From eed594171675eb2182f57fce7b853a23beac3def Mon Sep 17 00:00:00 2001
From: Ivan Pavlovich <ivan.pavlovic@hes-so.ch>
Date: Wed, 12 Mar 2025 19:25:14 +0100
Subject: [PATCH] Added wrapper Ollama to test ollama models
---
.../__pycache__/pubmedApi.cpython-313.pyc | Bin 6208 -> 6743 bytes
dataSources/PubMed/pubmedApi.py | 6 +--
.../Ollama/__pycache__/ollama.cpython-313.pyc | Bin 0 -> 2623 bytes
models/LLM/Ollama/ollama_wrapper.py | 47 ++++++++++++++++++
testModel/test.py | 2 +-
variables/models.py | 10 +++-
6 files changed, 59 insertions(+), 6 deletions(-)
create mode 100644 models/LLM/Ollama/__pycache__/ollama.cpython-313.pyc
create mode 100644 models/LLM/Ollama/ollama_wrapper.py
diff --git a/dataSources/PubMed/__pycache__/pubmedApi.cpython-313.pyc b/dataSources/PubMed/__pycache__/pubmedApi.cpython-313.pyc
index 4e650d570dcc84a349d496c81cb5c4b7a99fc2a2..9d5fa7641db53dafd2f09601a95d99a1e374299b 100644
GIT binary patch
delta 882
zcmX?LaNUIOGcPX}0|Ntt`>~7ZQ>8ZYIWsYB;@TX{l*+`+?9n)RH;X$nvq$)3R@Rl1
zUD$;tA7J%n@^_z{&#Edd2hs+@rc5A`fk6X8F{Fr2Ue78c5G=>az`zhH94xQSz`)=y
zIC&$h)MQmQZ$|COg=}F={&th|StTb2u(9DWNoaB*n;60*C9p|+lO5SaCf{aLXPh=U
zmsNVQ9D55R$Vrlu<=A=f7$!QImtBSz?kr_>28PKC*k>^+PPXQ-WmKG8$#I!cd9p9(
zbw<U>s$ANJ%)TBB455Od%vKQ$42diZ3<?bH%)aFyv0zJGUIvCdL3d`~C<X>@h)m1m
zMlMT6mC3ugYMItCO#Z;-q1ed4pva(u2pL8OhBPJx26+YrkQNp{_sxsBZJ8N`CqLw?
zW??QaDcT&(AIZoaz`(#D$-ux+ypV14egSKy`cJG3nu&~G*cg;_R=8a-cDbnIdLZ+n
zPQZo0sEaz$7h;kx>ZDvr%e=0bbx|?vhK>;qB^Oe2F6!jYa9JQe%l83JRUrA9z7O;b
zXRyqOyC|V^M|!fJuun3`4Y63=5Pwl8;Yw2Kb;Y!cifK2DEiYJkUo`eP5qZ%#{6a+9
zMdS1f8Tl8D3ud@1kh>&f@BoVfkkmyPgUR!R>$JYGF{l}AV7p-ManZo@gyuzqkPD&l
z7Y!0FB<5c<D7aEodR?{bqH5U<W6Q~kBH{uUN~$j!*DPRJ5OqlbWcFr7k*kb6p-c?Y
z${*Po1cblEO=c1^V$7awD(1;pF}Yq$)FoJl;gA`3h#<pZDVY#6=F42-p&ZPYb+|&f
znJ=4hhp;hUVPg&9X1*fG6=J}AMVdQAoB4`1D~N5z70Swfm4ho(Z1N2;MMl%fzr@;P
sK(V!w;WH@p7x^<VFx=v>$<0qG%}KQ@il013d^V>u6Qg8N90LOb0F&nUDgXcg
delta 506
zcmca^a=?J^GcPX}0|NuYw{;iO|B7$qb7o>H<J=s~l*+`+<neg&ZWecDCXbzySy@*y
z+D%^18Z&t#tJLJlY~G9(lMC6!CVypfnEa4UWb$fub;g9rxvbKY-?6t$zQ-|xQGRkF
zxA5dHPAw?w1m}UtWt<|D=WrbXi)b4%`L1GM2o(%vwu)e2NMvDPP+)Lp^1TTX3%1nd
zWnjn?bZ7G2!@$4|k$E<GFSjM5(&X>lwM+sGlXZC9n3;VaPu|ZX%gpSza`Sy2TV_U~
z$+7~~o97BdFmn4dFfd3mFfbIKX5A!Y&7|>>l|eI+@dF2gq4@=KkBbJLCp0e_gj@)X
zyJ!%9AtC*uLB;}>1>p;MC$AHUPys291u3?$yI|*k(LCTnVAMtP=nFAf7tOO5uq=qX
zs9-WVQ?!ot0|$eN)nq|2@y-5X`xtpVnHZ#%Ke96j2!9KjEGc2c7(dxZ!ZRv|iGfe?
z3a`QkHU<HaU&S5_3=9WVxC8kZ4w-QW8Z#W0k_nPvzMvx>q{V!Zk1J4@`Jx1Opa%0r
z4OS4_m@7z#`Jyd%5HIs3Ue+KX=1US>LF(+6w77ySCcl?ZWHgy9DA^_h^6*NA&!E^W
j@?&6NxW!?Uo1apelWJEKH+i$<Y|dInM#-XB1_lNI@ST#$
diff --git a/dataSources/PubMed/pubmedApi.py b/dataSources/PubMed/pubmedApi.py
index df29e7449..f694ee56e 100644
--- a/dataSources/PubMed/pubmedApi.py
+++ b/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"]
diff --git a/models/LLM/Ollama/__pycache__/ollama.cpython-313.pyc b/models/LLM/Ollama/__pycache__/ollama.cpython-313.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..00224bcf9f3e9bfd7270dd9731d100dede3da8f5
GIT binary patch
literal 2623
zcmey&%ge>Uz`($G?qa$g2Lr=n5C?`?p^VR73=9lY8G;#t8NC_27>gJcKx`&&1}~-}
zCNP`Xo4JTtpCOnfkg<p*m{p3Qh&7n4h%JUyi6NLhhAoE0lo?`{0z*2pCdW$<N0adu
zOL9hHi6-MM9_Nh2lAzS$g8aPVR6k9QDoMZmJYDDf+}zT<%;dzRoKyvu%;MC<;?&|>
z94?uONvS2N#kbg;6Z4W&i>joZGm7%_GLsdGQi}^RixNxniz*dTAnL2cofC^vGV{w4
zi<3)p5{qEs#Z|n%sd*)dISL-Bi8&=1Rs1kx6-p`#QWXr*1&orRJ^(qLfsKKI0mT2T
z!w3!;#!yB+hG3>pCO(E>W@FYo=4eK+ItB)YP=;WZQ08D(Jtlp|U^YvpJeE+FASReB
zf(~Lquwkqqb{Gpmn?jjEoKOZ570hl5wHKexJl0UwAZ{dWP-ZX(Ot%J9B$1VYA(S<k
zGnk8oA&)hh2P(`E#0O&`XeEYFR+#=gwrD|^Oeh;nRDmI#L6h6BYK5mlUTSKJLS=rb
zLP@?tdS+RwLT;);Nk*zdPGVAOPO(BsMq-IVa(-z}ib7H<SV100B}hd{YDI~HMs{jy
zfkI}ULT+YW3Pg3OLULlBLP2SXLT+hJNoGL~+_1#F6oul{oYdqJh5WpnN(_54!4`mA
zqiLl81t43j6siQET&TOO6sk;NBJLnpgB%1(bf9Dla!yupex5>Feo<~>iGmWuFG^Ml
z(XqE!N{dsAG?{L(6y@in-eOPA&nrpIE74@S#hRO+lA3diBR93UI59o7xQaa?ApvAe
z6>~yDLJ=sPy!`wB|9?%+B2ap}#ST?i1j@CySc^-FG7E08<v?hT)V!49^30NqTPz?W
zZn5U%C#DqNVl61j%q!7kF9OB+Eso;U!qU{d<kVYi5EtHJD=5m(EhxFg0rSc&4v_Zv
z;*z3Uyb!VE)Oe6kF(^GkL*Q0~enx(7s(xl!VxGQBesXDUYF<gPeqM5lZc1WFqHbb(
zdQob6Vo7Fxo^E1Zif(dFVsUY1T4pj>NFVI)VtpSUUw!|aoW$Hj{d_Q`S5SG21FE*N
zNQQxdL4bjQp?DDk149GD2PQ@V{u}(_9a$e37$pU72#QbO0I|$Iurl+RH@JP_Vvti>
z!TLZz?1r%9M^<K5whzp#mTVsxSmoFoJU;L-2uNJ#m%qp_f1O|bBER}|e%*`wx|jL&
