Hugging Face's logo

nsr51324
/
CortexRAG

sentence-transformers
rag
medical-ai
faiss
fastapi
cross-encoder
groq
Model card Files
xet
 Community
nsr51324 commited on
Commit
201270e
·
verified ·
1 Parent(s): a5ba8a1

Upload 15 files

Browse files
Files changed (16) hide show
  1. .gitattributes +4 -0
  2. AHD_english.xlsx +3 -0
  3. gold_set_for_manual_review.xlsx +0 -0
  4. notebooks/AHD_english_cleaned.xlsx +3 -0
  5. notebooks/Medical_RAG_Sytem.ipynb +0 -0
  6. notebooks/rag_data_cleaning.ipynb +0 -0
  7. question_embeddings.npy +3 -0
  8. questions.index +3 -0
  9. rag_model/data/knowledge_base.pkl +3 -0
  10. rag_model/faiss/question_embeddings.npy +3 -0
  11. rag_model/faiss/questions.index +3 -0
  12. rag_model/models/embedding_model.txt +1 -0
  13. rag_model/models/medical_synonyms.json +13 -0
  14. rag_model/models/reranker_model.txt +1 -0
  15. rag_model/rag_config.json +13 -0
  16. rag_model/requirements.txt +7 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ AHD_english.xlsx filter=lfs diff=lfs merge=lfs -text
37
+ notebooks/AHD_english_cleaned.xlsx filter=lfs diff=lfs merge=lfs -text
38
+ questions.index filter=lfs diff=lfs merge=lfs -text
39
+ rag_model/faiss/questions.index filter=lfs diff=lfs merge=lfs -text
AHD_english.xlsx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb842e81268b70c7455ced45ae8a5ec94f06df4ab0b9afec5a20a148d310ac6
3
+ size 123764685
gold_set_for_manual_review.xlsx ADDED
Binary file (6.64 kB). View file
 
notebooks/AHD_english_cleaned.xlsx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff718c8f717e54398d8fd52af30a27d99a6f0cfdec387859f6f834659b6c668
3
+ size 2138581
notebooks/Medical_RAG_Sytem.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
notebooks/rag_data_cleaning.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
question_embeddings.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7ac11de60fe90001191122829666f1e692c44c3f9b7f7022e41e1f278bbf734
3
+ size 25165952
questions.index ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7838b1244b63aa062865934bbf8350c24dd3d91bd93146a15189e434bf05b9dd
3
+ size 25165869
rag_model/data/knowledge_base.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d3ef12529d57233a1de3f9f972fc742b8afe352b51e57ca35854842d33ddb7
3
+ size 5919507
rag_model/faiss/question_embeddings.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7ac11de60fe90001191122829666f1e692c44c3f9b7f7022e41e1f278bbf734
3
+ size 25165952
rag_model/faiss/questions.index ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7838b1244b63aa062865934bbf8350c24dd3d91bd93146a15189e434bf05b9dd
3
+ size 25165869
rag_model/models/embedding_model.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ all-MiniLM-L6-v2
rag_model/models/medical_synonyms.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "underactive thyroid": "hypothyroidism",
3
+ "under active thyroid": "hypothyroidism",
4
+ "low thyroid": "hypothyroidism",
5
+ "overactive thyroid": "hyperthyroidism",
6
+ "over active thyroid": "hyperthyroidism",
7
+ "high thyroid": "hyperthyroidism",
8
+ "high blood sugar": "hyperglycemia",
9
+ "low blood sugar": "hypoglycemia",
10
+ "sugar disease": "diabetes",
11
+ "thyroid surgery": "thyroidectomy",
12
+ "sugar level": "blood glucose level"
13
+ }
rag_model/models/reranker_model.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ cross-encoder/ms-marco-MiniLM-L-6-v2
rag_model/rag_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "embedding_model": "all-MiniLM-L6-v2",
3
+ "reranker_model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
4
+ "retrieve_top_n": 20,
5
+ "rerank_top_k": 6,
6
+ "min_rerank_score": -8,
7
+ "min_similarity_floor": 0.4,
8
+ "min_support_count": 2,
9
+ "support_score": -5.0,
10
+ "semantic_similarity_threshold": 0.9,
11
+ "embedding_dimension": 384,
12
+ "dataset_size": 16384
13
+ }
rag_model/requirements.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ sentence-transformers
2
+ faiss-cpu
3
+ pandas
4
+ numpy
5
+ openpyxl
6
+ groq
7
+ tqdm