Improvements (#308)

* model-factory

* removed main.py from metadata extractor

* removed reduntant code - 1

* Model factory updates

* small fix

* initial implementation of attn based predicate extraction

* fixes to attn mechanism

* algo improve and removed prints

* deleted dead code

* fixed assertions in email tests

* removed prints

querent/config/core/llm_config.py

@@ -2,7 +2,6 @@
 from pydantic import BaseModel, Field
 from typing import List, Dict, Any, Optional
 import os
-
 from querent.config.engine.engine_config import EngineConfig
 
 class LLM_Config(EngineConfig):
@@ -11,11 +10,11 @@ class LLM_Config(EngineConfig):
     description: str = "An engine for NER and knowledge graph operations."
     version: str = "0.0.1"
     logger: str = "LLM.engine_config"
-    ner_model_name: str = "dbmdz/bert-large-cased-finetuned-conll03-english"
+    ner_model_name: str = "English"
     spacy_model_path: str = 'en_core_web_lg'
     nltk_path: str = '/model/nltk_data'
-    rel_model_type: str = 'llama'
-    rel_model_path: str = './tests/llama-2-7b-chat.Q5_K_M.gguf'
+    rel_model_type: str = 'bert'
+    rel_model_path: str = 'bert-base-uncased'
     grammar_file_path: str = './querent/kg/rel_helperfunctions/json.gbnf'
     emb_model_name: str = 'sentence-transformers/all-MiniLM-L6-v2'
     user_context: str = Field(default="In a semantic triple (Subject, Predicate & Object) framework, determine which of the above entity is the subject and which is the object based on the context along with the predicate between these entities. Please also identify the subject type, object type & predicate type.")

querent/config/core/opensource_llm_config.py

@@ -8,7 +8,7 @@ class Opensource_LLM_Config(BaseModel):
     version: str = "0.0.1"
     logger: str = "RelationshipExtractor.engine_config"
     model_type: str = 'llama'
-    model_path: str = './tests/llama-2-7b-chat.Q5_K_M.gguf' 
+    model_path: str = '' 
     grammar_file_path: str = './querent/kg/rel_helperfunctions/json.gbnf'
     qa_template: str = Field(default=None)
     emb_model_name: str = 'sentence-transformers/all-MiniLM-L6-v2'