Update app.py

app.py

@@ -171,13 +171,18 @@ def upload_to_firebase(user_id, file):
     content = convert_file_to_md(file)  # Ensure this function extracts content correctly
     if not content:
         return None, "Failed to extract content from the file."
+    
+    existing_files = st.session_state.get("documents", {})
+    for doc_id, doc_data in existing_files.items():
+        if doc_data["name"] == file.name and doc_data["content"] == content:
+            return None, f"File '{file.name}' already exists."
 
     doc_id = str(uuid.uuid4())
     document_data = {"content": content, "name": file.name}
 
     # Save document to Firebase
     db.child("users").child(user_id).child("KnowledgeBase").child(doc_id).set(document_data)
-
+    fetch_documents() 
     # Add content to the knowledge base
     if "knowledge_base" not in st.session_state:
         st.session_state["knowledge_base"] = []
@@ -190,15 +195,16 @@ def upload_to_firebase(user_id, file):
     return content, None
 
 
+    
 def index_document_content(doc_content, doc_id):
     """
     Indexes the document content by splitting it into chunks and creating embeddings.
     """
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
     texts = text_splitter.split_text(doc_content)
 
     # Create embeddings for each chunk
-    embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
+    embeddings = OpenAIEmbeddings(model="text-embedding-ada-002", api_key=openai_api_key)
     doc_metadata = [{"doc_id": doc_id, "chunk_id": i} for i in range(len(texts))]
     vector_store = FAISS.from_texts(texts, embeddings, metadatas=doc_metadata)
 
@@ -544,13 +550,17 @@ def download_link(content, filename):
 
 
 def fetch_documents():
+    """
+    Fetch all documents for the current user from Firebase and update session state.
+    """
+    user_id = st.session_state["wix_user_id"]
     try:
-        docs = db.child("users").child(st.session_state["wix_user_id"]).child("KnowledgeBase").get().val()
-        st.session_state["documents"] = docs if docs else {}
+        documents = db.child("users").child(user_id).child("KnowledgeBase").get()
+        st.session_state["documents"] = {
+            doc.key(): doc.val() for doc in documents.each()
+        } if documents.each() else {}
     except Exception as e:
         st.sidebar.error(f"Error fetching documents: {e}")
-        st.session_state["documents"] = {}
-
 
 
 # Function to delete a document from Firebase
@@ -778,16 +788,7 @@ def side():
             if uploaded_file:
                 try:
                     content, _= upload_to_firebase(st.session_state["wix_user_id"], uploaded_file)
-                    if content:
-                        doc_id = str(uuid.uuid4())
-                        db.child("users").child(st.session_state["wix_user_id"]).child("KnowledgeBase").child(doc_id).set(
-                            {"content": content, "name": uploaded_file.name}
-                        )
-                        st.session_state["documents"][doc_id] = {"content": content, "name": uploaded_file.name}
-                        st.sidebar.success(f"Document '{uploaded_file.name}' uploaded successfully!")
-                        st.rerun()
-                    else:
-                        st.sidebar.warning("File upload failed.")
+                    st.rerun()
                 except Exception as e:
                     st.sidebar.error(f"Error uploading document: {e}")
             else: