Fix/readme

README.md

@@ -129,27 +129,25 @@ builder.l3.configure(model="knowledgator/gliner-linker-large-v1.0")
 executor = DAGExecutor(builder.get_config())
 
 # 3. Load entities
-executor.load_entities("data/entities.jsonl", target_layers=["dict"])
+executor.load_entities("data/pubmesh_ontology.jsonl", target_layers=["dict"])
 
 # 4. Process text
 result = executor.execute({
-    "texts": ["Farnese Palace is one of the most important palaces in the city of Rome."]
+    "texts": ["BRCA1 mutations are associated with breast cancer risk."]
 })
 
 # 5. Get results
 l0_result = result.get("l0_result")
-for entity in l0_result.entities:
-    if entity.linked_entity:
-        print(f"{entity.mention_text} → {entity.linked_entity.label}")
-        print(f"  Confidence: {entity.linked_entity.score:.3f}")
+for text_entities in l0_result.entities:
+    for entity in text_entities:
+        if entity.linked_entity:
+            print(f"{entity.mention_text} → {entity.linked_entity.label}")
+            print(f"  Confidence: {entity.linked_entity.confidence:.3f}")
 ```
 
 **Output:**
 ```
-BRCA1 → BRCA1: Breast cancer type 1 susceptibility protein
-  Confidence: 0.923
-breast cancer → Breast Cancer: Malignant neoplasm of the breast
-  Confidence: 0.887
+# Labels and confidence values depend on the model and loaded entity database.
 ```
 
 ---
@@ -284,7 +282,7 @@ For full control over every layer, define the pipeline in YAML and load it:
 ```python
 from glinker import ProcessorFactory
 
-executor = ProcessorFactory.create_pipeline("configs/pipelines/dict/simple.yaml")
+executor = ProcessorFactory.create_pipeline("configs/pipelines/dict/default.yaml")
 executor.load_entities("data/entities.jsonl")
 result = executor.execute({"texts": ["TP53 mutations cause cancer"]})
 ```

configs/pipelines/README.md

@@ -59,13 +59,11 @@ python scripts/database/jsonl2postgresql.py
 - Use case: High-performance BiEncoder inference
 
 ```python
-from src.core.dag import DAGExecutor, DAGPipeline
-import yaml
+from glinker import ProcessorFactory
 
-with open("configs/pipelines/postgres/with_embeddings.yaml") as f:
-    pipeline = DAGPipeline(**yaml.safe_load(f))
-
-executor = DAGExecutor(pipeline)
+executor = ProcessorFactory.create_pipeline(
+    "configs/pipelines/postgres/with_embeddings.yaml"
+)
 
 # Step 1: Load entities
 executor.load_entities("entities.jsonl", target_layers=["postgres"])
@@ -233,13 +231,11 @@ python demo.py -c configs/pipelines/postgres_redis/default.yaml
 ```bash
 # Setup embeddings
 python -c "
-from src.core.dag import DAGExecutor, DAGPipeline
-import yaml
+from glinker import ProcessorFactory
 
-with open('configs/pipelines/postgres/with_embeddings.yaml') as f:
-    pipeline = DAGPipeline(**yaml.safe_load(f))
-
-executor = DAGExecutor(pipeline)
+executor = ProcessorFactory.create_pipeline(
+    'configs/pipelines/postgres/with_embeddings.yaml'
+)
 executor.load_entities('entities.jsonl', target_layers=['postgres'])
 executor.precompute_embeddings(target_layers=['postgres'])
 "

docs/DATABASE_SETUP.md

@@ -351,7 +351,7 @@ from glinker.core.factory import ProcessorFactory
 import yaml
 
 # Load pipeline config with multiple database layers
-with open("configs/pipelines/postgres_redis_basic.yaml") as f:
+with open("configs/pipelines/postgres_redis/default.yaml") as f:
     config = yaml.safe_load(f)
 
 executor = ProcessorFactory.create_from_dict(config, verbose=True)
@@ -379,7 +379,7 @@ from glinker.core.factory import ProcessorFactory
 import yaml
 
 # Use embedding-enabled config
-with open("configs/pipelines/postgres_redis_embeddings.yaml") as f:
+with open("configs/pipelines/postgres_redis/with_embeddings.yaml") as f:
     config = yaml.safe_load(f)
 
 executor = ProcessorFactory.create_from_dict(config, verbose=True)