Update app.py

app.py

@@ -41,7 +41,7 @@ async def create_text_splitter(docs: List[langchain_core.documents.Document]):
     docs = text_splitter.split_documents(docs) # split the documents into chunks
     return docs
 
-def create_faiss_vector_store(docs: List[langchain_core.documents.Document]) -> FAISS:
+async def create_faiss_vector_store(docs: List[langchain_core.documents.Document]) -> FAISS:
     """
     Create a FAISS vector store or vector database from a list of documents
     More Info: https://python.langchain.com/docs/integrations/vectorstores/faiss/
@@ -50,10 +50,13 @@ def create_faiss_vector_store(docs: List[langchain_core.documents.Document]) ->
     Returns:
         FAISS: A vector store containing the documents
     """
-    embedding = cl.user_session.get("embedding") # we can get the embedding model from the user session or pass as a parameter too!
-    vector_db = FAISS.from_documents(docs, embedding) # create the vector store
-    vector_db.k = 5 # we set k to 5, so we get 5 documents back
-    return vector_db
+    try:
+        embedding = cl.user_session.get("embedding") # we can get the embedding model from the user session or pass as a parameter too!
+        vector_db = FAISS.from_documents(docs, embedding) # create the vector store
+        vector_db.k = 5 # we set k to 5, so we get 5 documents back
+        return vector_db
+    except Exception as e:
+        await cl.Message(content=f"failed to create vector db: {e}").send() # display the error if we failed to create the vector db
 
 def create_bm25_retreiver(docs: List[langchain_core.documents.Document]) -> BM25Retriever:
     """
@@ -100,7 +103,7 @@ async def start():
         await cl.Message(content="embedding model loaded").send()
         youtube_link = await cl.AskUserMessage("Please provide the YouTube video link").send() # We can ask the user for input using cl.AskUserMessage().send() which does not affect cl.on_message()
         # more on ask user message: https://docs.chainlit.io/api-reference/ask/ask-for-input
-        await cl.Message(content=f"youtube link: {youtube_link}").send() # display and double check to make sure the link is correct
+        await cl.Message(content=f"youtube link: {youtube_link['content']}").send() # display and double check to make sure the link is correct
         youtube_docs = await create_youtube_transcription(youtube_link['content']) # create the youtube transcription
         transcription = youtube_docs[0].page_content # get the transcription of the first document
         await cl.Message(content=f"youtube docs: {transcription}").send() # display the transcription of the first document to show that we have the correct data