Update app.py

app.py

@@ -22,8 +22,8 @@ import chainlit as cl
 load_dotenv()
 
 
-ai_framework_document = PyMuPDFLoader(file_path="https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf").load()
-ai_blueprint_document = PyMuPDFLoader(file_path="https://www.whitehouse.gov/wp-content/uploads/2022/10/Blueprint-for-an-AI-Bill-of-Rights.pdf").load()
+document = PyMuPDFLoader(file_path="sk-proj-eIwEnyq0pSHm0s3yiMdZT3BlbkFJ2aeAlVApXY6jveE8aJ9t").load()
+
 
 
 def metadata_generator(document, name):
@@ -37,22 +37,20 @@ def metadata_generator(document, name):
         doc.metadata["source"] = name
     return collection
 
-recursive_framework_document = metadata_generator(ai_framework_document, "AI Framework")
-recursive_blueprint_document = metadata_generator(ai_blueprint_document, "AI Blueprint")
-combined_documents = recursive_framework_document + recursive_blueprint_document
+documents = metadata_generator(document, "Propaganda")
 
 embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
 
 vectorstore = Qdrant.from_documents(
-    documents=combined_documents,
+    documents=documents,
     embedding=embeddings,
     location=":memory:",
-    collection_name="ai_policy"
+    collection_name="Propaganda"
 )
 alt_retriever = vectorstore.as_retriever()
 
 ## Generation LLM
-llm = ChatOpenAI(model="gpt-4o-mini")
+llm = ChatOpenAI(model="gpt-4o")
 
 RAG_PROMPT = """\
 You are an AI Policy Expert. 
@@ -79,7 +77,7 @@ retrieval_augmented_qa_chain = (
     | {"response": rag_prompt | llm, "context": itemgetter("context")}
 )
 
-#alt_rag_chain.invoke({"question" : "What is the AI framework all about?"})
+
 
 @cl.on_message
 async def handle_message(message):