Update app.py

app.py

@@ -5,7 +5,6 @@ from langchain_community.document_loaders import DirectoryLoader, TextLoader
 from langchain_community.vectorstores import FAISS
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from transformers import AutoTokenizer
 
 # Step 1: Extract ZIP
 def extract_zip(zip_path, extract_to):
@@ -14,7 +13,14 @@ def extract_zip(zip_path, extract_to):
             zip_ref.extractall(extract_to)
         st.success("✅ Knowledge Base extracted successfully!")
 
-# Step 2: Load and embed knowledge base
+# Step 2: Auto-detect folder that contains .md files
+def find_md_folder(base_path):
+    for root, dirs, files in os.walk(base_path):
+        if any(file.endswith(".md") for file in files):
+            return root
+    return None
+
+# Step 3: Load and embed knowledge base
 @st.cache_resource
 def load_knowledge_base(folder_path):
     loader = DirectoryLoader(folder_path, glob="*.md", loader_cls=TextLoader)
@@ -29,11 +35,8 @@ def load_knowledge_base(folder_path):
         st.error("❌ Failed to split documents.")
         return None
 
-    # Use AutoTokenizer to load the appropriate tokenizer for the model
     model_name = "sentence-transformers/paraphrase-MiniLM-L6-v2"
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-    embeddings = HuggingFaceEmbeddings(model_name=model_name, tokenizer=tokenizer)
+    embeddings = HuggingFaceEmbeddings(model_name=model_name)
 
     try:
         db = FAISS.from_documents(split_docs, embeddings)
@@ -45,19 +48,22 @@ def load_knowledge_base(folder_path):
 # Streamlit UI
 st.title("📘 Fitlytic Chatbot")
 
-# Step 3: Extract ZIP if needed
+# Step 4: Extract ZIP if needed
 zip_path = "Knowledge_Base.zip"
 extract_to = "Knowledge_Base"
 extract_zip(zip_path, extract_to)
 
-# Step 4: Load knowledge base
-if os.path.exists(extract_to):
-    db = load_knowledge_base(os.path.join(extract_to, "Knowledge_Base"))
+# Step 5: Find folder containing .md files
+md_folder = find_md_folder(extract_to)
+
+# Step 6: Load knowledge base
+if md_folder:
+    db = load_knowledge_base(md_folder)
 else:
-    st.error("❌ ZIP file not found or extraction failed.")
+    st.error("❌ Could not find any Markdown files in the extracted folder.")
     st.stop()
 
-# Step 5: User interaction
+# Step 7: User interaction
 if db:
     query = st.text_input("Ask me anything about Fitlytic:")
     if query: