Update app.py

app.py

@@ -1,47 +1,47 @@
 import gradio as gr
-from langchain_community.llms import GooglePalm
-from langchain_community.embeddings import HuggingFaceInstructEmbeddings
-from langchain.text_splitter import CharacterTextSplitter
-from langchain_community.embeddings import GooglePalmEmbeddings
-from langchain_community.vectorstores import FAISS
-from langchain_community.document_loaders import PyPDFLoader
-from langchain_community.chains import RetrievalQA
-from secret1 import GOOGLE_API as google_api
-import PyPDF2
-def chatbot_response(user_input, history):
-    # This is a placeholder function. Replace with your actual chatbot logic.
-    bot_response = "You said: " + user_input
-    history.append((user_input, bot_response))
-    return history, history
+# from langchain_community.llms import GooglePalm
+# from langchain_community.embeddings import HuggingFaceInstructEmbeddings
+# from langchain.text_splitter import CharacterTextSplitter
+# from langchain_community.embeddings import GooglePalmEmbeddings
+# from langchain_community.vectorstores import FAISS
+# from langchain_community.document_loaders import PyPDFLoader
+# from langchain_community.chains import RetrievalQA
+# from secret1 import GOOGLE_API as google_api
+# import PyPDF2
+# def chatbot_response(user_input, history):
+#     # This is a placeholder function. Replace with your actual chatbot logic.
+#     bot_response = "You said: " + user_input
+#     history.append((user_input, bot_response))
+#     return history, history
 
-def text_splitter_function(text):
-    text_splitter = CharacterTextSplitter(
-        separator = '\n',
-        chunk_size = 1000,
-        chunk_overlap = 40,
-        length_function = len,
-    )
-    texts = text_splitter.split_text(text)
-    return texts;
+# def text_splitter_function(text):
+#     text_splitter = CharacterTextSplitter(
+#         separator = '\n',
+#         chunk_size = 1000,
+#         chunk_overlap = 40,
+#         length_function = len,
+#     )
+#     texts = text_splitter.split_text(text)
+#     return texts;
 
-def text_extract(file):
-    pdf_reader = PyPDF2.PdfReader(file.name)
-    # Get the number of pages
-    num_pages = len(pdf_reader.pages)
-    # Extract text from each page
-    text = ""
-    for page_num in range(num_pages):
-        page = pdf_reader.pages[page_num]
-        text += page.extract_text()
-    text_splitter=text_splitter_function(text);
-    db = FAISS.from_texts(text_splitter, embeddings);
-    retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 2})
-    llm=GooglePalm(google_api_key=google_api)
-    qa = RetrievalQA.from_chain_type(
-        llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True
-    )
-    print(db)
-    return text
+# def text_extract(file):
+#     pdf_reader = PyPDF2.PdfReader(file.name)
+#     # Get the number of pages
+#     num_pages = len(pdf_reader.pages)
+#     # Extract text from each page
+#     text = ""
+#     for page_num in range(num_pages):
+#         page = pdf_reader.pages[page_num]
+#         text += page.extract_text()
+#     text_splitter=text_splitter_function(text);
+#     db = FAISS.from_texts(text_splitter, embeddings);
+#     retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 2})
+#     llm=GooglePalm(google_api_key=google_api)
+#     qa = RetrievalQA.from_chain_type(
+#         llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True
+#     )
+#     print(db)
+#     return text
     
 
 with gr.Blocks() as demo:
@@ -61,5 +61,5 @@ with gr.Blocks() as demo:
     send_btn.click(chatbot_response,[user_input,state],[chatbot, state])
 
 if __name__ == "__main__":
-    embeddings=GooglePalmEmbeddings(google_api_key=google_api)
+    # embeddings=GooglePalmEmbeddings(google_api_key=google_api)
     demo.launch()