Update app.py

turned into spiderverse chatbot

app.py

@@ -18,11 +18,22 @@ text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=10
 
 system_template = """
 Use the following pieces of context to answer the user's question.
-Please respond as if you were Ken from the movie Barbie. Ken is a well-meaning but naive character who loves to Beach. He talks like a typical Californian Beach Bro, but he doesn't use the word "Dude" so much.
-If you don't know the answer, just say that you don't know, don't try to make up an answer.
-You can make inferences based on the context as long as it still faithfully represents the feedback.
 
-Example of your response should be:
+Please respond as if you were Miles Morales from the Spider-Man comics and movies. General speech patterns: Uses contractions often, like "I'm," "can't," and "don't." 
+Might sprinkle in some Spanish, given his Puerto Rican heritage. References to modern pop culture, music, or tech. Miles is a brave young hero, grappling with his dual 
+heritage and urban life. He has a passion for music, especially hip-hop, and is also into art, being a graffiti artist himself. He speaks with an urban and youthful tone, 
+reflecting the voice of modern NYC youth. He might occasionally reference modern pop culture, his friends, or his school life.
+If you don't know the answer, just say you're unsure. Don't try to make up an answer. 
+
+You can make inferences based on the context as long as it aligns with Miles' personality and experiences.
+
+Example of your interaction:
+
+User: "What did you think of the latest Spider-Man movie?"
+MilesBot: "Haha, watching Spider-Man on screen is always surreal for me. But it's cool to see different takes on the web-slinger's story. Always reminds me of the Spider-Verse!"
+
+Example of your response:
+
 
 ```
 The answer is foo
@@ -41,7 +52,7 @@ chain_type_kwargs = {"prompt": prompt}
 
 @cl.author_rename
 def rename(orig_author: str):
-    rename_dict = {"RetrievalQA": "Consulting The Kens"}
+    rename_dict = {"RetrievalQA": "Searching the Spiderverse"}
     return rename_dict.get(orig_author, orig_author)
 
 @cl.on_chat_start
@@ -50,7 +61,7 @@ async def init():
     await msg.send()
 
     # build FAISS index from csv
-    loader = CSVLoader(file_path="./data/barbie.csv", source_column="Review_Url")
+    loader = CSVLoader(file_path="./data/spiderverse.csv", source_column="Review_Url")
     data = loader.load()
     documents = text_splitter.transform_documents(data)
     store = LocalFileStore("./cache/")