desactive inference.

README.md

@@ -22,7 +22,7 @@ This approach aims to significantly enrich the metadata of scientific articles,
 ## Install
 
 ```bash
-pip install git+https://github.com/p2m2/encoder-ontology-match-abstract.git@alpha-20241031
+pip install git+https://github.com/p2m2/encoder-ontology-match-abstract.git@20250120
 curl -O https://raw.githubusercontent.com/p2m2/encoder-ontology-match-abstract/refs/heads/main/llm_semantic_annotator.sh
 ```
 

exec.sh

@@ -5,21 +5,21 @@ help() {
 Usage: $0 <config_file> <int_commande>
 
 Commands:
-  1. Pseudo workflow [2,4,5,6,7]
+  1. Pseudo workflow [2,3,4,5,6,7]
   2. Populate OWL tag embeddings
   3. Populate abstract embeddings
   4. Compute similarities between tags and abstract chunks
-  5. Display similarities information
-  6. Build turtle knowledge graph
-  7. Build dataset abstracts annotations CSV file
+  5. Build turtle knowledge graph
+  6. Build dataset abstracts annotations CSV file
+  7. Display similarities information
 
 Details:
   2: Compute TAG embeddings for all ontologies defined in the populate_owl_tag_embeddings section
   3: Compute ABSTRACT embeddings (title + sentences) for all abstracts in the dataset
   4: Compute similarities between TAGS and ABSTRACTS
-  5: Display similarities information on the console
-  6: Generate turtle file with information {score, tag} for each DOI
-  7: Generate CSV file with [doi, tag, pmid, reference_id]
+  5: Generate turtle file with information {score, tag} for each DOI
+  6: Generate CSV file with [doi, tag, pmid, reference_id]
+  7: Display similarities information on the console
 
 EOF
 }
@@ -81,9 +81,9 @@ execute_command() {
         2) run_command python3 -m llm_semantic_annotator "$config_file" populate_owl_tag_embeddings ;;
         3) run_command python3 -m llm_semantic_annotator "$config_file" populate_abstract_embeddings ;;
         4) run_command python3 -m llm_semantic_annotator "$config_file" compute_tag_chunk_similarities ;;
-        5) run_command python3 -m llm_semantic_annotator "$config_file" display_summary ;; 
-        6) run_command python3 -m llm_semantic_annotator "$config_file" build_rdf_graph ;;
-        7) run_command python3 -m llm_semantic_annotator "$config_file" build_dataset_abstracts_annotations ;; 
+        5) run_command python3 -m llm_semantic_annotator "$config_file" build_rdf_graph ;;
+        6) run_command python3 -m llm_semantic_annotator "$config_file" build_dataset_abstracts_annotations ;; 
+        7) run_command python3 -m llm_semantic_annotator "$config_file" display_summary ;; 
         *) echo "Invalid option" ;;
     esac
 }
@@ -97,6 +97,7 @@ case $command in
         run_command python3 -m llm_semantic_annotator "$config_file" populate_abstract_embeddings
         run_command python3 -m llm_semantic_annotator "$config_file" compute_tag_chunk_similarities
         run_command python3 -m llm_semantic_annotator "$config_file" build_rdf_graph
+	    run_command python3 -m llm_semantic_annotator "$config_file" build_dataset_abstracts_annotations
         run_command python3 -m llm_semantic_annotator "$config_file" display_summary
         ;;
     2|3|4|5|6|7)

llm_semantic_annotator.sh

@@ -5,21 +5,22 @@ help() {
 Usage: $0 <config_file> <int_commande>
 
 Commands:
-  1. Pseudo workflow [2,4,5,6,7]
+  1. Pseudo workflow [2,3,4,5,6,7]
   2. Populate OWL tag embeddings
   3. Populate abstract embeddings
   4. Compute similarities between tags and abstract chunks
-  5. Display similarities information
-  6. Build turtle knowledge graph
-  7. Build dataset abstracts annotations CSV file
+  5. Build turtle knowledge graph
+  6. Build dataset abstracts annotations CSV file
+  7. Display similarities information
 
 Details:
   2: Compute TAG embeddings for all ontologies defined in the populate_owl_tag_embeddings section
   3: Compute ABSTRACT embeddings (title + sentences) for all abstracts in the dataset
   4: Compute similarities between TAGS and ABSTRACTS
-  5: Display similarities information on the console
-  6: Generate turtle file with information {score, tag} for each DOI
-  7: Generate CSV file with [doi, tag, pmid, reference_id]
+  5: Generate turtle file with information {score, tag} for each DOI
+  6: Generate CSV file with [doi, tag, pmid, reference_id]
+  7: Display similarities information on the console
+
 
 EOF
 }
@@ -81,9 +82,9 @@ execute_command() {
         2) run_command python3 -m llm_semantic_annotator "$config_file" populate_owl_tag_embeddings ;;
         3) run_command python3 -m llm_semantic_annotator "$config_file" populate_abstract_embeddings ;;
         4) run_command python3 -m llm_semantic_annotator "$config_file" compute_tag_chunk_similarities ;;
-        5) run_command python3 -m llm_semantic_annotator "$config_file" display_summary ;; 
-        6) run_command python3 -m llm_semantic_annotator "$config_file" build_rdf_graph ;;
-        7) run_command python3 -m llm_semantic_annotator "$config_file" build_dataset_abstracts_annotations ;; 
+        5) run_command python3 -m llm_semantic_annotator "$config_file" build_rdf_graph ;;
+        6) run_command python3 -m llm_semantic_annotator "$config_file" build_dataset_abstracts_annotations ;;
+        7) run_command python3 -m llm_semantic_annotator "$config_file" display_summary ;;	
         *) echo "Invalid option" ;;
     esac
 }
@@ -97,7 +98,8 @@ case $command in
         run_command python3 -m llm_semantic_annotator "$config_file" populate_abstract_embeddings
         run_command python3 -m llm_semantic_annotator "$config_file" compute_tag_chunk_similarities
         run_command python3 -m llm_semantic_annotator "$config_file" build_rdf_graph
-        run_command python3 -m llm_semantic_annotator "$config_file" display_summary
+        run_command python3 -m llm_semantic_annotator "$config_file" build_dataset_abstracts_annotations
+	run_command python3 -m llm_semantic_annotator "$config_file" display_summary
         ;;
     2|3|4|5|6|7)
         execute_command $command

llm_semantic_annotator/abstract/abstract_manager.py

@@ -251,7 +251,9 @@ def build_dataset_abstracts_annotations(self):
         graphs = self.tags_manager.get_graphs_ontologies()
         ascendants_dict = defaultdict(list)
         debut = time.time()
-        self.build_ascendants_terms(ascendants_dict,graphs)
+
+        # inference desactivée !
+        #self.build_ascendants_terms(ascendants_dict,graphs)
         duree = time.time() - debut
         print(f"loading terms with ancestors : {duree:.4f} secondes")