Update src/main.py

src/main.py

@@ -8,11 +8,14 @@ from langchain.document_loaders import TextLoader
 from langchain.chains import RetrievalQA,  ConversationalRetrievalChain
 from langchain.memory import ConversationBufferMemory
 from langchain.chat_models import ChatOllama
+from langchain.llms import Ollama
+from langchain.embeddings import OllamaEmbeddings
+from langchain.callbacks.manager import CallbackManager
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 from langchain.document_loaders import TextLoader
 from langchain.document_loaders import GitLoader
 from langchain.memory import ConversationBufferMemory, ConversationBufferWindowMemory
 from langchain.vectorstores import Chroma
-from langchain.embeddings import OllamaEmbeddings
 from langchain.prompts import PromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate, AIMessagePromptTemplate, ChatPromptTemplate
 import datetime
 import shutil
@@ -62,9 +65,13 @@ def ingest_chunks(chunks):
 #Retreival function to get the data from the database and reply to the user
 def retreival(vector_store, k):
     #Creating LLM
-    llm = ChatOllama(
-    base_url='https://thewise-ollama-server.hf.space',
-    model="codellama")
+    # llm = ChatOllama(
+    # base_url='https://thewise-ollama-server.hf.space',
+    # model="codellama")
+    llm = Ollama(
+    model="codellama",
+    base_url="https://thewise-ollama-server.hf.space",
+    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))
                      
     # Define the system message template
     #Adding CHAT HISTORY to the System template explicitly because mainly Chat history goes to Condense the Human Question with Backround (Not template), but System template goes straight the LLM Chain