sinapsis-bertopic 0.1.0__tar.gz

sinapsis_bertopic-0.1.0/PKG-INFO

@@ -0,0 +1,310 @@
+Metadata-Version: 2.4
+Name: sinapsis-bertopic
+Version: 0.1.0
+Summary: Add your description here
+Project-URL: Homepage, https://sinapsis.tech
+Project-URL: Documentation, https://docs.sinapsis.tech/docs
+Project-URL: Tutorials, https://docs.sinapsis.tech/tutorials
+Project-URL: Repository, https://github.com/Sinapsis-AI/sinapsis-bertopic.git
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: bertopic>=0.17.4
+Requires-Dist: kaleido>=1.2.0
+Requires-Dist: pillow>=12.1.1
+Requires-Dist: sinapsis>=0.2.25
+Provides-Extra: wikipedia-reader
+Requires-Dist: sinapsis-langchain-readers[langchain-wikipedia-readers]>=0.1.8; extra == "wikipedia-reader"
+Provides-Extra: sinapsis-data-writers
+Requires-Dist: sinapsis-data-writers[opencv]>=0.1.16; extra == "sinapsis-data-writers"
+Provides-Extra: all
+Requires-Dist: sinapsis-bertopic[sinapsis-data-writers,wikipedia-reader]; extra == "all"
+
+<h1 align="center">
+<br>
+<a href="https://sinapsis.tech/">
+  <img
+    src="https://github.com/Sinapsis-AI/brand-resources/blob/main/sinapsis_logo/4x/logo.png?raw=true"
+    alt="" width="300">
+</a><br>
+Sinapsis BERTopic
+<br>
+</h1>
+
+<h4 align="center">Package for BERTopic </h4>
+
+<p align="center">
+<a href="#installation">🐍  Installation</a> •
+<a href="#features"> 🚀 Features</a> •
+<a href="#documentation">📙 Documentation</a> •
+<a href="#license"> 🔍 License </a>
+</p>
+
+**Sinapsis BERTopic** provides BERTopic model integration for the Sinapsis framework for topic clusterization.
+
+
+<h2 id="installation"> 🐍  Installation </h2>
+
+Install using your package manager of choice. We encourage the use of <code>uv</code>
+
+This project is private. Make sure you have authorized credentials before proceeding.
+
+**Recommended Method (using `.netrc`):**
+
+To avoid baking credentials into URLs, configure your `~/.netrc` file with your credentials:
+
+
+
+Example with <code>uv</code>:
+
+```bash
+  uv pip install sinapsis-bertopic --extra-index-url https://pypi.sinapsis.tech
+```
+ or with raw <code>pip</code>:
+```bash
+  pip install sinapsis-bertopic --extra-index-url https://pypi.sinapsis.tech
+```
+<h2 id="features">🚀 Features</h2>
+
+<h3>Templates Supported</h3>
+
+This package includes a publisher Template and a Worker agent
+- **BERTopicFitModel**: A template class for fitting BERTopic models and saving them to disk.
+- **BERTopicPredict**: Template for topic prediction using BERTopic models.
+- **BERTopicVisualizeDocuments**: BERTopic-based document visualization template for generating and exporting interactive topic model
+    visualizations.
+    This template extends BERTopicBase to provide functionality for encoding documents using sentence transformers,
+    fitting a BERTopic model, and producing interactive visualizations of documents in a reduced dimensional space.
+    The visualizations can be saved as HTML files and optionally exported as image arrays.
+- **BERTopicVisualizeTopics**: Template for BERTopic topic visualization.
+
+    This template extends BERTopicPredict to generate and save interactive visualizations
+    of topics discovered by a BERTopic model. It produces plotly-based visual representations
+    of topic relationships and characteristics, and persists them as HTML files.
+
+> [!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 ***BERTopicFitModel*** use ```sinapsis info --example-template-config BERTopicFitModel``` to produce an example config like:
+
+```yaml
+agent:
+  name: my_test_agent
+templates:
+- template_name: InputTemplate
+  class_name: InputTemplate
+  attributes: {}
+- template_name: BERTopicFitModel
+  class_name: BERTopicFitModel
+  template_input: InputTemplate
+  attributes:
+    bertopic_model_params:
+      language: english
+      top_n_words: 10
+      n_gram_range: !!python/tuple
+      - 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
+    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: !!python/tuple
+      - null
+      - null
+      - null
+    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]`'
+    bertopic_save_model_params:
+      serialization: safetensors
+      save_ctfidf: true
+      save_embedding_model: sentence-transformers/all-MiniLM-L6-v2
+    root_dir: /root/.cache/sinapsis
+    save_path: '`replace_me:<class ''str''>`'
+
+
+
+```
+
+
+<h2 id='example'>📚 Usage example</h2>
+
+Below is an example YAML configuration for an albumentations worker
+
+<details>
+<summary ><strong><span style="font-size: 1.4em;">Config</span></strong></summary>
+
+```yaml
+agent:
+  name: my_test_agent
+templates:
+- template_name: InputTemplate
+  class_name: InputTemplate
+  attributes: {}
+- template_name: BERTopicFitModel
+  class_name: BERTopicFitModel
+  template_input: InputTemplate
+  attributes:
+    bertopic_model_params:
+      language: english
+      top_n_words: 10
+      n_gram_range: !!python/tuple
+      - 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
+    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: !!python/tuple
+      - null
+      - null
+      - null
+    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]`'
+    bertopic_save_model_params:
+      serialization: safetensors
+      save_ctfidf: true
+      save_embedding_model: sentence-transformers/all-MiniLM-L6-v2
+    root_dir: /root/.cache/sinapsis
+    save_path: '`replace_me:<class ''str''>`'
+
+```
+</details>
+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:
+```bash
+sinapsis run name_of_config.yml
+```
+
+
+<h2 id="documentation">📙 Documentation</h2>
+
+Documentation for this and other sinapsis packages is available on the [sinapsis website](https://docs.sinapsis.tech/docs)
+
+Tutorials for different projects within sinapsis are available at [sinapsis tutorials page](https://docs.sinapsis.tech/tutorials)
+

