Update app.py

app.py

@@ -43,13 +43,14 @@ def get_text_chunks(text):
 
 def get_vectorstore(text_chunks):
     # Load the desired embeddings model.
-    # embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',
-    #                                    model_kwargs={'device': 'cpu'})
+    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L12-v2',
+                                       model_kwargs={'device': 'cpu'})
+    print('embeddings = ', embeddings)
     # embeddings = OpenAIEmbeddings()sentence-transformers/all-MiniLM-L6-v2
-    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl",
-                                              model_kwargs={'device':'cpu'})
-    # vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
-    vectorstore = Chroma.from_texts(texts=text_chunks, embedding=embeddings)
+    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl",
+    #                                           model_kwargs={'device':'cpu'})
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    # vectorstore = Chroma.from_texts(texts=text_chunks, embedding=embeddings)
 
     return vectorstore
 
@@ -58,6 +59,8 @@ def get_conversation_chain(vectorstore):
     # llm = ChatOpenAI()
     # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
     config = {'max_new_tokens': 2048}
+
+    
     llm = CTransformers(model="llama-2-7b-chat.ggmlv3.q2_K.bin", model_type="llama", config=config)
     memory = ConversationBufferMemory(
         memory_key='chat_history', return_messages=True)