Update app.py

app.py

@@ -51,13 +51,16 @@ def display_chat_history(chain):
 
 def create_conversational_chain(vector_store):
     load_dotenv()
+    replicate_api_token = "r8_AA3K1fhDykqLa5M74E5V0w5ss1z0P9S3foWJl"  # Replace with your actual token
+    os.environ["REPLICATE_API_TOKEN"] = replicate_api_token
+
     llm = Replicate(
-    streaming=True,
-    model="replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781",
-    replicate_api_token="r8_AA3K1fhDykqLa5M74E5V0w5ss1z0P9S3foWJl",  
-    callbacks=[StreamingStdOutCallbackHandler()],
-    input={"temperature": 0.01, "max_length": 500, "top_p": 1}
-)
+        streaming=True,
+        model="replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781",
+        callbacks=[StreamingStdOutCallbackHandler()],
+        input={"temperature": 0.01, "max_length": 500, "top_p": 1},
+        replicate_api_token=replicate_api_token
+    )
     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
 
     chain = ConversationalRetrievalChain.from_llm(llm=llm, chain_type='stuff',
@@ -102,4 +105,4 @@ def main():
         display_chat_history(chain)
 
 if __name__ == "__main__":
-    main()
+    main()