sinapsis-bertopic 0.1.2

Package for topic modeling using BERTopic, including templates for fitting models and making predictions.

Sinapsis BERTopic

Package for topic modeling using BERTopic.

🐍 Installation • 🚀 Features • 📙 Documentation • 🔍 License

Sinapsis BERTopic provides BERTopic model integration for the Sinapsis framework for topic clusterization.

🐍 Installation

Install using your package manager of choice. We encourage the use of uv

Example with uv:

  uv pip install sinapsis-bertopic --extra-index-url https://pypi.sinapsis.tech

or with raw pip:

  pip install sinapsis-bertopic --extra-index-url https://pypi.sinapsis.tech

🚀 Features

Templates Supported

This package includes a publisher Template and a Worker agent

• BERTopicFitModel: A template class for fitting BERTopic models and saving them to disk.
• BERTopicFitModelFromDataFrame: A template class for fitting BERTopic models using data from a DataFrame and saving the model to disk.
• BERTopicPredict: Template for topic prediction using BERTopic models.

[!TIP] Use CLI command sinapsis info --all-template-names to show a list with all the available Template names installed with Sinapsis OpenAI.

[!TIP] Use CLI command sinapsis info --example-template-config TEMPLATE_NAME to produce an example Agent config for the Template specified in TEMPLATE_NAME.

For example, for BERTopicPredict use sinapsis info --example-template-config BERTopicPredict to produce an example config like:

agent:
  name: my_test_agent
templates:
- template_name: InputTemplate
  class_name: InputTemplate
  attributes: {}
- template_name: BERTopicPredict
  class_name: BERTopicPredict
  template_input: InputTemplate
  attributes:
    root_dir: /root/.cache/sinapsis
    export_visualization_to_image: true
    image_export_params:
      format: png
      width: null
      height: null
      scale: null
      validate_figure: true
    sentence_model_name: sentence-transformers/all-MiniLM-L6-v2
    model_path: '`replace_me:<class ''str''>`'
    visualize_predictions: true
    visualize_topics: true
    historical_data_path: null
    prediction_viz_path: prediction_viz.html
    visualize_topics_params:
      topics: null
      top_n_topics: null
      use_ctfidf: false
      custom_labels: false
      title: <b>Intertopic Distance Map</b>
      figure_width: 650
      figure_height: 650
    save_topic_visualization_path: topics_visualization.html

📚 Usage example

Below is an example YAML configuration for BERTopic model fit.

Config

agent:
  name: my_test_agent
templates:
- template_name: InputTemplate
  class_name: InputTemplate
  attributes: {}
- template_name: BERTopicFitModel
  class_name: BERTopicFitModel
  template_input: InputTemplate
  attributes:
    root_dir: /root/.cache/sinapsis
    export_visualization_to_image: true
    image_export_params:
      format: png
      width: null
      height: null
      scale: null
      validate_figure: true
    sentence_model_name: sentence-transformers/all-MiniLM-L6-v2
    bertopic_model_params:
      language: english
      top_n_words: 10
      n_gram_range:
      - 1
      - 1
      min_topic_size: 10
      nr_topics: null
      low_memory: false
      calculate_probabilities: false
      seed_topic_list: null
      zeroshot_topic_list: null
      zeroshot_min_similarity: 0.7
    bertopic_save_model_params:
      serialization: safetensors
      save_ctfidf: true
    hdbscan_model_params:
      min_cluster_size: 5
      min_samples: null
      cluster_selection_epsilon: 0.0
      cluster_selection_persistence: 0.0
      max_cluster_size: 0
      metric: euclidean
      alpha: 1.0
      p: null
      algorithm: best
      leaf_size: 40
      approx_min_span_tree: true
      gen_min_span_tree: false
      core_dist_n_jobs: 4
      cluster_selection_method: eom
      allow_single_cluster: false
      prediction_data: false
      branch_detection_data: false
      match_reference_implementation: false
      cluster_selection_epsilon_max: '`replace_me:<class ''float''>`'
      kwargs: '`replace_me:dict[str, typing.Any]`'
    save_documents_visualization_path: documents_visualization.html
    save_model_path: '`replace_me:<class ''str''>`'
    save_training_data: false
    save_training_data_path: training_data.pkl
    umap_model_params:
      n_neighbors: 15
      n_components: 2
      metric: euclidean
      metric_kwds: null
      output_metric: euclidean
      output_metric_kwds: null
      n_epochs: null
      learning_rate: 1.0
      init: spectral
      min_dist: 0.1
      spread: 1.0
      low_memory: true
      n_jobs: -1
      set_op_mix_ratio: 1.0
      local_connectivity: 1.0
      repulsion_strength: 1.0
      negative_sample_rate: 5
      transform_queue_size: 4.0
      a: null
      b: null
      random_state: null
      angular_rp_forest: false
      target_n_neighbors: -1
      target_metric: categorical
      target_metric_kwds: null
      target_weight: 0.5
      transform_seed: 42
      transform_mode: embedding
      force_approximation_algorithm: false
      verbose: false
      tqdm_kwds: null
      unique: false
      densmap: false
      dens_lambda: 2.0
      dens_frac: 0.3
      dens_var_shift: 0.1
      output_dens: false
      disconnection_distance: null
      precomputed_knn:
      - null
      - null
      - null
    visualize_documents_params:
      topics: null
      sample: null
      hide_annotations: false
      hide_document_hover: false
      custom_labels: false
      title: <b>Documents and Topics</b>
      width: 1200
      height: 750

This configuration defines an agent and a sequence of templates to fit a bertopic data based on incoming data.

To run the config, use the CLI:

sinapsis run name_of_config.yml

📙 Documentation

Documentation for this and other sinapsis packages is available on the sinapsis website

Tutorials for different projects within sinapsis are available at sinapsis tutorials page