Merge pull request #98 from vanderbilt-data-science/hf-struggle

app.py

@@ -1,20 +1,29 @@
 import streamlit as st
 import streamlit_authenticator as stauth
-import sqlite3
+from deta import Deta
 import yaml
 from yaml.loader import SafeLoader
 import os
+from cryptography.fernet import Fernet
 
 from free_speech_app.DataLoadDb import *
 from free_speech_app.FreeSpeechPromptsResponses import *
 from langchain.chat_models import ChatOpenAI
 
-# Connect to SQLite database
-conn = sqlite3.connect('user_data.db')
+#connect to/create Deta user database
+deta = Deta(st.secrets["deta_key"])
+db = deta.Base("user_data")
 
-# Load the configuration file
-with open('config.yaml') as file:
-    config = yaml.load(file, Loader=SafeLoader)
+#fernet key (generated locally, stored in streamlit secrets)
+fernet = Fernet(bytes(st.secrets["fernet_key"],'utf-8'))
+
+#activeloop_token
+os.environ["ACTIVELOOP_TOKEN"] = st.secrets["deeplake_key"]
+
+config_drive = deta.Drive("passwords")
+config = config_drive.get("config.yaml").read()
+
+config = yaml.load(config, Loader=SafeLoader)
 
 # Create an authenticator
 authenticator = stauth.Authenticate(
@@ -25,25 +34,23 @@ authenticator = stauth.Authenticate(
     config['preauthorized']
 )
 
-# Render the login module
-name, authentication_status, username = authenticator.login('Login', 'main')
+def get_user_data(user):
+    data = db.fetch().items
+    for person in data:
+        if person['key'] == user:
+            return person
+    return None
 
-# Create table for user data if it doesn't exist
-conn.execute('''CREATE TABLE IF NOT EXISTS user_data
-                (username TEXT PRIMARY KEY,
-                 principles TEXT,
-                 writing_style TEXT,
-                 sources TEXT)''')
+def encrypt(api_key: str, fernet) -> bytes:
+    """Encrypt the API key."""
+    return fernet.encrypt(api_key.encode())
 
-def get_user_data(user):
-    cursor = conn.cursor()
-    cursor.execute("SELECT * FROM user_data WHERE username = ?", (user,))
-    data = cursor.fetchone()
-    return data
+def decrypt(encrypted_api_key: bytes, fernet) -> str:
+    """Decrypt the encrypted API key."""
+    return fernet.decrypt(encrypted_api_key).decode()
 
-def update_user_data(user, principles, writing_style, sources):
-    conn.execute("INSERT OR REPLACE INTO user_data VALUES (?, ?, ?, ?)", (user, principles, writing_style, sources))
-    conn.commit()
+# Render the login module
+name, authentication_status, username = authenticator.login('Login', 'main')
 
 # If the user is authenticated
 if authentication_status:
@@ -51,51 +58,157 @@ if authentication_status:
     st.write(f'Welcome *{name}*')
 
     # Sidebar for navigation
-    page = st.sidebar.selectbox("Choose a page", ["Main screen", "Principles and sources"])
+    page = st.sidebar.radio("Choose a page", ["OpenAI API Key Setup", "Account Setup", "Respond to Post"])
 
     # Fetch user data from the database
     user_data = get_user_data(username)
 
-    if page == "Main screen":
-        st.title("Main Screen")
+    if page == "Account Setup":
+
+        st.title("Account Setup")
+        st.markdown("Please use this page to provide your OpenAI API Key, Principles and Writing Style. **Please make sure to press the Save Changes button after providing the information.**")
         
-        # Input boxes
-        api_input = st.text_input("OpenAI API Token")
-        original_post = st.text_input("Paste Original Post Here")
-        background_info = st.text_input("Background information on original post (references, relevant information, best practices for responding)")
+    
+        # Input boxes with existing data
+    
+        if 'api_key' not in st.session_state:
+            st.session_state.api_key = ""
+        api_input = st.text_input("OpenAI API Key", value=decrypt(user_data["api_key"].encode()[2:-1], fernet) if user_data and "api_key" in user_data else "", type="password")
+        encrypted_api_key = str(encrypt(api_input, fernet))
+        st.session_state.api_key = api_input
         
