing
    mock_mode: false

annotation_schemes:
  - annotation_type: radio
    name: sentiment
    labels: [Positive, Negative, Neutral]
 
  - annotation_type: radio
    name: topic
    labels: [Politics, Sports, Tech, Entertainment]
 
active_learning:
  enabled: true
  schema_names:
    - sentiment
    - topic
 
  # Schema-specific settings
  schema_config:
    sentiment:
      min_instances_for_training: 30
      update_frequency: 50
    topic:
      min_instances_for_training: 50
      update_frequency: 100

active_learning:
  enabled: true
  schema_names:
    - sentiment
 
  model_persistence:
    enabled: true
    save_dir: "models/"
    max_saved_models: 5  # Keep last 5 models
 
    # Save to database instead of files
    use_database: false

active_learning:
  enabled: true
  min_instances_for_training: 50  # Wait for 50 annotations

update_frequency: 100  # Retrain every 100 annotations

model_persistence:
  enabled: true
  save_dir: "models/"

task_name: "Sentiment Analysis with Active Learning"
task_dir: "."
port: 8000
 
data_files:
  - "data/reviews.json"
 
item_properties:
  id_key: id
  text_key: text
 
annotation_schemes:
  - annotation_type: radio
    name: sentiment
    description: "What is the sentiment?"
    labels:
      - Positive
      - Negative
      - Neutral
 
active_learning:
  enabled: true
  schema_names:
    - sentiment
 
  min_annotations_per_instance: 1
  min_instances_for_training: 30
  update_frequency: 50
  max_instances_to_reorder: 500
 
  classifier:
    type: LogisticRegression
    params:
      C: 1.0
      max_iter: 1000
 
  vectorizer:
    type: TfidfVectorizer
    params:
      max_features: 3000
      ngram_range: [1, 2]
 
  model_persistence:
    enabled: true
    save_dir: "models/"
    max_saved_models: 3
 
output_annotation_dir: "output/"
output_annotation_format: "json"
allow_all_users: true

active_learning:
  enabled: true
  schema_names:
    - sentiment
  min_instances_for_training: 30
 
ai_support:
  enabled: true
  endpoint_type: openai
 
  ai_config:
    model: gpt-4
    api_key: ${OPENAI_API_KEY}
 
  features:
    label_suggestions:
      enabled: true