Upload 11 files

app_drive.py

@@ -6,14 +6,15 @@ import datetime
 import os
 
 from lc_base.chain import openai_chain
+from lc_base.dnd_database import create_dnd_database
 from driveapi.drive import upload_chat_to_drive
 from driveapi.drive_database import create_chroma_db
 
 # global time_diff, model_name, search_type
 time_diff = 0
-# model_name="gpt-3.5-turbo-1106"
+model_name="gpt-3.5-turbo-1106" # FOR TESTING
 # model_name = "gpt-4-1106-preview"
-model_name = "gpt-4-0125-preview"
+# model_name = "gpt-4-0125-preview"
 search_type = "stuff"
 input_question = ""
 model_response = ""
@@ -23,20 +24,28 @@ dir = ""
 title = """<h1 align="center">ResearchBuddy</h1>"""
 description = """<br><br><h3 align="center">This is a GPT based Research Buddy to assist in navigating new research topics.</h3>"""
 
-def save_api_key(api_key):
-    os.environ['OPENAI_API_KEY'] = str(api_key)
-    return f"API Key saved in the environment: {api_key}"
 
 def save_drive_link(drive_link):
+    drive_link += "?usp=sharing"
     os.environ['DRIVE_LINK'] = str(drive_link)
-    print(f"API Key saved in the environment: {drive_link}")
+    print("Drive link saved in the environment")
     return None
 
-def create_data_from_drive():
+def create_data_from_drive(drive_link):
     global db
+
+    drive_link += "?usp=sharing"
+    os.environ['DRIVE_LINK'] = str(drive_link)
+    print("Drive link saved in the environment! Creating Database...")
+
     db = create_chroma_db()
     return "Processing Completed - You can start the chat now!"
 
+def check_pdfs(pdf_files):
+    global db
+    db = create_dnd_database(pdf_files)
+    return "Processing Completed - You can start the chat now!"
+
 def user(user_message, history):
     return "", history + [[user_message, None]]
 
@@ -48,20 +57,14 @@ def respond(message, chat_history):
     print(type(db))
     question = str(message)
     chain = openai_chain(inp_dir=dir)
-    # prompt = '''You are an AI assistant equipped with advanced analytical capabilities. 
-    # You have been provided with a carefully curated set of documents relevant to a specific question. 
-    # Your task is to meticulously analyze these documents and provide a comprehensive answer to the following question. 
-    # Ensure that your response is detailed, accurate, and maintains a formal, academic tone. 
-    # The information required to answer this question is contained within the documents. 
-    # Please proceed with a thorough examination to deliver a well-informed response. Question:  '''
-
-    # query = prompt + question
+
     query = question
 
     start_time = time.time()
 
     output = chain.get_response_from_drive(query=query, database=db, k=10, model_name=model_name, type=search_type)
     print(output)
+    
 
     # Update global variables to log
     time_diff = time.time() - start_time
@@ -72,7 +75,7 @@ def respond(message, chat_history):
     chat_history.append((message, bot_message))
 
     time.sleep(2)
-    return " ", chat_history
+    return " ", chat_history 
 
 def save_feedback(feedback):
     global user_feedback
@@ -85,9 +88,10 @@ def save_feedback(feedback):
         [input_question, model_response, model_name, time_diff, user_feedback]
     ]
     
-    if user_feedback[0] != "None":
+    if model_response and user_feedback[0] != "None":
         upload_chat_to_drive(log_data, file_name)
 
+
 def default_feedback():
     return "None"
 
@@ -112,25 +116,24 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="emerald", neutral_hue="slate"))
 
     global db
 
-    with gr.Row():
+    with gr.Row(equal_height=True):
         with gr.Column():
-            api_key_input = gr.Textbox(lines=1, label="Enter your OpenAI API Key, then press Enter...")
+            with gr.Row():
+                pdf_files_dnd = gr.File(file_count='multiple', height=250, label="Upload PDF Files")
 
-        with gr.Column():
-            drive_link_input = gr.Textbox(lines=1, label="Enter your shared drive link, then press Enter...")
 
