Update app.py

app.py

@@ -3,10 +3,10 @@ from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_google_genai import GoogleGenerativeAIEmbeddings
 from langchain.prompts import PromptTemplate
 from langchain_community.vectorstores import Chroma
-from langchain_text_splitters import CharacterTextSplitter
+from langchain.text_splitter import CharacterTextSplitter
 from langchain.chains.combine_documents import create_stuff_documents_chain
 from langchain.chains import create_retrieval_chain
-from langchain.vectorstores import Chroma
+from langchain_community.document_loaders import PyPDFLoader
 
 # Set your API key
 GOOGLE_API_KEY = "AIzaSyCHLS-wFvSYxSTJjkRQQ-FiC5064112Eq8"
@@ -29,17 +29,14 @@ pages = loader.load_and_split(text_splitter)
 # Turn the chunks into embeddings and store them in Chroma
 vectordb = Chroma.from_documents(pages, embeddings)
 
-# Configure Chroma as a retriever with top_k=5
+# Configure Chroma as a retriever with top_k=10
 retriever = vectordb.as_retriever(search_kwargs={"k": 10})
 
 # Create the retrieval chain
-template = """
-You are a helpful AI assistant.
-Answer based on the context provided. 
+template = """You are a helpful AI assistant. Answer based on the context provided.
 context: {context}
 input: {input}
-answer:
-"""
+answer:"""
 prompt = PromptTemplate.from_template(template)
 combine_docs_chain = create_stuff_documents_chain(llm, prompt)
 retrieval_chain = create_retrieval_chain(retriever, combine_docs_chain)
@@ -48,4 +45,4 @@ retrieval_chain = create_retrieval_chain(retriever, combine_docs_chain)
 response = retrieval_chain.invoke({"input": "How do I apply for personal leave?"})
 
 # Print the answer to the question
-print(response["answer"])
+print(response["answer"])