two domain added

app.py

@@ -20,37 +20,6 @@ from utils.helper_functions import *
 openai.api_key = os.environ["OPENAI_API_KEY"]
 
 
-# Load the dataset from a provided source.
-dataset = load_dataset(
-    "eagle0504/youthless-homeless-shelter-web-scrape-dataset-qa-formatted"
-)
-
-# Initialize a new client for ChromeDB.
-client = chromadb.Client()
-
-# Generate a random number between 1 billion and 10 billion.
-random_number: int = np.random.randint(low=1e9, high=1e10)
-
-# Generate a random string consisting of 10 uppercase letters and digits.
-random_string: str = "".join(
-    np.random.choice(list(string.ascii_uppercase + string.digits), size=10)
-)
-
-# Combine the random number and random string into one identifier.
-combined_string: str = f"{random_number}{random_string}"
-
-# Create a new collection in ChromeDB with the combined string as its name.
-collection = client.create_collection(combined_string)
-
-
-# Embed and store the first N supports for this demo
-L = len(dataset["train"]["questions"])
-collection.add(
-    ids=[str(i) for i in range(0, L)],  # IDs are just strings
-    documents=dataset["train"]["questions"],  # Enter questions here
-    metadatas=[{"type": "support"} for _ in range(0, L)],
-)
-
 # Front-end Design
 st.title("Youth Homelessness Chatbot")
 
@@ -75,6 +44,7 @@ st.sidebar.markdown(
 st.sidebar.success(
     "Please enter a distance threshold (we advise to set it around 0.2)."
 )
+option = st.selectbox("Which website do you want to ask?", ("YSA", "Larkin"))
 special_threshold = st.sidebar.number_input(
     "Insert a number", value=0.2, placeholder="Type a number..."
 )  # 0.3
@@ -86,6 +56,43 @@ st.sidebar.warning(
 if clear_button:
     st.session_state.messages = []
 
+
+# Load the dataset from a provided source.
+if option == "YSA":
+    dataset = load_dataset(
+        "eagle0504/youthless-homeless-shelter-web-scrape-dataset-qa-formatted"
+    )
+else:
+    dataset = load_dataset("eagle0504/larkin-web-scrape-dataset-qa-formatted")
+
+
+# Initialize a new client for ChromeDB.
+client = chromadb.Client()
+
+# Generate a random number between 1 billion and 10 billion.
+random_number: int = np.random.randint(low=1e9, high=1e10)
+
+# Generate a random string consisting of 10 uppercase letters and digits.
+random_string: str = "".join(
+    np.random.choice(list(string.ascii_uppercase + string.digits), size=10)
+)
+
+# Combine the random number and random string into one identifier.
+combined_string: str = f"{random_number}{random_string}"
+
+# Create a new collection in ChromeDB with the combined string as its name.
+collection = client.create_collection(combined_string)
+
+
+# Embed and store the first N supports for this demo
+L = len(dataset["train"]["questions"])
+collection.add(
+    ids=[str(i) for i in range(0, L)],  # IDs are just strings
+    documents=dataset["train"]["questions"],  # Enter questions here
+    metadatas=[{"type": "support"} for _ in range(0, L)],
+)
+
+
 # React to user input
 if prompt := st.chat_input("Tell me about YSA"):
     # Display user message in chat message container
@@ -119,10 +126,15 @@ if prompt := st.chat_input("Tell me about YSA"):
             ref_from_db_search = ref["answers"].str.cat(sep=" ")
             final_ref = ref
 
-        try:
-            llm_response = llama2_7b_ysa(question)
-        except:
-            llm_response = "Sorry, the inference endpoint is temporarily down. 😔"
+        if option == "YSA":
+            try:
+                llm_response = llama2_7b_ysa(question)
+            except:
+                llm_response = "Sorry, the inference endpoint is temporarily down. 😔"
+        else:
+            llm_response = (
+                "Sorry for the delay. We are in the progress of fine-tune the model. ⚙️"
+            )
 
         finetuned_llm_guess = ["from_llm", question, llm_response, 0]
         final_ref.loc[-1] = finetuned_llm_guess