Update app.py

app.py

@@ -5,7 +5,6 @@ from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.llms import HuggingFaceHub
 from langchain.chains import ConversationalRetrievalChain
-from pathlib import Path
 
 # Load the HuggingFace language model and embeddings
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
@@ -17,14 +16,29 @@ embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-b
 vector_store = None
 retriever = None
 
-def update_documents(documents):
+def update_documents(text_input):
     global vector_store, retriever
+    # Split the input text into individual documents based on newlines or other delimiters
+    documents = text_input.split("\n")
+    
     # Update the FAISS vector store with new documents
     vector_store = FAISS.from_texts(documents, embeddings)
+    
+    # Set the retriever to use the new vector store
     retriever = vector_store.as_retriever()
     return f"{len(documents)} documents successfully added to the vector store."
 
-def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
+# Set up ConversationalRetrievalChain
+rag_chain = None
+
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
     global rag_chain, retriever
     
     if retriever is None:
@@ -54,21 +68,27 @@ def respond(message, history: list[tuple[str, str]], system_message, max_tokens,
     # Return the model's response
     return response['answer']
 
-def upload_file(file):
-    text = file.read().decode("utf-8")  # Read file content
-    documents = text.split("\n")  # Split into documents
-    return update_documents(documents)
+def upload_file(filepath):
+    name = Path(filepath).name
+    return [gr.UploadButton(visible=False), gr.DownloadButton(label=f"Download {name}", value=filepath, visible=True)]
+
+def download_file():
+    return [gr.UploadButton(visible=True), gr.DownloadButton(visible=False)]
 
 # Gradio interface setup
 demo = gr.Blocks()
 
 with demo:
     with gr.Row():
-        u = gr.UploadButton("Upload a file (txt)", file_count="single", file_types=[".txt"])
-        
-    # Process the uploaded file
-    u.upload(upload_file, u, gr.Textbox(label="Status", visible=True))
+        # upload_button = gr.Button("Upload Documents")
+        with gr.Row():
+            u = gr.UploadButton("Upload a file", file_count="single")
+            d = gr.DownloadButton("Download the file", visible=False)
 
+    u.upload(upload_file, u, [u, d])
+    d.click(download_file, None, [u, d])
+        
+    
     with gr.Row():
         # Chat interface for the RAG system
         chat = gr.ChatInterface(
@@ -81,5 +101,8 @@ with demo:
             ],
         )
 
+    # Bind button to update the document vector store
+    # upload_button.click(update_documents, inputs=[doc_input], outputs=gr.Textbox(label="Status"))
+
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()