Update app.py

app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 from langchain_community.document_loaders import WebBaseLoader
-from langchain.text_splitter import CharacterTextSplitter
+from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import Chroma
 from langchain_nomic.embeddings import NomicEmbeddings
 
@@ -11,9 +11,11 @@ from langchain_core.runnables import RunnablePassthrough
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.prompts import ChatPromptTemplate
 
+from langchain.embeddings import HuggingFaceEmbeddings
 
 def method_get_website_text(urls):
     # Convert string of URLs to list
+    
     urls_list = urls.split("\n")
     docs = [WebBaseLoader(url).load() for url in urls_list]
     docs_list = [item for sublist in docs for item in sublist]
@@ -22,7 +24,9 @@ def method_get_website_text(urls):
 
 def method_get_text_chunks(text):
     #split the text into chunks
-    text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=7500, chunk_overlap=100)
+    
+    #text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=7500, chunk_overlap=100)
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
     doc_splits = text_splitter.split_documents(text)
     return doc_splits
 
@@ -31,7 +35,8 @@ def method_get_vectorstore(document_chunks):
     #convert text chunks into embeddings and store in vector database
 
     # create the open-source embedding function
-    embeddings = NomicEmbeddings(model="nomic-embed-text-v1.5")
+    #embeddings = NomicEmbeddings(model="nomic-embed-text-v1.5")
+    embeddings = HuggingFaceEmbeddings()
 
     # create a vectorstore from the chunks
     vector_store = Chroma.from_documents(document_chunks, embeddings)
@@ -51,7 +56,7 @@ def get_context_retriever_chain(vector_store, question):
     after_rag_prompt = ChatPromptTemplate.from_template(after_rag_template)
     
     # Initialize the Hugging Face language model (LLM)
-    llm = HuggingFaceHub(repo_id="mistralai/Mistral-7B-Instruct-v0.2")
+    llm = HuggingFaceHub(repo_id="mistralai/Mistral-7B-Instruct-v0.2", model_kwargs={"temperature":0.6, "max_length":512})
     
     # Construct the RAG pipeline
     after_rag_chain = (