Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
-from langchain.vectorstores import Chroma
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.llms import HuggingFaceHub
+from langchain_community.vectorstores import Chroma
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.llms import HuggingFaceHub
 from langchain.chains import ConversationalRetrievalChain
-from langchain.document_loaders import SimpleDocumentLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.memory import ConversationBufferMemory
+from langchain_community.document_loaders import PyPDFLoader
 
 # Initialize the Hugging Face embedding model
 embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
@@ -21,19 +21,21 @@ memory = ConversationBufferMemory(memory_key="chat_history", return_messages=Tru
 qa_chain = ConversationalRetrievalChain.from_llm(llm, retriever=vectorstore.as_retriever(), memory=memory)
 
 def upload_docs(docs):
-    # Load and process the uploaded documents
-    loader = SimpleDocumentLoader(docs)
-    documents = loader.load()
-    
+    # Load and process the uploaded PDF documents
+    loaded_docs = []
+    for doc in docs:
+        loader = PyPDFLoader(doc.name)
+        loaded_docs.extend(loader.load())
+
     # Split documents into manageable chunks
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    texts = text_splitter.split_documents(documents)
-    
+    texts = text_splitter.split_documents(loaded_docs)
+
     # Add documents to the vector store and persist them
     vectorstore.add_documents(texts)
     vectorstore.persist()
-    
-    return "Documents uploaded and processed successfully!"
+
+    return "PDF documents uploaded and processed successfully!"
 
 def chat(query):
     # Process the query with the conversational chain and return the result
@@ -44,7 +46,7 @@ def chat(query):
 with gr.Blocks() as demo:
     with gr.Row():
         with gr.Column():
-            doc_upload = gr.File(label="Upload your documents", file_types=[".txt", ".pdf", ".docx"], multiple=True)
+            doc_upload = gr.File(label="Upload your PDF documents", file_types=[".pdf"], multiple=True)
             upload_button = gr.Button("Upload")
             upload_button.click(upload_docs, inputs=doc_upload, outputs=gr.Textbox())