-        chat_mdl = None
-        draft_response = ''
-
-        # Check if the "Submit" button is clicked
-        if st.button("Submit"):
-            if api_input:
-                os.environ["OPENAI_API_KEY"] = api_input
-                chat_mdl = ChatOpenAI(model_name = 'gpt-3.5-turbo-16k', temperature=0.1)
+        principles = st.text_input("My Principles", placeholder = "Enter the main principles of your life you wish this response to uphold", value=user_data["principles"] if user_data and "principles" in user_data else "")
+        writing_style = st.text_input("My Writing Style (Paste Examples)", placeholder = "Provide examples of your writing style here", value=user_data["writing_style"] if user_data and "writing_style" in user_data else "")
+        sources = st.text_input("Sources (Provide all sources you would like to use)", value=st.session_state.sources if 'sources' in st.session_state else '', key = 'sources_key')
     
-            if chat_mdl is not None:
-                if user_data is None:
-                    draft_response = generate_custom_response(original_post, chat_mdl, background_info, "", "", "").content
-                else:
-                    draft_response = generate_custom_response(original_post, chat_mdl, background_info, user_data[1], user_data[2], user_data[3]).content
-            
-        # Output from function
-        st.text_area(label="Draft Response. Please edit here or prompt suggestions in the box below.", value=draft_response, height=350)
+        # Update button
+        if st.button("Save Changes"):
+            db.put({"key": username, "principles": principles, "writing_style": writing_style, "sources": sources, "api_key": encrypted_api_key})
+        
+    if page == "OpenAI API Key Setup":
+        st.title("OpenAI API Key Setup")
 
-        regenerate_prompt = st.text_input("Additional prompting for regenerating draft response")
+        st.header('What is an API key?')
+        st.write('An API (Application Programming Interface) key is like a password that allows you to access certain functions or data from a website or service. Many sites use API keys to identify you and control access to their APIs.')
 
-    elif page == "Principles and sources":
-        st.title("Principles and Sources")
+        st.header('Why do you need an API key?')
+        st.write('API keys allow sites to track usage and prevent abuse of their services. They help keep things secure. When you request an API key, the site knows the calls are coming from you.')
 
-        # Input boxes with existing data
-        principles = st.text_input("My Principles", value=user_data[1] if user_data else "")
-        writing_style = st.text_input("My Writing Style (Paste Examples)", value=user_data[2] if user_data else "")
-        sources = st.text_input("Sources (Provide all sources you would like to use)", value=user_data[3] if user_data else "")
+        image = 'free_speech_app/apikeyex.png'
+        st.header('How to get an OpenAI API key:')
+        st.write('1. Go to https://platform.openai.com/account/api-keys') 
+        st.write('2. Log in or create an OpenAI account if you do not have one')
+        st.write('3. Click "Create new secret key" and give your key a name')
+        st.image(image, caption=None, width=None, use_column_width=None, clamp=False, channels="RGB", output_format="auto")
+        st.write('4. Copy the generated API key and keep it private like a password')
 
-        # Update button
-        if st.button("Update"):
-            update_user_data(username, principles, writing_style, sources)
+        st.header('Using your API key')
+        st.write('When making calls to the OpenAI API, include your API key in the request headers or parameters to authenticate.')
+        st.code('headers = {"Authorization": f"Bearer {YOUR_API_KEY}"}')
+
+        st.warning('Treat your API key like a secret! Do not share it publicly.')
+
+
+    elif page == "Respond to Post":
+        st.title("Respond to Post")
+        
+        left_col, right_col = st.columns(2)
+        
+        # Input boxes
 
+        with right_col: 
+            background_info = st.text_area("Background information on original post (references, relevant information, best practices for responding)", height = 700, value=st.session_state.background_info if 'background_info' in st.session_state else '', key = 'background_info_key')
+
+        with left_col:
+            original_post = st.text_area("Paste Original Post Here \n", height=100)
+            
+            chat_mdl = None
+            draft_response = ''
+    
+            # Check if the "Submit" button is clicked
+            if st.button("Submit"):
+                if st.session_state.api_key:
+                    os.environ["OPENAI_API_KEY"] = st.session_state.api_key
+                    # add condition to check for passphrase to allow use of DSI api key stored in secrets
+                    if (os.environ["OPENAI_API_KEY"] == st.secrets["secret_passphrase"]):
+                        os.environ["OPENAI_API_KEY"] = st.secrets["dsi_openai_key"]
+                    chat_mdl = ChatOpenAI(model_name='gpt-4', temperature=0.1)
+        
+                if chat_mdl is not None:
+                    if user_data is None:
+                        draft_response, background_text, sources_text = generate_custom_response(original_post, chat_mdl, "", "")
+                        st.session_state.draft_response = draft_response.content
+                        st.session_state.background_text = background_text
+                        st.session_state.sources_text = sources_text
+                        st.session_state.background_info = background_text
+                        st.session_state.sources = sources_text
+                        st.rerun()
+                    else:
+                        draft_response, background_text, sources_text = generate_custom_response(original_post, chat_mdl, user_data['principles'], user_data['writing_style'])
+                        st.session_state.draft_response = draft_response.content
+                        st.session_state.background_text = background_text
+                        st.session_state.sources_text = sources_text
+                        st.session_state.background_info = background_text
+                        st.session_state.sources = sources_text
+                        st.rerun()
+                        
+            
+            # Ensure session state variables are initialized
+            if 'draft_response' not in st.session_state:
+                st.session_state.draft_response = ''
+            if 'regenerate_prompt' not in st.session_state:
+                st.session_state.regenerate_prompt = ''
+            
+            # Output from function
+            response_textarea = st.text_area(
+                label="Draft Response. Please edit here or prompt suggestions in the box below.",
+                value=st.session_state.draft_response if 'draft_response' in st.session_state else '',
+                height=350,
+                key='draft_response_key'
+            )
+                        
+            # Initialization of the regeneration flag
+            if 'is_regenerating' not in st.session_state:
+                st.session_state.is_regenerating = False
+            
+            # Check if the app is in the "regeneration" phase
+            if st.session_state.is_regenerating:
+                # Display the regenerated response explicitly
+                regenerate_prompt = st.text_area(
+                    "Request a new draft",
+                    value=st.session_state.regenerate_prompt,
+                    placeholder="You may edit the regenerated draft directly above, or request further changes here.",
+                    height=100,
+                    key='regenerate_prompt_key'
+                )
+                # Reset the regeneration flag
+                st.session_state.is_regenerating = False
+            else:
+                # Normal behavior: display the text area for manual input
+                regenerate_prompt = st.text_area(
+                    "Request a new draft",
+                    placeholder="You may edit the draft directly above, or request a new draft with additional guidance here.",
+                    height=100,
+                    key='regenerate_prompt_key'
+                )
+
+            if (draft_response is not None) and (regenerate_prompt is not None):
+                if st.button("Regenerate"):
+                    if st.session_state.api_key:
+                        os.environ['OPENAI_API_KEY'] = st.session_state.api_key
+                        # add condition to check for passphrase to allow use of DSI api key stored in secrets
+                        if (os.environ["OPENAI_API_KEY"] == st.secrets["secret_passphrase"]):
+                            os.environ["OPENAI_API_KEY"] = st.secrets["dsi_openai_key"]
+                        chat_mdl = ChatOpenAI(model_name='gpt-4', temperature=0.1)
+                    
+                    if chat_mdl is not None:
+                        updated_response = regenerate_custom_response(chat_mdl, regenerate_prompt, st.session_state.draft_response).content    
+                        st.session_state.regenerate_prompt = updated_response
+                        st.session_state.is_regenerating = True
+
+                    st.rerun()
+                        
+                
 elif authentication_status is False:
     st.error('Username/password is incorrect')
 
@@ -103,10 +216,12 @@ elif authentication_status is None:
     st.warning('Please enter your username and password')
     
     try:
-        if authenticator.register_user('Register user', preauthorization=False):
-            st.success('User registered successfully')
+        if authenticator.register_user('New User Registration', preauthorization=False):
+            st.success('User Registered Successfully! Please log in above.')
     except Exception as e:
         st.error(e)
 
 with open('config.yaml', 'w') as file:
     yaml.dump(config, file, default_flow_style=False)
+
+config_drive.put("config.yaml", path = "config.yaml")

free_speech_app/DataLoadDb.py

@@ -1,9 +1,9 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/free-speech-stores.ipynb.
 
 # %% auto 0
-__all__ = ['setup_openai_api_key', 'is_google_colab', 'upload_docs', 'setup_db']
+__all__ = ['setup_openai_api_key', 'setup_db']
 
-# %% ../nbs/free-speech-stores.ipynb 5
+# %% ../nbs/free-speech-stores.ipynb 4
 # libraries required for functionality
 import os
 from getpass import getpass
@@ -17,49 +17,23 @@ from langchain.text_splitter import CharacterTextSplitter
 from langchain.embeddings import OpenAIEmbeddings
 from langchain.vectorstores import Chroma
 
-# %% ../nbs/free-speech-stores.ipynb 9
+# %% ../nbs/free-speech-stores.ipynb 12
 def setup_openai_api_key():
     openai_api_key = getpass()
     os.environ["OPENAI_API_KEY"] = openai_api_key
 
-# %% ../nbs/free-speech-stores.ipynb 12
+# %% ../nbs/free-speech-stores.ipynb 15
 import nltk
 nltk.download('averaged_perceptron_tagger')
 
-# %% ../nbs/free-speech-stores.ipynb 13
-def is_google_colab():
-  try:
-    from google.colab import files
-    return True
-  except:
-    return False
-
-def upload_docs():
-  
-  if not is_google_colab():
-    raise ModuleNotFoundError('This function only works in Google Colab; local functionality not currently supported.')
-  
-  # upload files if google colab
-  from google.colab import files
-  uploaded = files.upload()
-  file_list = []
-
-  for name, data in uploaded.items():
-    with open(name, 'wb') as f:
-      f.write(data)
-    print('saved file', name)
-    file_list.append(name)
-  return file_list
-
-
-# %% ../nbs/free-speech-stores.ipynb 22
-def setup_db(list_of_files, chunk_size=1000, chunk_overlap=5):
-  # set path to files
-  #paths = ["https://github.com/vanderbilt-data-science/free-speech-app/raw/9818f87679a82769ab6f90dba00801447b6e952c/response-resources/2307.04761_Understanding_counterspeech.pdf", "https://github.com/vanderbilt-data-science/free-speech-app/raw/main/response-resources/campaigns.docx", "https://github.com/vanderbilt-data-science/free-speech-app/raw/9818f87679a82769ab6f90dba00801447b6e952c/response-resources/samples.pdf"]
+# %% ../nbs/free-speech-stores.ipynb 27
+def setup_db(local_path, hub_path, chunk_size=1000, chunk_overlap=5):
+  file_list = os.listdir(local_path)
 
   # set up loaders
   loaders_list = []
-  for file_path in list_of_files:
+  for file_path in file_list:
+    file_path = local_path + file_path
     loaders_list.append(UnstructuredFileLoader(file_path))
 
   loader_all = MergedDataLoader(loaders=[loader for loader in loaders_list])
@@ -70,7 +44,7 @@ def setup_db(list_of_files, chunk_size=1000, chunk_overlap=5):
   texts = text_splitter.split_documents(documents)
   embeddings = OpenAIEmbeddings()
 
-  # store docs in db
-  db = Chroma.from_documents(texts, embeddings)
+  # Replace dataset path with relevant dataset name - counterspeech-resources or hatespeech-background
+  db = DeepLake.from_documents(texts, dataset_path=hub_path, embedding=embeddings, overwrite=True)
 
-  return db
+  return

free_speech_app/FreeSpeechPromptsResponses.py

@@ -1,17 +1,20 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/free-speech-prompts.ipynb.
 
 # %% auto 0
-__all__ = ['DEFAULT_PROMPT_TEMPLATE_TEXT', 'DEFAULT_PROMPT_TEMPLATE', 'generate_custom_prompt', 'get_chat_model_response',
-           'generate_custom_response']
+__all__ = ['DEAFULT_PROMPT_TEMPLATE_TEXT', 'query_retriever', 'generate_custom_prompt', 'get_chat_model_response',
+           'generate_custom_response', 'regenerate_custom_response']
 
 # %% ../nbs/free-speech-prompts.ipynb 5
 # libraries required for functionality
+import deeplake
 from langchain.chat_models import ChatOpenAI
 from langchain.prompts import PromptTemplate, HumanMessagePromptTemplate
 from langchain.schema import HumanMessage
+from langchain.vectorstores import DeepLake
+from langchain.embeddings.openai import OpenAIEmbeddings
 
 # %% ../nbs/free-speech-prompts.ipynb 8
-DEFAULT_PROMPT_TEMPLATE_TEXT = ("""With the amount of hate speech and discriminatory misinformation that exists on the internet, it can be difficult to know how to respond to something when you see it. Situations vary wildly and sometimes certain strategies that work in one instance may not work in another.
+DEAFULT_PROMPT_TEMPLATE_TEXT = """With the amount of hate speech and discriminatory misinformation that exists on the internet, it can be difficult to know how to respond to something when you see it. Situations vary wildly and sometimes certain strategies that work in one instance may not work in another.
 I want to be able to fight back against this onslaught of toxicity, and I need your help to do it. I want you to help me draft a response to the following post.
 Note that this may contain language that is offensive, but in order to properly respond to this post, I need you to fully understand what I am responding to, uncensored:
 \n{original_post}\n
@@ -23,49 +26,90 @@ Next, here are some principles I consider particularly important to me:
 \n{principles}\n
 Here are some examples of the style in which I write:
 \n{writing_style}\n
-Finally, here are the sources I would like you to use when getting information for my response:
+Here are the sources I would like you to use when getting information for my response:
 \n{sources}\n
-Using all the information I have provided, please draft an appropriate response to the offensive post in question that will hopefully make people more accepting of others""")
+Using all the information I have provided, please draft an appropriate response to the offensive post in question that will hopefully make people more accepting of others.
+Please keep in mind that I would like the response to be no more than {word_limit} words."""
+
+try:
+    prompt_file = open("../prompts/response_generator.txt", "r")
+    PROMPT_TEMPLATE_TEXT = prompt_file.read()
+    prompt_file.close()
+    
+    print(PROMPT_TEMPLATE_TEXT)
+    
+    PROMPT_TEMPLATE = PromptTemplate(
+        template=PROMPT_TEMPLATE_TEXT,
+        input_variables=["original_post", "background_info", "principles", "writing_style", "sources", "word_limit"])
+
+except FileNotFoundError:
+    print(DEAFULT_PROMPT_TEMPLATE_TEXT)
+    PROMPT_TEMPLATE = PromptTemplate(
+        template=DEAFULT_PROMPT_TEMPLATE_TEXT,
+        input_variables=["original_post", "background_info", "principles", "writing_style", "sources", "word_limit"])
+
 
