file loading testing

app.py

@@ -1,5 +1,5 @@
 import chainlit as cl
-from helper_functions import process_file, load_documents_from_url, add_to_qdrant
+from helper_functions import process_file, load_documents_from_url, store_uploaded_file
 import models
 import agents
 import asyncio
@@ -44,7 +44,7 @@ async def main(message: cl.Message):
             await asyncio.to_thread(qdrant_store.add_documents, splits)
 
             await cl.Message(f"Processing `{message.content}` done. You can now ask questions!").send()
-            
+
         except Exception as e:
             await cl.Message(f"Error processing the document: {e}").send()
     else:
@@ -85,7 +85,8 @@ async def handle_response(res):
         await msg.send()
 
         # load the file
-        docs = await asyncio.to_thread(process_file, file)
+        file_path = store_uploaded_file(file)
+        docs = await asyncio.to_thread(process_file, file_path)
         await cl.Message(content="loaded docs").send()
         splits = await asyncio.to_thread(models.semanticChunker_tuned.split_documents, docs)
         await cl.Message(content="split docs").send()

helper_functions.py

@@ -8,32 +8,24 @@ from langchain_core.language_models import BaseLanguageModel
 import os
 import functools
 import requests
+from chainlit.types import AskFileResponse
 
-def process_file(uploaded_file):
-    # Save the file temporarily to process it
-    temp_file_path = f"/tmp/{uploaded_file.name}"
-    
-    with open(temp_file_path, "wb") as temp_file:
-        # Write the uploaded file content to the temporary file
-        temp_file.write(uploaded_file.read())
-    
-    # Determine the file type and load it accordingly
-    if uploaded_file.name.endswith(".pdf"):
+def store_uploaded_file(uploaded_file: AskFileResponse):
+    file_path = f"./tmp/{uploaded_file.name}"
+    open(file_path, "wb").write(uploaded_file.content)
+    return file_path
+
+def process_file(file_path):
+    if file_path.endswith(".pdf"):
         # Load PDF with PyMuPDFLoader
-        loader = PyMuPDFLoader(temp_file_path)
-    elif uploaded_file.name.endswith(".txt"):
+        loader = PyMuPDFLoader(file_path)
+    elif file_path.endswith(".txt"):
         # Load text file with TextLoader
-        loader = TextLoader(temp_file_path)
+        loader = TextLoader(file_path)
     else:
         raise ValueError("Unsupported file format. Only PDF and TXT are supported.")
 
-    # Load documents from the file
-    documents = loader.load()
-
-    # Clean up the temporary file
-    os.remove(temp_file_path)
-
-    return documents
+    return loader.load()
 
 def load_documents_from_url(url):
     try: