Index

_

__init__() (src.clients.api_client.ProductionEmbeddingClient method) (src.core.core.ForzaEmbed method) (src.core.processing.Processor method) (src.reporting.aggregator.DataAggregator method) (src.reporting.markdown_filter.MarkdownFilter method) (src.reporting.reporting.ReportGenerator method) (src.services.embedding_service.EmbeddingService method) (src.services.visualization_service.VisualizationService method) (src.utils.database.EmbeddingDatabase method) (src.utils.models.Base method) (src.utils.models.EmbeddingCache method) (src.utils.models.EvaluationMetric method) (src.utils.models.GeneratedFile method) (src.utils.models.GlobalChart method) (src.utils.models.Model method) (src.utils.models.ProcessingResult method) (src.utils.models.TSNECoordinate method)

_instances (src.clients.fastembed_client.FastEmbedClient attribute) (src.clients.sentencetransformers_client.SentenceTransformersClient attribute) (src.clients.transformers_client.TransformersClient attribute)

A

add_evaluation_metrics() (src.utils.database.EmbeddingDatabase method) add_generated_file() (src.utils.database.EmbeddingDatabase method) add_global_chart() (src.utils.database.EmbeddingDatabase method)

add_model() (src.utils.database.EmbeddingDatabase method) analyze_silhouette_by_cluster() (in module src.metrics.silhouette_decomposition) api_batch_sizes (src.core.config.MultiprocessingSettings attribute), [1] AppConfig (class in src.core.config)

B

Base (class in src.utils.models) base_model_name (src.utils.models.Model attribute), [1]

base_url (src.clients.api_client.ProductionEmbeddingClient attribute) (src.core.config.ModelConfig attribute), [1]

C

cache_path (src.reporting.aggregator.DataAggregator attribute) calculate_all_metrics() (in module src.metrics.evaluation_metrics) calculate_silhouette_metrics() (in module src.metrics.evaluation_metrics) calculate_similarity() (src.services.similarity_service.SimilarityService static method) chart_type (src.utils.models.GlobalChart attribute), [1] chunk_overlap (src.core.config.GridSearchParams attribute), [1] (src.utils.models.Model attribute), [1] chunk_size (src.core.config.GridSearchParams attribute), [1] (src.utils.models.Model attribute), [1] chunk_text() (in module src.utils.utils) chunking_strategy (src.core.config.GridSearchParams attribute), [1] (src.utils.models.Model attribute), [1] clear_tsne_cache() (src.utils.database.EmbeddingDatabase method) config (src.core.core.ForzaEmbed attribute) (src.core.processing.Processor attribute) (src.reporting.markdown_filter.MarkdownFilter attribute) (src.reporting.reporting.ReportGenerator attribute) (src.services.embedding_service.EmbeddingService attribute) (src.utils.database.EmbeddingDatabase attribute)

config_name (src.core.core.ForzaEmbed attribute) (src.reporting.markdown_filter.MarkdownFilter attribute) (src.reporting.reporting.ReportGenerator attribute) config_path (src.core.core.ForzaEmbed attribute) contains_horaire_pattern() (in module src.utils.utils) coordinates (src.utils.models.TSNECoordinate attribute), [1] created_at (src.utils.models.EmbeddingCache attribute), [1] (src.utils.models.EvaluationMetric attribute), [1] (src.utils.models.GeneratedFile attribute), [1] (src.utils.models.GlobalChart attribute), [1] (src.utils.models.Model attribute), [1] (src.utils.models.ProcessingResult attribute), [1] (src.utils.models.TSNECoordinate attribute), [1]

D

data_aggregator (src.reporting.reporting.ReportGenerator attribute) DataAggregator (class in src.reporting.aggregator) database (src.core.config.AppConfig attribute), [1] DatabaseSettings (class in src.core.config) db (src.core.core.ForzaEmbed attribute) (src.core.processing.Processor attribute) (src.reporting.aggregator.DataAggregator attribute) (src.reporting.markdown_filter.MarkdownFilter attribute) (src.reporting.reporting.ReportGenerator attribute) (src.services.embedding_service.EmbeddingService attribute) (src.services.visualization_service.VisualizationService attribute)

db_path (src.core.core.ForzaEmbed attribute) (src.utils.database.EmbeddingDatabase attribute) decompose_silhouette_score() (in module src.metrics.silhouette_decomposition) dimension (src.utils.models.EmbeddingCache attribute), [1] dimensions (src.core.config.ModelConfig attribute), [1]

E

embedding_batch_size_api (src.core.config.MultiprocessingSettings attribute), [1] embedding_batch_size_local (src.core.config.MultiprocessingSettings attribute), [1] embedding_computation_time (src.utils.models.EvaluationMetric attribute), [1] embedding_service (src.core.processing.Processor attribute) EmbeddingCache (class in src.utils.models) EmbeddingDatabase (class in src.utils.database)

