Update app.py

app.py

@@ -6,9 +6,9 @@ hftoken = os.environ["hftoken"]
 
 from langchain_huggingface import HuggingFaceEndpoint
 
-repo_id = "mistralai/Mistral-7B-Instruct-v0.3"
+# repo_id = "mistralai/Mistral-7B-Instruct-v0.3"
 # repo_id = "google/gemma-2-9b-it"
-# repo_id = "meta-llama/Meta-Llama-3-8B-Instruct" # answers the question well, but continues the text and does not stop when its necessary. often ends in incomplete responses.
+repo_id = "meta-llama/Meta-Llama-3-8B-Instruct" # answers the question well, but continues the text and does not stop when its necessary. often ends in incomplete responses.
 # repo_id = "mistralai/Mixtral-8x22B-Instruct-v0.1"
 llm = HuggingFaceEndpoint(repo_id = repo_id, max_new_tokens = 128, temperature = 0.7, huggingfacehub_api_token = hftoken)
 
@@ -39,7 +39,7 @@ from langchain_core.prompts import ChatPromptTemplate
 
 prompt = ChatPromptTemplate.from_template("""Given the following context and a question, generate an answer based on the provided context only.
 
-In your answer, try to use as much text as possible from the "response" section in the source document context.
+In your answer, try to use as much text as possible from the "response" section in the source document context without making significant changes.
 If someone asks "Who are you?" or a similar question, reply with "I am Rishi's assistant built using a Large Language Model!"
 If the answer is not found in the context, kindly state "I don't know. Please ask Rishi on Discord at https://discord.gg/6ezpZGeCcM or email [email protected]." Do not attempt to make up an answer.