Update app.py

app.py

@@ -25,6 +25,7 @@ st.header("Welcome!. Today, What company's sustainability story is inspiring you
 
 myurl = st.text_input("Give the URL to find a sustainability or annual report", "https://www.wipro.com/content/dam/nexus/en/sustainability/sustainability_reports/wipro-sustainability-report-fy-2021-22.pdf")
 
+
 yourquestion = st.text_input('Ask your question on best practices', 'What is Wipro plans for Biodiversity in 2024?')
 st.write('Your input is ', yourquestion)
 
@@ -40,33 +41,35 @@ llmgpt3 = AzureOpenAI(      deployment_name="testdavanci", model_name="text-davi
 #llmchatgpt = AzureOpenAI(     deployment_name="esujnand", model_name="gpt-35-turbo" )
 
 
-if myurl:
-    index = None
-    loader1 = PyPDFLoader(myurl)
-    langchainembeddings = OpenAIEmbeddings(deployment="textembedding", chunk_size=1)
-
-    index = VectorstoreIndexCreator(
-            # split the documents into chunks
-            text_splitter=CharacterTextSplitter(chunk_size=1000, chunk_overlap=0),
-            # select which embeddings we want to use
-            embedding=langchainembeddings,
-            # use Chroma as the vectorestore to index and search embeddings
-            vectorstore_cls=Chroma
-        ).from_loaders([loader1])
-        
-    st.write("loaded")
+with st.form("my_form"):
 
+   myurl = st.text_input("Give the URL to find a sustainability or annual report", "https://www.wipro.com/content/dam/nexus/en/sustainability/sustainability_reports/wipro-sustainability-report-fy-2021-22.pdf")
 
+   yourquestion = st.text_input('Ask your question on best practices', 'What is Wipro plans for Biodiversity in 2024?')
+   st.write('Your input is ', yourquestion)
 
-if yourquestion:
-  answer = index.query(llm=llmgpt3, question=yourquestion, chain_type="map_reduce")
-  st.write(answer)
+   # Every form must have a submit button.
+   submitted = st.form_submit_button("Ask question")
+   if submitted:
+      if myurl:
+          index = None
+          loader1 = PyPDFLoader(myurl)
+          langchainembeddings = OpenAIEmbeddings(deployment="textembedding", chunk_size=1)
 
+          index = VectorstoreIndexCreator(
+                  # split the documents into chunks
+                  text_splitter=CharacterTextSplitter(chunk_size=1000, chunk_overlap=0),
+                  # select which embeddings we want to use
+                  embedding=langchainembeddings,
+                  # use Chroma as the vectorestore to index and search embeddings
+                  vectorstore_cls=Chroma
+              ).from_loaders([loader1])
+              
+          st.write("loaded")
 
- 
 
- 
- 
 
+      if yourquestion:
+        answer = index.query(llm=llmgpt3, question=yourquestion, chain_type="map_reduce")
+        st.write(answer)
 
-