zuk)K-<Tu+;d70nwI=}lxe)r4#o(&!k*!i!sOI&1^m?3(dUH&4w{0(908ICiOCfIdw
zJQ0zY?lsA4M#W_jjRxN*ESw#>S6L)JgA#pW3=0E8NJeT=VqSi6NoKM_N>OQgu|iR5
zK~ZXPYF>##VxB^3Zfa3_W?s5NL1IY;C~2pp=46(o7AfTCfzu}_Mly?274p**3W`#b
zGmA6x^AvJZQ!<k?^HTK`Jo3v^%TkMU6q52wN^(;3Qj@bm7UU*o=7Ex7az<iNVsc4p
zQDzm$juIrdlq43Vr<N4!C}gIj=9OfoRiZ1%Nli>qNY2kK$S=)HDb`T{<(`tn%$)op
zbd_Ll=_!QdE994@7A5CHvT$)KvZHhq%2Po;0Q(!1Tad%WJvA>sH&qAX;l!d6kZ(b1
zGD>q3^Ays-vI^xH`NgRUsTH8W1BU`An<u3zl$K=XWLBl7fC4W$KQ}2e4_ty2B^IQX
zf&v}n?v%{LbZ8tT78K+_lU}i<E9_Gl>c*pkgE^HL)l!GcR2?DX};;MIoaysVFl=
z0qh7}M^A-<%!1S$i0Pn0sVKj=ShpxOEwu=ghl&*fN|St3Qy`vjPt8kJa78%PKQ}Kk
zskB%JRC&3l`niVaD1>CBDma6yEd_}86&y=)5{n_hoRO;F=jox~o1c>ksjNJ66Tztj
z<QeDuypp2C;t~bNbWkF4Ni0bOIT#$mAQz{nDrDxRWR_*7lqTkYLNB!#lor7L0F{l&
zsYS&Kpuz!MO{ON7KnpN<GKELFo`N%qFF|1iiWkhdgP0fO=UALtr~u0K3TZ|8x#0Am
zU}&yxU|;|VM}?Bi;^I<}gCMCcGZj?EBXS5dRf0nSH35Q3Q-!j`qRjl#VyIck;NXKM
z&BUCX{PJQ2q!bEH;GlGYNcF{_L{gNRlUkOTR{{+Sh2qkrg8YKg9B^?|tfvqTPGz84
z0*7Bq@)gn&lQVNNOA<@KX-y#|wJbF!zW`M5fzobXYPkZ$Cs?dcN-Zf#1vNjwNitPO
zp)@ZgwWzoxF%Oh@ic%9xAbBk}KQFT+zephw?CaE$N|4DYk*HV20WK+x^^7#xZ?Qp&
zO>pf{1ZqMQ2{AA*++y)_b_oU-pSM^*mDx&$B3T9oh9YT@B!^9IeoARhs$G#1sObkP
zU-cLm7(OsFGBVy}5WmYHf182(6ALE?Qv=H<F%d?|4>}ASX@U(b4;eT*q$Y&SFuBU0
H05%T*zTqId
literal 0
HcmV?d00001
diff --git a/models/LLM/Ollama/ollama_wrapper.py b/models/LLM/Ollama/ollama_wrapper.py
new file mode 100644
index 000000000..ad23ab557
--- /dev/null
+++ b/models/LLM/Ollama/ollama_wrapper.py
@@ -0,0 +1,47 @@
+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
diff --git a/testModel/test.py b/testModel/test.py
index 4fd378194..1a09d4f62 100644
--- a/testModel/test.py
+++ b/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()
diff --git a/variables/models.py b/variables/models.py
index ded4df5fd..9a3e18880 100644
--- a/variables/models.py
+++ b/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
--
GitLab