From dad10e82cbc775abbb739e525377f9f07a05a70a Mon Sep 17 00:00:00 2001
From: Sebastian Schmidt <publicarray@users.noreply.github.com>
Date: Sun, 2 Feb 2025 09:46:27 +1100
Subject: [PATCH] Update llama3.1_local_rag.py

Fixes The class `OllamaEmbeddings` was deprecated in LangChain 0.3.1 and will be removed in 1.0.0. An updated version of the class exists in the :class:`~langchain-ollama package and should be used instead.
---
 .../llama3.1_local_rag/llama3.1_local_rag.py     | 16 ++++++++++------
 .../llama3.1_local_rag/requirements.txt          |  3 ++-
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/rag_tutorials/llama3.1_local_rag/llama3.1_local_rag.py b/rag_tutorials/llama3.1_local_rag/llama3.1_local_rag.py
index b7bfdad..854f526 100644
--- a/rag_tutorials/llama3.1_local_rag/llama3.1_local_rag.py
+++ b/rag_tutorials/llama3.1_local_rag/llama3.1_local_rag.py
@@ -1,15 +1,19 @@
 import streamlit as st
-import ollama
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.document_loaders import WebBaseLoader
 from langchain_community.vectorstores import Chroma
-from langchain_community.embeddings import OllamaEmbeddings
+from langchain_ollama import OllamaEmbeddings
+from langchain_ollama import ChatOllama
 
 st.title("Chat with Webpage 🌐")
 st.caption("This app allows you to chat with a webpage using local llama3 and RAG")
 
 # Get the webpage URL from the user
 webpage_url = st.text_input("Enter Webpage URL", type="default")
+# Connect to Ollama
+ollama_endpoint = "http://127.0.0.1:11434"
+ollama_model = "llama3.1"
+ollama = ChatOllama(model=ollama_model, base_url=ollama_endpoint)
 
 if webpage_url:
     # 1. Load the data
@@ -19,14 +23,14 @@ if webpage_url:
     splits = text_splitter.split_documents(docs)
 
     # 2. Create Ollama embeddings and vector store
-    embeddings = OllamaEmbeddings(model="llama3.1")
+    embeddings = OllamaEmbeddings(model=ollama_model, base_url=ollama_endpoint)
     vectorstore = Chroma.from_documents(documents=splits, embedding=embeddings)
 
     # 3. Call Ollama Llama3 model
     def ollama_llm(question, context):
         formatted_prompt = f"Question: {question}\n\nContext: {context}"
-        response = ollama.chat(model='llama3.1', messages=[{'role': 'user', 'content': formatted_prompt}])
-        return response['message']['content']
+        response = ollama.invoke([('human', formatted_prompt)])
+        return response.content.strip()
 
     # 4. RAG Setup
     retriever = vectorstore.as_retriever()
@@ -47,4 +51,4 @@ if webpage_url:
     # Chat with the webpage
     if prompt:
         result = rag_chain(prompt)
-        st.write(result)
\ No newline at end of file
+        st.write(result)
diff --git a/rag_tutorials/llama3.1_local_rag/requirements.txt b/rag_tutorials/llama3.1_local_rag/requirements.txt
index 2824430..b2b7614 100644
--- a/rag_tutorials/llama3.1_local_rag/requirements.txt
+++ b/rag_tutorials/llama3.1_local_rag/requirements.txt
@@ -1,4 +1,5 @@
 streamlit 
 ollama 
 langchain 
-langchain_community
\ No newline at end of file
+langchain_community
+langchain_ollama