EmbeddingService (class in src.services.embedding_service) engine (src.utils.database.EmbeddingDatabase attribute) enhanced_silhouette_analysis() (in module src.metrics.silhouette_decomposition) EvaluationMetric (class in src.utils.models) expected_dimension (src.clients.api_client.ProductionEmbeddingClient attribute) extract_context_around_phrase() (in module src.utils.utils)

F

FastEmbedClient (class in src.clients.fastembed_client) file_batch_size (src.core.config.MultiprocessingSettings attribute), [1] file_id (src.utils.models.ProcessingResult attribute), [1] (src.utils.models.TSNECoordinate attribute), [1]

file_path (src.utils.models.GeneratedFile attribute), [1] (src.utils.models.GlobalChart attribute), [1] file_type (src.utils.models.GeneratedFile attribute), [1] ForzaEmbed (class in src.core.core)

G

generate_all() (src.reporting.reporting.ReportGenerator method) generate_filtered_markdowns (src.core.config.AppConfig attribute), [1] generate_filtered_markdowns() (src.reporting.markdown_filter.MarkdownFilter method) generate_main_page() (in module src.reporting.web_generator) generate_reports() (src.core.core.ForzaEmbed method) generated_files (src.utils.models.Model attribute), [1] GeneratedFile (class in src.utils.models) get_aggregated_data() (src.reporting.aggregator.DataAggregator method) get_all_models() (src.utils.database.EmbeddingDatabase method) get_all_processing_results() (src.utils.database.EmbeddingDatabase method) get_all_processing_results_for_run() (src.utils.database.EmbeddingDatabase method) get_all_run_names() (src.utils.database.EmbeddingDatabase method) get_db_modification_time() (src.utils.database.EmbeddingDatabase method) get_embedding_function() (src.services.embedding_service.EmbeddingService method) get_embeddings() (src.clients.api_client.ProductionEmbeddingClient method) (src.clients.fastembed_client.FastEmbedClient static method) (src.clients.sentencetransformers_client.SentenceTransformersClient class method) (src.clients.transformers_client.TransformersClient class method) get_embeddings_by_hashes() (src.utils.database.EmbeddingDatabase method)

get_global_charts() (src.utils.database.EmbeddingDatabase method) get_huggingface_embeddings() (in module src.clients.huggingface_client) get_instance() (src.clients.fastembed_client.FastEmbedClient class method) (src.clients.sentencetransformers_client.SentenceTransformersClient class method) (src.clients.transformers_client.TransformersClient class method) get_metrics_info() (in module src.reporting.reporting) get_model_files() (src.utils.database.EmbeddingDatabase method) get_model_info() (src.utils.database.EmbeddingDatabase method) get_or_create_embeddings() (src.services.embedding_service.EmbeddingService method) get_or_create_tsne_data() (src.services.visualization_service.VisualizationService method) get_processed_files() (src.utils.database.EmbeddingDatabase method) get_processed_files_with_similarities() (src.utils.database.EmbeddingDatabase method) get_run_details() (src.utils.database.EmbeddingDatabase method) get_spacy_model() (in module src.utils.utils) get_text_hash() (src.services.embedding_service.EmbeddingService static method) get_tsne_coordinates() (src.utils.database.EmbeddingDatabase method) GlobalChart (class in src.utils.models) grid_search_params (src.core.config.AppConfig attribute), [1] GridSearchParams (class in src.core.config)

I

id (src.utils.models.EvaluationMetric attribute), [1] (src.utils.models.GeneratedFile attribute), [1] (src.utils.models.GlobalChart attribute), [1] (src.utils.models.Model attribute), [1] (src.utils.models.ProcessingResult attribute), [1] (src.utils.models.TSNECoordinate attribute), [1]

intelligent_quantization (src.core.config.DatabaseSettings attribute), [1] inter_cluster_distance_normalized (src.utils.models.EvaluationMetric attribute), [1] intra_cluster_distance_normalized (src.utils.models.EvaluationMetric attribute), [1]

L

load_config() (in module src.core.config)

load_markdown_files() (in module src.utils.data_loader)

M

markdown_filter (src.reporting.reporting.ReportGenerator attribute) MarkdownFilter (class in src.reporting.markdown_filter) max_workers_api (src.core.config.MultiprocessingSettings attribute), [1] max_workers_local (src.core.config.MultiprocessingSettings attribute), [1] maxtasksperchild (src.core.config.MultiprocessingSettings attribute), [1] mean_pooling() (in module src.clients.huggingface_client) (in module src.clients.transformers_client) metadata (src.utils.models.Base attribute) metrics (src.utils.models.Model attribute), [1] Model (class in src.utils.models) model (src.clients.api_client.ProductionEmbeddingClient attribute) (src.utils.models.EvaluationMetric attribute), [1] (src.utils.models.GeneratedFile attribute), [1] model_config (src.core.config.AppConfig attribute) (src.core.config.DatabaseSettings attribute) (src.core.config.GridSearchParams attribute) (src.core.config.ModelConfig attribute) (src.core.config.MultiprocessingSettings attribute) model_exists() (src.utils.database.EmbeddingDatabase method) model_name (src.utils.models.EmbeddingCache attribute), [1] (src.utils.models.EvaluationMetric attribute), [1] (src.utils.models.GeneratedFile attribute), [1] (src.utils.models.ProcessingResult attribute), [1] ModelConfig (class in src.core.config)

