add other parameters in dir

app.py

@@ -31,15 +31,23 @@ with st.spinner("🔄 Loading Model..."):
 # ------------------------------
 # File Upload
 # ------------------------------
-uploaded_file = "msci.txt"
+uploaded_file = "./msci"
 
 # ------------------------------
 # Extract Text
 # ------------------------------
-def extract_text(file):
-    loader = TextLoader(file, encoding = "utf-8")
-    return loader.load()[0].page_content
-    # return "\n".join([page.extract_text() for page in pdf_reader.pages if page.extract_text()])
+def extract_text(folder_path):
+    loader = DirectoryLoader(
+        path=folder_path,
+        glob="**/*.txt",  
+        loader_cls=TextLoader,
+        recursive=True 
+    )
+    documents = loader.load()
+    # doc_sources = [doc.metadata["source"] for doc in documents]
+    # loader = TextLoader(file, encoding = "utf-8")
+    # return doc_sources
+    return "\n".join([doc.page_content for doc in documents])
 
 # ------------------------------
 # Build FAISS Index
@@ -52,9 +60,9 @@ def build_faiss(_docs):
 docs = []
 db = None
 
-query = st.text_input("💬 Ask a question about MSCI Indexes:")
+query = st.text_input("💬 Ask a question about MSCI Indexes: - https://www.msci.com/indexes#featured-indexes", placeholder="MSCI World IMI Index")
 
-placeholder = st.empty()
+# placeholder = st.empty()
 
 if uploaded_file:
     text = extract_text(uploaded_file)
@@ -64,11 +72,11 @@ if uploaded_file:
         db = build_faiss(docs)
         st.success("✅ Knowledge Base ready!")
         st.info("You can ask any question regarding data feed to model is as below!")
-        with placeholder:
-            long_text = st.text_area(text, height=150, disabled=True)
+        # with placeholder:
+        #     long_text = st.text_area(text, height=150, disabled=True)
 
 if query and db:
-    placeholder.empty()
+    # placeholder.empty()
     retriever = db.as_retriever(search_kwargs={"k": 3})
     retrieved_docs = retriever.get_relevant_documents(query)
     context = "\n".join([doc.page_content for doc in retrieved_docs])