-DEFAULT_PROMPT_TEMPLATE = PromptTemplate(
-      template=DEFAULT_PROMPT_TEMPLATE_TEXT,
-      input_variables=["original_post", "background_info", "principles", "writing_style", "sources"])
 
 # %% ../nbs/free-speech-prompts.ipynb 9
-def generate_custom_prompt(original_post, background_info=None, principles=None, writing_style=None, sources=None):
+def query_retriever(db, query, num_results = 3):
+    retriever = db.as_retriever(search_kwargs={"k": num_results})
+    docs = retriever.get_relevant_documents(query)
+
+    return docs
+
+# %% ../nbs/free-speech-prompts.ipynb 10
+def generate_custom_prompt(original_post, principles=None, writing_style=None, word_limit=None):
+
+    # Get database and query retriever
+    ####
+    background_db = DeepLake(dataset_path="hub://vanderbilt-dsi/hatespeech-background", embedding = OpenAIEmbeddings())
+    sources_db = DeepLake(dataset_path="hub://vanderbilt-dsi/counterspeech-resources", embedding = OpenAIEmbeddings())
 
     # Use defaults in the case of None
-    if background_info is None:
-        background_info = "There is no necessary additional context."
     
     if principles is None:
         principles="There are no principles which I consider more important to me than the average person might."
     
     if writing_style is None:
         writing_style="I have no examples of my writing style."
-    
-    if sources is None:
-        sources="There are no particular sources that I would like you to use."
+
+    if word_limit is None:
+        word_limit="an infinite amount of"
+
+    retriever_query = original_post
+    background_info = query_retriever(background_db, retriever_query)
+    sources = query_retriever(sources_db, retriever_query)
 
     # Fill the prompt
-    filled_prompt = DEFAULT_PROMPT_TEMPLATE.format(original_post=original_post, background_info=background_info, principles=principles, writing_style=writing_style, sources=sources)
+    filled_prompt = PROMPT_TEMPLATE.format(original_post=original_post, background_info=background_info, principles=principles, writing_style=writing_style, sources=sources, word_limit=word_limit)
 
-    return filled_prompt
+    return filled_prompt, background_info, sources
 
-# %% ../nbs/free-speech-prompts.ipynb 10
+# %% ../nbs/free-speech-prompts.ipynb 11
 def get_chat_model_response(mdl, input_prompt):
 
     messages = [HumanMessage(content=input_prompt)]
 
     return mdl(messages)
 
-# %% ../nbs/free-speech-prompts.ipynb 11
-def generate_custom_response(original_post, chat_mdl, background_info=None, principles=None, writing_style=None, sources=None):
+# %% ../nbs/free-speech-prompts.ipynb 12
+def generate_custom_response(original_post, chat_mdl, principles=None, writing_style=None, word_limit=None):
 
     # create customized prompt
-    customized_prompt = generate_custom_prompt(original_post, background_info, principles, writing_style, sources)
+    customized_prompt, background_info, sources = generate_custom_prompt(original_post, principles, writing_style, word_limit)
 
     # get response
     draft_response = get_chat_model_response(chat_mdl, customized_prompt)
 
-    return draft_response
+    return draft_response, background_info, sources
+
+# %% ../nbs/free-speech-prompts.ipynb 13
+def regenerate_custom_response(chat_mdl, regenerate_prompt, draft_response):
+
+    # create customized prompt
+    customized_prompt = f"Please update the original response according to the following request. {regenerate_prompt}. Here is the original response: {draft_response}"
+
+    # get response
+    updated_response = get_chat_model_response(chat_mdl, customized_prompt)
+
+    return updated_response

requirements.txt

@@ -1,11 +1,12 @@
 streamlit
-sqlite3
-yaml
+streamlit-authenticator
+deeplake
+deta
+cryptography
+pyyaml
 langchain
 openai
 chromadb
 tiktoken
 unstructured
-getpass
 nltk
-free_speech_app @ git+https://github.com/vanderbilt-data-science/free-speech-app.git