-    with gr.Row():
-        process_files_input = gr.Button(value="Process files")   
+        with gr.Column():
+           with gr.Row():
+                drive_link_input = gr.Textbox(lines=1, label="Enter your shared drive link, then press Enter...")
+           with gr.Row():
+                status_message = gr.Text(label="Status", value="⬆️Submit a (shared) drive link containing only PDFs \n-or- \n⬅️Upload PDF files", text_align='center')
+            
 
-    with gr.Row():
-        status_message = gr.Text(label="Status", value="Click - Process Files")
+        
+        
 
-    
-    
-    api_key_input.submit(save_api_key, [api_key_input])
-    drive_link_input.submit(fn=save_drive_link, inputs=[drive_link_input])
-    drive_link_check = os.environ.get("DRIVE_LINK")
-    process_files_input.click(fn=create_data_from_drive, outputs=status_message)
+    drive_link_input.submit(fn=create_data_from_drive, inputs=[drive_link_input], outputs=[status_message])
+    pdf_files_dnd.change(fn=check_pdfs, inputs=[pdf_files_dnd], outputs=[status_message])
 
     chatbot = gr.Chatbot(height=750)
     msg = gr.Textbox(label="Send a message", placeholder="Send a message",
@@ -151,9 +154,8 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="emerald", neutral_hue="slate"))
             feedback_radio = gr.Radio(
                 choices=["1", "2", "3", "4", "5", "6", "None"],
                 value=["None"],
-                label="How would you rate the current response?",
-                info="Choosing a number sends the following diagnostic data to the developer - Question, Response, Time Taken. Let it be [None] to not send any data.",
-            )
+                label="On a scale from 1 (very unsatisfied) to 6 (very satisfied), how would you rate the current response?",
+                )
         
         with gr.Column():
             feedback_text = gr.Textbox(lines=1, label="Additional comments on the current response...")
@@ -161,7 +163,7 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="emerald", neutral_hue="slate"))
 
     msg.submit(respond, [msg, chatbot], [msg, chatbot])
     msg.submit(default_feedback, outputs=[feedback_radio])
-    msg.submit(default_text, outputs=[feedback_text])
+    chatbot.change(save_feedback, inputs=[feedback_radio])
 
     feedback_radio.change(
         fn=save_feedback,
@@ -173,8 +175,13 @@ with gr.Blocks(theme=gr.themes.Soft(primary_hue="emerald", neutral_hue="slate"))
         inputs=[feedback_text]
     )
 
+    feedback_text.submit(
+        fn=default_text,
+        outputs=[feedback_text]
+    )
+
     gr.HTML(description)
 
 
 chat.queue()
-chat.launch()
+chat.launch()

driveapi/drive_database.py

@@ -28,4 +28,4 @@ def create_chroma_db():
     print('Length of text: ' + str(len(raw_text)))
     db = FAISS.from_texts(texts, embedding)
 
-    return db
+    return db

driveapi/service.py

@@ -26,6 +26,3 @@ def get_shared_folder_id(drive_shared_link):
     shared_folder_id = str(drive_shared_link[start:end])
     
     return shared_folder_id
-
-
-

lc_base/dnd_database.py

@@ -0,0 +1,24 @@
+from driveapi.drive import process_pdf
+
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS 
+
+def create_dnd_database(file_list):
+    raw_text = ''
+    for pdf in file_list:
+        raw_text += process_pdf(pdf)
+
+    embedding = OpenAIEmbeddings()
+
+    text_splitter = CharacterTextSplitter(        
+            separator = "\n",
+            chunk_size = 1000,
+            chunk_overlap  = 200, 
+            length_function = len,
+        )
+    texts = text_splitter.split_text(raw_text)
+    print('Length of text: ' + str(len(raw_text)))
+    db = FAISS.from_texts(texts, embedding)
+    
+    return db

requirements.txt

@@ -1,10 +1,11 @@
 faiss-gpu==1.7.2
-gradio==3.45.0
+gradio==4.20.0
+pycryptodome==3.20.0
 tiktoken==0.5.1
 PyPDF2==3.0.1
 pandas==2.0.3
 openai==0.28.1
 langchain==0.0.331
-google-auth 
-google-auth-httplib2 
-google-api-python-client
+google-auth==2.28.1
+google-auth-httplib2==0.2.0
+google-api-python-client==2.120.0