Update app.py

app.py

@@ -259,43 +259,78 @@ document_chain = create_stuff_documents_chain(llm, prompt)
 retriever = st.session_state.vector.as_retriever()
 retrieval_chain = create_retrieval_chain(retriever, document_chain)
 
-i=0
-while True:
+prompt = st.text_input("Input your prompt here") #, key=key)
+
+# If the user hits enter
+if prompt:
+    # Then pass the prompt to the LLM
+    start = time.process_time()
+    response = retrieval_chain.invoke({"input": prompt})
+    # print(f"Response time: {time.process_time() - start}")
+    st.write(f"Response time: {time.process_time() - start} seconds")
+
+    st.write(response["answer"])
+
+    # With a streamlit expander
+    with st.expander("Document Similarity Search"):
+        # Find the relevant chunks
+        for i, doc in enumerate(response["context"]):
+            # print(doc)
+            # st.write(f"Source Document # {i+1} : {doc.metadata['source'].split('/')[-1]}")
+            st.write(doc)
+            st.write(f"Source Document # {i+1} : {doc.metadata['source'].split('/')[-1]}")
+            
+            
+            st.write(doc.page_content)
+            st.write("--------------------------------")
+
+st.write("---------------------------------")
+
+
+
 
-    # data = ["input1", "input2", "input3"]
 
-    #for i, item in enumerate(data):
-    key = f"input_{i}"
-    # text_input = st.text_input(f"Enter value for {item}", key=key)
-    # Access the value directly
-    print(f"Value for key: {key}")
 
-    i=i+1
-    
-    prompt = st.text_input("Input your prompt here", key=key)
-
-
-    # If the user hits enter
-    if prompt:
-        # Then pass the prompt to the LLM
-        start = time.process_time()
-        response = retrieval_chain.invoke({"input": prompt})
-        # print(f"Response time: {time.process_time() - start}")
-        st.write(f"Response time: {time.process_time() - start} seconds")
-
-        st.write(response["answer"])
-
-        # With a streamlit expander
-        with st.expander("Document Similarity Search"):
-            # Find the relevant chunks
-            for i, doc in enumerate(response["context"]):
-                # print(doc)
-                # st.write(f"Source Document # {i+1} : {doc.metadata['source'].split('/')[-1]}")
-                st.write(doc)
-                st.write(f"Source Document # {i+1} : {doc.metadata['source'].split('/')[-1]}")
-            
-            
-                st.write(doc.page_content)
-                st.write("--------------------------------")
 
-    st.write("---------------------------------")
+
+
+#i=0
+#while True:
+#
+#    # data = ["input1", "input2", "input3"]
+#
+#    #for i, item in enumerate(data):
+#    key = f"input_{i}"
+#    # text_input = st.text_input(f"Enter value for {item}", key=key)
+#    # Access the value directly
+#    print(f"Value for key: {key}")
+#
+#    i=i+1
+#    
+#    prompt = st.text_input("Input your prompt here", key=key)
+#
+#
+#    # If the user hits enter
+#    if prompt:
+#        # Then pass the prompt to the LLM
+#        start = time.process_time()
+#        response = retrieval_chain.invoke({"input": prompt})
+#        # print(f"Response time: {time.process_time() - start}")
+#        st.write(f"Response time: {time.process_time() - start} seconds")
+#
+#        st.write(response["answer"])
+#
+#        # With a streamlit expander
+#        with st.expander("Document Similarity Search"):
+#            # Find the relevant chunks
+#            for i, doc in enumerate(response["context"]):
+#                # print(doc)
+#                # st.write(f"Source Document # {i+1} : {doc.metadata['source'].split('/')[-1]}")
+#                st.write(doc)
+#                st.write(f"Source Document # {i+1} : {doc.metadata['source'].split('/')[-1]}")
+#            
+#            
+#                st.write(doc.page_content)
+#                st.write("--------------------------------")
+#
+#    st.write("---------------------------------")