Update app.py

app.py

@@ -3,11 +3,12 @@ import os
 from langchain_community.document_loaders import PyMuPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_openai import OpenAIEmbeddings, ChatOpenAI
-from langchain_community.vectorstores import Qdrant
+from langchain_qdrant import QdrantVectorStore
 from langchain.prompts import ChatPromptTemplate
-from langchain.schema.output_parser import StrOutputParser
-from langchain.schema.runnable import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
 from qdrant_client import QdrantClient
+from qdrant_client.http.models import Distance, VectorParams
 from operator import itemgetter
 
 # Set up API keys
@@ -37,20 +38,30 @@ def load_and_process_pdfs(pdf_links):
 
 @st.cache_resource
 def setup_vectorstore():
-    qdrant_client = QdrantClient(":memory:")
-    embeddings = OpenAIEmbeddings()
-    
+    LOCATION = ":memory:"
     COLLECTION_NAME = "AI_Ethics_Framework"
-    vector_store = Qdrant(
-        client=qdrant_client, 
+    VECTOR_SIZE = 1536
+
+    qdrant_client = QdrantClient(location=LOCATION)
+
+    # Create the collection
+    qdrant_client.create_collection(
         collection_name=COLLECTION_NAME,
-        embeddings=embeddings
+        vectors_config=VectorParams(size=VECTOR_SIZE, distance=Distance.COSINE),
     )
-    
+
+    # Create the vector store
+    qdrant_vector_store = QdrantVectorStore(
+        client=qdrant_client,
+        collection_name=COLLECTION_NAME,
+        embedding=OpenAIEmbeddings()
+    )
+
+    # Load and add documents
     documents = load_and_process_pdfs(pdf_links)
-    vector_store.add_documents(documents)
-    
-    return vector_store
+    qdrant_vector_store.add_documents(documents)
+
+    return qdrant_vector_store
 
 @st.cache_resource
 def create_rag_pipeline(vector_store):
@@ -79,7 +90,7 @@ def create_rag_pipeline(vector_store):
     """
 
     prompt = ChatPromptTemplate.from_template(template)
-    primary_qa_llm = ChatOpenAI(model_name="gpt-4", temperature=0)  # Note: Changed from gpt-4o-mini to gpt-4
+    primary_qa_llm = ChatOpenAI(model_name="gpt-4", temperature=0)
 
     retrieval_augmented_qa_chain = (
         {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
@@ -89,6 +100,7 @@ def create_rag_pipeline(vector_store):
 
     return retrieval_augmented_qa_chain
 
+# Streamlit UI
 st.title("Ask About AI Ethics!")
 
 vector_store = setup_vectorstore()