Update app.py

app.py

@@ -5,8 +5,8 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_openai import OpenAIEmbeddings, ChatOpenAI
 from langchain_community.vectorstores import Qdrant
 from langchain.prompts import ChatPromptTemplate
-from langchain_core.output_parsers import StrOutputParser
-from langchain_core.runnables import RunnablePassthrough
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnablePassthrough
 from qdrant_client import QdrantClient
 from operator import itemgetter
 
@@ -19,7 +19,6 @@ pdf_links = [
     "https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf"
 ]
 
-# Load and process PDFs
 @st.cache_resource
 def load_and_process_pdfs(pdf_links):
     documents = []
@@ -36,7 +35,6 @@ def load_and_process_pdfs(pdf_links):
 
     return text_splitter.split_documents(documents)
 
-# Set up Qdrant and embeddings
 @st.cache_resource
 def setup_vectorstore():
     qdrant_client = QdrantClient(":memory:")
@@ -49,15 +47,11 @@ def setup_vectorstore():
         embeddings=embeddings
     )
     
-    # Check if collection exists, if not, create and populate it
-    collections = qdrant_client.get_collections().collections
-    if not any(collection.name == COLLECTION_NAME for collection in collections):
-        documents = load_and_process_pdfs(pdf_links)
-        vector_store.add_documents(documents)
+    documents = load_and_process_pdfs(pdf_links)
+    vector_store.add_documents(documents)
     
     return vector_store
 
-# Create RAG pipeline
 @st.cache_resource
 def create_rag_pipeline(vector_store):
     retriever = vector_store.as_retriever()
@@ -85,7 +79,7 @@ def create_rag_pipeline(vector_store):
     """
 
     prompt = ChatPromptTemplate.from_template(template)
-    primary_qa_llm = ChatOpenAI(model_name="gpt-4", temperature=0)
+    primary_qa_llm = ChatOpenAI(model_name="gpt-4", temperature=0)  # Note: Changed from gpt-4o-mini to gpt-4
 
     retrieval_augmented_qa_chain = (
         {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
@@ -95,7 +89,6 @@ def create_rag_pipeline(vector_store):
 
     return retrieval_augmented_qa_chain
 
-# Streamlit UI
 st.title("Ask About AI Ethics!")
 
 vector_store = setup_vectorstore()