demo updated to llama 3.1

llama3.1_local_rag/README.md

@@ -0,0 +1,34 @@
+## 💻 Local Lllama-3.1 with RAG
+Streamlit app that allows you to chat with any webpage using local Llama-3.1 and Retrieval Augmented Generation (RAG). This app runs entirely on your computer, making it 100% free and without the need for an internet connection.
+
+
+### Features
+- Input a webpage URL
+- Ask questions about the content of the webpage
+- Get accurate answers using RAG and the Llama-3.1 model running locally on your computer
+
+### How to get Started?
+
+1. Clone the GitHub repository
+
+```bash
+git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git
+```
+2. Install the required dependencies:
+
+```bash
+pip install -r requirements.txt
+```
+3. Run the Streamlit App
+```bash
+streamlit run llama3.1_local_rag.py
+```
+
+### How it Works?
+
+- The app loads the webpage data using WebBaseLoader and splits it into chunks using RecursiveCharacterTextSplitter.
+- It creates Ollama embeddings and a vector store using Chroma.
+- The app sets up a RAG (Retrieval-Augmented Generation) chain, which retrieves relevant documents based on the user's question.
+- The Llama-3.1 model is called to generate an answer using the retrieved context.
+- The app displays the answer to the user's question.
+

llama3.1_local_rag/llama3.1_local_rag.py

@@ -0,0 +1,50 @@
+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
+
+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")
+
+if webpage_url:
+    # 1. Load the data
+    loader = WebBaseLoader(webpage_url)
+    docs = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=10)
+    splits = text_splitter.split_documents(docs)
+
+    # 2. Create Ollama embeddings and vector store
+    embeddings = OllamaEmbeddings(model="llama3.1")
+    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']
+
+    # 4. RAG Setup
+    retriever = vectorstore.as_retriever()
+
+    def combine_docs(docs):
+        return "\n\n".join(doc.page_content for doc in docs)
+
+    def rag_chain(question):
+        retrieved_docs = retriever.invoke(question)
+        formatted_context = combine_docs(retrieved_docs)
+        return ollama_llm(question, formatted_context)
+
+    st.success(f"Loaded {webpage_url} successfully!")
+
+    # Ask a question about the webpage
+    prompt = st.text_input("Ask any question about the webpage")
+
+    # Chat with the webpage
+    if prompt:
+        result = rag_chain(prompt)
+        st.write(result)

llama3.1_local_rag/requirements.txt

@@ -0,0 +1,4 @@
+streamlit 
+ollama 
+langchain 
+langchain_community