Added wrapper Ollama to test ollama models

dataSources/PubMed/pubmedApi.py

@@ -85,7 +85,7 @@ def getPubmedData(term, date_min, date_max, nb_items = -1, debug = False, store
                             for part in entrie["MedlineCitation"]["Article"]["Journal"]["Title"]:
                                 if "#text" in part:
                                     data["Title"] += part["#text"]
-                        elif isinstance(entrie["MedlineCitation"]["Article"]["Journal"]["Title"], object):
+                        elif not isinstance(entrie["MedlineCitation"]["Article"]["Journal"]["Title"], str):
                             data["Title"] = entrie["MedlineCitation"]["Article"]["Journal"]["Title"]["#text"]
                         else:
                             data["Title"] = entrie["MedlineCitation"]["Article"]["Journal"]["Title"]
@@ -95,7 +95,7 @@ def getPubmedData(term, date_min, date_max, nb_items = -1, debug = False, store
                             for part in entrie["MedlineCitation"]["Article"]["ArticleTitle"]:
                                 if "#text" in part:
                                     data["ArticleTitle"] += part["#text"]
-                        elif isinstance(entrie["MedlineCitation"]["Article"]["ArticleTitle"], object):
+                        elif not isinstance(entrie["MedlineCitation"]["Article"]["ArticleTitle"], str):
                             data["ArticleTitle"] = entrie["MedlineCitation"]["Article"]["ArticleTitle"]["#text"]
                         else:
                             data["ArticleTitle"] = entrie["MedlineCitation"]["Article"]["ArticleTitle"]
@@ -106,7 +106,7 @@ def getPubmedData(term, date_min, date_max, nb_items = -1, debug = False, store
                                 for part in entrie["MedlineCitation"]["Article"]["Abstract"]["AbstractText"]:
                                     if "#text" in part:
                                         data["Abstract"] += part["#text"]
-                            elif isinstance(entrie["MedlineCitation"]["Article"]["Abstract"]["AbstractText"], object):
+                            elif not isinstance(entrie["MedlineCitation"]["Article"]["Abstract"]["AbstractText"], str):
                                 data["Abstract"] = entrie["MedlineCitation"]["Article"]["Abstract"]["AbstractText"]["#text"]
                             else:
                                 data["Abstract"] = entrie["MedlineCitation"]["Article"]["Abstract"]["AbstractText"]

models/LLM/Ollama/ollama_wrapper.py

+from ollama import chat
+from ollama import ChatResponse
+import json
+
+NCDS = [
+    "Non-Communicable Diseases",
+    "Diabetes",
+    "Cancer",
+    "Chronic respiratory disease",
+    "Cardiovascular diseases",
+    "Mental Health",
+    "Diabetes type 1",
+    "Diabetes type 2"
+]
+
+def classify(model, sequence, labels):
+    prompt = f'I need you to give me the labels that could be given to the text (keep in mind that u can put multiple labels and select only the labels that i give you):\
+        text: {sequence}\
+        labels: {labels}\
+        Give the response in json format "labels": [] with no text at all'
+
+    response: ChatResponse = chat(model=model, messages=[
+    {
+        'role': 'user',
+        'content': prompt,
+    },
+    ])
+
+    json_str = response.message.content.strip().lstrip('```json').strip()
+
+    if json_str.endswith("```"):
+        json_str = json_str[0:-3]
+
+    responce_json = json.loads(json_str)
+
+    print(responce_json)
+
+    res = {}
+
+    for label in labels:
+        res[label] = label in responce_json["labels"]
+            
+    return 
+
+text = "Theranostic drugs represent an emerging path to deliver on the promise of precision medicine. However, bottlenecks remain in characterizing theranostic targets, identifying theranostic lead compounds, and tailoring theranostic drugs. To overcome these bottlenecks, we present the Theranostic Genome, the part of the human genome whose expression can be utilized to combine therapeutic and diagnostic applications. Using a deep learning-based hybrid human-AI pipeline that cross-references PubMed, the Gene Expression Omnibus, DisGeNET, The Cancer Genome Atlas and the NIH Molecular Imaging and Contrast Agent Database, we bridge individual genes in human cancers with respective theranostic compounds. Cross-referencing the Theranostic Genome with RNAseq data from over 17'000 human tissues identifies theranostic targets and lead compounds for various human cancers, and allows tailoring targeted theranostics to relevant cancer subpopulations. We expect the Theranostic Genome to facilitate the development of new targeted theranostics to better diagnose, understand, treat, and monitor a variety of human cancers."
+
+classify('llama3.2', text, NCDS)
\ No newline at end of file

testModel/test.py

@@ -108,7 +108,7 @@ for disease_label in DISEASES_LABELS:
         if MODELS[model]["isHuggingFace"]:
             predictions = MODELS[model]["predict"](pipline, title+abstract, DISEASES_LABELS, data["treshold"])
         else:
-            predictions = MODELS[model]["predict"](title+abstract, DISEASES_LABELS)
+            predictions = MODELS[model]["predict"](model, title+abstract, DISEASES_LABELS)
 
         end = time.time()
 

variables/models.py

@@ -2,10 +2,16 @@ import sys
 import os
 
 # Ajouter le répertoire parent au chemin de recherche
-sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../")))
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '../')))
 
 from models.ZeroShotClassifier.HuggingFace.zero_shot_classification import create_classifier, classify
+import models.LLM.Ollama as ollama
 
 MODELS = {
-    'facebook/bart-large-mnli': {'predict': classify, 'isHuggingFace': True, 'pipline': create_classifier}
+    'facebook/bart-large-mnli': {'predict': classify, 'isHuggingFace': True, 'pipline': create_classifier},
+    'MoritzLaurer/bge-m3-zeroshot-v2.0': {'predict': classify, 'isHuggingFace': True, 'pipline': create_classifier},
+    'MoritzLaurer/DeBERTa-v3-base-mnli-fever-anli': {'predict': classify, 'isHuggingFace': True, 'pipline': create_classifier},
+    'MoritzLaurer/deberta-v3-base-zeroshot-v1.1-all-33': {'predict': classify, 'isHuggingFace': True, 'pipline': create_classifier},
+    'MoritzLaurer/multilingual-MiniLMv2-L6-mnli-xnli': {'predict': classify, 'isHuggingFace': True, 'pipline': create_classifier},
+    'llama3.2': {'predict': ollama.classify, 'isHuggingFace': False, 'pipline': None}
 }
\ No newline at end of file