Update to llm

app/rag.py

@@ -1,5 +1,5 @@
 from langchain_community.vectorstores import Chroma
-from langchain_community.chat_models import ChatOllama
+from langchain_community.llms import Ollama
 from langchain_community.embeddings import FastEmbedEmbeddings
 from langchain.schema.output_parser import StrOutputParser
 from langchain_community.document_loaders import PyMuPDFLoader
@@ -15,7 +15,7 @@ class ChatPDF:
     chain = None
 
     def __init__(self):
-        self.model = ChatOllama(
+        self.model = Ollama(
             model="qwen:1.8b",
             keep_alive=-1,
             temperature=0,
@@ -30,8 +30,8 @@ class ChatPDF:
             """
             <|im_start|> You are an assistant for question-answering tasks. Use the following pieces of retrieved context to 
             answer the question. If you don't know the answer, just say that you don't know. Use 512 characters
-             maximum and keep the answer concise. <|im_end|>
-            <|im_start|> Question: {question} 
+             maximum and keep the answer concise. 
+            Question: {question} 
             Context: {context} 
             Answer: <|im_end|>
             """