sinapsis_bertopic-0.1.0/README.md

@@ -0,0 +1,289 @@
+<h1 align="center">
+<br>
+<a href="https://sinapsis.tech/">
+  <img
+    src="https://github.com/Sinapsis-AI/brand-resources/blob/main/sinapsis_logo/4x/logo.png?raw=true"
+    alt="" width="300">
+</a><br>
+Sinapsis BERTopic
+<br>
+</h1>
+
+<h4 align="center">Package for BERTopic </h4>
+
+<p align="center">
+<a href="#installation">🐍  Installation</a> •
+<a href="#features"> 🚀 Features</a> •
+<a href="#documentation">📙 Documentation</a> •
+<a href="#license"> 🔍 License </a>
+</p>
+
+**Sinapsis BERTopic** provides BERTopic model integration for the Sinapsis framework for topic clusterization.
+
+
+<h2 id="installation"> 🐍  Installation </h2>
+
+Install using your package manager of choice. We encourage the use of <code>uv</code>
+
+This project is private. Make sure you have authorized credentials before proceeding.
+
+**Recommended Method (using `.netrc`):**
+
+To avoid baking credentials into URLs, configure your `~/.netrc` file with your credentials:
+
+
+
+Example with <code>uv</code>:
+
+```bash
+  uv pip install sinapsis-bertopic --extra-index-url https://pypi.sinapsis.tech
+```
+ or with raw <code>pip</code>:
+```bash
+  pip install sinapsis-bertopic --extra-index-url https://pypi.sinapsis.tech
+```
+<h2 id="features">🚀 Features</h2>
+
+<h3>Templates Supported</h3>
+
+This package includes a publisher Template and a Worker agent
+- **BERTopicFitModel**: A template class for fitting BERTopic models and saving them to disk.
+- **BERTopicPredict**: Template for topic prediction using BERTopic models.
+- **BERTopicVisualizeDocuments**: BERTopic-based document visualization template for generating and exporting interactive topic model
+    visualizations.
+    This template extends BERTopicBase to provide functionality for encoding documents using sentence transformers,
+    fitting a BERTopic model, and producing interactive visualizations of documents in a reduced dimensional space.
+    The visualizations can be saved as HTML files and optionally exported as image arrays.
+- **BERTopicVisualizeTopics**: Template for BERTopic topic visualization.
+
+    This template extends BERTopicPredict to generate and save interactive visualizations
+    of topics discovered by a BERTopic model. It produces plotly-based visual representations
+    of topic relationships and characteristics, and persists them as HTML files.
+
+> [!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 ***BERTopicFitModel*** use ```sinapsis info --example-template-config BERTopicFitModel``` to produce an example config like:
+
+```yaml
+agent:
+  name: my_test_agent
+templates:
+- template_name: InputTemplate
+  class_name: InputTemplate
+  attributes: {}
+- template_name: BERTopicFitModel
+  class_name: BERTopicFitModel
+  template_input: InputTemplate
+  attributes:
+    bertopic_model_params:
+      language: english
+      top_n_words: 10
+      n_gram_range: !!python/tuple
+      - 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
+    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: !!python/tuple
+      - null
