Update app.py

app.py

@@ -8,7 +8,6 @@ from langchain_core.runnables import RunnablePassthrough
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 import bs4
 import torch
-import getpass
 
 # Prompt the user to enter their Langchain API key
 api_key_langchain = st.text_input("Enter your LANGCHAIN_API_KEY", type="password")
@@ -47,13 +46,11 @@ else:
     embedding_model = SentenceTransformerEmbedding('all-MiniLM-L6-v2')
 
     # Load, chunk, and index the contents of the blog
-    def load_data():
+    def load_data(url):
         loader = WebBaseLoader(
-            web_paths=("https://lilianweng.github.io/posts/2023-06-23-agent/",),
+            web_paths=(url,),
             bs_kwargs=dict(
-                parse_only=bs4.SoupStrainer(
-                    class_=("post-content", "post-title", "post-header")
-                )
+                parse_only=bs4.SoupStrainer()
             ),
         )
         docs = loader.load()
@@ -62,30 +59,34 @@ else:
         vectorstore = Chroma.from_documents(documents=splits, embedding=embedding_model)
         return vectorstore
 
-    vectorstore = load_data()
-
     # Streamlit UI
-    st.title("Blog Retrieval and Question Answering")
+    st.title("URL Retrieval and Question Answering")
 
-    question = st.text_input("Enter your question:")
+    # Input URL from user
+    url = st.text_input("Enter the URL:")
 
-    if question:
-        retriever = vectorstore.as_retriever()
-        prompt = hub.pull("rlm/rag-prompt", api_key=api_key_langchain)
+    if url:
+        vectorstore = load_data(url)
 
-        def format_docs(docs):
-            return "\n\n".join(doc.page_content for doc in docs)
+        question = st.text_input("Enter your question:")
 
-        rag_chain = (
-            {"context": retriever | format_docs, "question": RunnablePassthrough()}
-            | prompt
-            | llm  # Replace with your LLM or appropriate function if needed
-            | StrOutputParser()
-        )
+        if question:
+            retriever = vectorstore.as_retriever()
+            prompt = hub.pull("rlm/rag-prompt", api_key=api_key_langchain)
+
+            def format_docs(docs):
+                return "\n\n".join(doc.page_content for doc in docs)
+
+            rag_chain = (
+                {"context": retriever | format_docs, "question": RunnablePassthrough()}
+                | prompt
+                | llm  # Replace with your LLM or appropriate function if needed
+                | StrOutputParser()
+            )
 
-        # Example invocation
-        try:
-            result = rag_chain.invoke(question)
-            st.write("Answer:", result)
-        except Exception as e:
-            st.error(f"An error occurred: {e}")
+            # Example invocation
+            try:
+                result = rag_chain.invoke(question)
+                st.write("Answer:", result)
+            except Exception as e:
+                st.error(f"An error occurred: {e}")