models_to_test (src.core.config.AppConfig attribute), [1] module src.clients.api_client src.clients.fastembed_client src.clients.huggingface_client src.clients.sentencetransformers_client src.clients.transformers_client src.core.config src.metrics.evaluation_metrics src.metrics.silhouette_decomposition src.reporting.aggregator src.reporting.markdown_filter src.reporting.reporting src.reporting.web_generator src.services.embedding_service src.services.similarity_service src.services.visualization_service src.utils.data_loader src.utils.database src.utils.models src.utils.utils multiprocessing (src.core.config.AppConfig attribute), [1] multiprocessing_config (src.services.embedding_service.EmbeddingService attribute) MultiprocessingSettings (class in src.core.config)

N

name (src.core.config.ModelConfig attribute), [1] (src.utils.models.Model attribute), [1]

O

output_dir (src.core.config.AppConfig attribute), [1] (src.core.core.ForzaEmbed attribute) (src.reporting.aggregator.DataAggregator attribute) (src.reporting.markdown_filter.MarkdownFilter attribute) (src.reporting.reporting.ReportGenerator attribute)

P

ProcessingResult (class in src.utils.models) Processor (class in src.core.processing)

processor (src.core.core.ForzaEmbed attribute) ProductionEmbeddingClient (class in src.clients.api_client)

Q

quantization_enabled (src.utils.database.EmbeddingDatabase attribute)

R

registry (src.utils.models.Base attribute) report_generator (src.core.core.ForzaEmbed attribute) ReportGenerator (class in src.reporting.reporting)

results_blob (src.utils.models.ProcessingResult attribute), [1] run_grid_search() (src.core.core.ForzaEmbed method) run_test() (src.core.processing.Processor method)

S

safe_numpy_converter() (in module src.reporting.web_generator) save_embeddings_batch() (src.utils.database.EmbeddingDatabase method) save_processing_result() (src.utils.database.EmbeddingDatabase method) save_processing_results_batch() (src.utils.database.EmbeddingDatabase method) save_tsne_coordinates() (src.utils.database.EmbeddingDatabase method) SentenceTransformersClient (class in src.clients.sentencetransformers_client) session (src.clients.api_client.ProductionEmbeddingClient attribute) Session (src.utils.database.EmbeddingDatabase attribute) silhouette_score (src.utils.models.EvaluationMetric attribute), [1] similarity_metric (src.utils.models.Model attribute), [1] similarity_metrics (src.core.config.GridSearchParams attribute), [1] similarity_service (src.core.processing.Processor attribute) similarity_threshold (src.core.config.AppConfig attribute), [1] (src.reporting.markdown_filter.MarkdownFilter attribute) (src.reporting.reporting.ReportGenerator attribute) SimilarityService (class in src.services.similarity_service) src.clients.api_client module src.clients.fastembed_client module src.clients.huggingface_client module src.clients.sentencetransformers_client module src.clients.transformers_client module src.core.config module

src.metrics.evaluation_metrics module src.metrics.silhouette_decomposition module src.reporting.aggregator module src.reporting.markdown_filter module src.reporting.reporting module src.reporting.web_generator module src.services.embedding_service module src.services.similarity_service module src.services.visualization_service module src.utils.data_loader module src.utils.database module src.utils.models module src.utils.utils module

T

text_hash (src.utils.models.EmbeddingCache attribute), [1] theme_name (src.utils.models.Model attribute), [1] themes (src.core.config.GridSearchParams attribute), [1] timeout (src.clients.api_client.ProductionEmbeddingClient attribute) (src.core.config.ModelConfig attribute), [1]

touch_cache() (src.reporting.aggregator.DataAggregator method) TransformersClient (class in src.clients.transformers_client) tsne_key (src.utils.models.TSNECoordinate attribute), [1] TSNECoordinate (class in src.utils.models) type (src.core.config.ModelConfig attribute), [1] (src.utils.models.Model attribute), [1]

U

update_metrics_for_file() (src.utils.database.EmbeddingDatabase method)

V

vacuum_database() (src.utils.database.EmbeddingDatabase method) validate_similarities() (src.services.similarity_service.SimilarityService static method)

vector (src.utils.models.EmbeddingCache attribute), [1] visualization_service (src.core.processing.Processor attribute) VisualizationService (class in src.services.visualization_service)