+      - null
+      - null
+    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]`'
+    bertopic_save_model_params:
+      serialization: safetensors
+      save_ctfidf: true
+      save_embedding_model: sentence-transformers/all-MiniLM-L6-v2
+    root_dir: /root/.cache/sinapsis
+    save_path: '`replace_me:<class ''str''>`'
+
+
+
+```
+
+
+<h2 id='example'>📚 Usage example</h2>
+
+Below is an example YAML configuration for an albumentations worker
+
+<details>
+<summary ><strong><span style="font-size: 1.4em;">Config</span></strong></summary>
+
+```yaml
+agent:
+  name: my_test_agent
+templates:
+- template_name: InputTemplate
+  class_name: InputTemplate
+  attributes: {}
+- template_name: BERTopicFitModel
+  class_name: BERTopicFitModel
+  template_input: InputTemplate
+  attributes:
+    bertopic_model_params:
+      language: english
+      top_n_words: 10
+      n_gram_range: !!python/tuple
+      - 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
+    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: !!python/tuple
+      - null
+      - null
+      - null
+    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]`'
+    bertopic_save_model_params:
+      serialization: safetensors
+      save_ctfidf: true
+      save_embedding_model: sentence-transformers/all-MiniLM-L6-v2
+    root_dir: /root/.cache/sinapsis
+    save_path: '`replace_me:<class ''str''>`'
+
+```
+</details>
+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:
+```bash
+sinapsis run name_of_config.yml
+```
+
+
+<h2 id="documentation">📙 Documentation</h2>
+
+Documentation for this and other sinapsis packages is available on the [sinapsis website](https://docs.sinapsis.tech/docs)
+
+Tutorials for different projects within sinapsis are available at [sinapsis tutorials page](https://docs.sinapsis.tech/tutorials)
+

sinapsis_bertopic-0.1.0/pyproject.toml

@@ -0,0 +1,67 @@
+[project]
+name = "sinapsis-bertopic"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "bertopic>=0.17.4",
+    "kaleido>=1.2.0",
+    "pillow>=12.1.1",
+    "sinapsis>=0.2.25",
+]
+
+[project.optional-dependencies]
+wikipedia-reader = [
+    "sinapsis-langchain-readers[langchain-wikipedia-readers]>=0.1.8",
+]
+sinapsis-data-writers = [
+    "sinapsis-data-writers[opencv]>=0.1.16",
+]
+all = [
+    "sinapsis-bertopic[sinapsis-data-writers,wikipedia-reader]",
+]
+
+[[tool.uv.index]]
+name = "sinapsis-core"
+url = "https://pypi.sinapsis.tech/"
+
+
+[tool.ruff]
+lint.select = [
+    "ARG",
+    "ANN",
+    "BLE",
+    "C4",
+    "E",
+    "F",
+    "FIX",
+    "FLY",
+    "I",
+    "PERF",
+    "PIE",
+    "RUF",
+    "RSE",
+    "SIM",
+    "SLOT",
+    "T10",
+    "T20",
+    "TD",
+    "TID",
+]
+
+
+lint.ignore = ['ANN401']
+line-length = 120
+show-fixes = true
+
+
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project.urls]
+Homepage = "https://sinapsis.tech"
+Documentation = "https://docs.sinapsis.tech/docs"
+Tutorials = "https://docs.sinapsis.tech/tutorials"
+Repository = "https://github.com/Sinapsis-AI/sinapsis-bertopic.git"

sinapsis_bertopic-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+