now able to set your own api key

app.py

@@ -12,11 +12,6 @@ from langchain.schema.runnable.config import RunnableConfig
 from langchain_core.output_parsers import StrOutputParser
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.document_loaders import UnstructuredPDFLoader
-from langchain_community.document_loaders import OnlinePDFLoader
-from langchain_community.document_loaders import PyPDFLoader
-
-
-
 
 
 load_dotenv()
@@ -87,26 +82,37 @@ loader = UnstructuredPDFLoader("br_femogfirs.pdf",  strategy="fast")
 data = loader.load_and_split(text_splitter)
 # data = loader.load()
 
-embedding_model = OpenAIEmbeddings(model="text-embedding-3-small")
 
-vector_store = Pinecone.from_documents(data, embedding_model, index_name="bygnings-regl-rag-1")
-retriever = vector_store.as_retriever()
 
 rag_prompt = ChatPromptTemplate.from_template(RAG_PROMPT)
 
-model = ChatOpenAI(model="gpt-3.5-turbo")
 
 @cl.on_chat_start
-async def main():
-    mecanic_qa_chain = ""
-    mecanic_qa_chain = (
-        {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
-        | RunnablePassthrough.assign(context=itemgetter("context"))
-        | rag_prompt | model | StrOutputParser()
-    )
+async def main():    
+    
+    user_env = await cl.AskUserMessage(content="Please enter your OpenAI API Key:").send()
+
+    if user_env:
+
+            await cl.Message(content=f"{user_env['output']}",).send()
+
+            os.environ["OPENAI_API_KEY"] = user_env['output']
+
+            model = ChatOpenAI(model="gpt-3.5-turbo")
+            embedding_model = OpenAIEmbeddings(model="text-embedding-3-small")
+            vector_store = Pinecone.from_documents(data, embedding_model, index_name="bygnings-regl-rag-1")
+            retriever = vector_store.as_retriever()
+
+
+            mecanic_qa_chain = (
+            {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
+            | RunnablePassthrough.assign(context=itemgetter("context"))
+            | rag_prompt | model | StrOutputParser())
 
     cl.user_session.set("runnable", mecanic_qa_chain)
 
+ 
+
 @cl.on_message
 async def on_message(message: cl.Message):
     runnable = cl.user_session.get("runnable")