Update app.py

app.py

@@ -28,9 +28,10 @@ def set_custom_prompt():
 
 def load_llm():
     llm = CTransformers(
-        model = 'TheBloke/Llama-2-7B-Chat-GGML',
+        #model = 'TheBloke/Llama-2-7B-Chat-GGML',
         #model = AutoModel.from_pretrained("TheBloke/Llama-2-7B-Chat-GGML"),
-        model_type = 'llama',
+        model = 'MaziyarPanahi/BioMistral-7B-GGUF'
+        model_type = 'mistral',
         max_new_token = 512,
         temperature = 0.5
     )
@@ -48,8 +49,10 @@ def retrieval_qa_chain(llm,prompt,db):
     return qa_chain
 
 def qa_bot():
-    embeddings = HuggingFaceBgeEmbeddings(model_name = 'sentence-transformers/all-MiniLM-L6-v2',
-                                          model_kwargs = {'device':'cpu'})
+    #embeddings = HuggingFaceBgeEmbeddings(model_name = 'sentence-transformers/all-MiniLM-L6-v2',
+    #                                      model_kwargs = {'device':'cpu'})
+    embeddings = HuggingFaceBgeEmbeddings(model_name = 'NeuML/pubmedbert-base-embeddings',
+                                         model_kwargs =  {'device':'cpu'} )
     
     
     db = FAISS.load_local(DB_FAISS_PATH, embeddings,allow_dangerous_deserialization=True)