submission-Emperor

.gitignore

@@ -0,0 +1 @@
+.vscode

.streamlit/credentials.json

@@ -0,0 +1,13 @@
+{
+    "type": "service_account",
+    "project_id": "sebi-hackathon-sheets-db",
+    "private_key_id": "56fc605149245f890e4d36df6a862918fd8bf870",
+    "private_key": "-----BEGIN PRIVATE KEY-----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\nHeDDLgogXN0T5a41yX9jAg==\n-----END PRIVATE KEY-----\n",
+    "client_email": "sebi-hackathon-service-acc@sebi-hackathon-sheets-db.iam.gserviceaccount.com",
+    "client_id": "111806018619958126515",
+    "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+    "token_uri": "https://oauth2.googleapis.com/token",
+    "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+    "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/sebi-hackathon-service-acc%40sebi-hackathon-sheets-db.iam.gserviceaccount.com",
+    "universe_domain": "googleapis.com"
+  }

.streamlit/sebi-hackathon-sheets-db-56fc60514924.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "sebi-hackathon-sheets-db",
+  "private_key_id": "56fc605149245f890e4d36df6a862918fd8bf870",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nHeDDLgogXN0T5a41yX9jAg==\n-----END PRIVATE KEY-----\n",
+  "client_email": "sebi-hackathon-service-acc@sebi-hackathon-sheets-db.iam.gserviceaccount.com",
+  "client_id": "111806018619958126515",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/sebi-hackathon-service-acc%40sebi-hackathon-sheets-db.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

.streamlit/secrets.toml

@@ -0,0 +1,17 @@
+# .streamlit/secrets.toml
+
+public_gsheets_url = "https://docs.google.com/spreadsheets/d/1w-zpQ66_hxtQfDlAidxmExSMBpUGGIAos9dvlRktk74/edit?usp=sharing"
+
+openai_apikey = "---- ENTER YOUR API KEY HERE -----"
+
+[gcp_service_account]
+type = "service_account"
+project_id = "sebi-hackathon-sheets-db"
+private_key_id = "56fc605149245f890e4d36df6a862918fd8bf870"
+private_key = "-----BEGIN PRIVATE KEY-----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\nHeDDLgogXN0T5a41yX9jAg==\n-----END PRIVATE KEY-----\n"
+client_email =  "sebi-hackathon-service-acc@sebi-hackathon-sheets-db.iam.gserviceaccount.com"
+client_id = "111806018619958126515"
+auth_uri = "https://accounts.google.com/o/oauth2/auth"
+token_uri = "https://oauth2.googleapis.com/token"
+auth_provider_x509_cert_url = "https://www.googleapis.com/oauth2/v1/certs"
+client_x509_cert_url = "https://www.googleapis.com/robot/v1/metadata/x509/sebi-hackathon-service-acc%40sebi-hackathon-sheets-db.iam.gserviceaccount.com"

.vscode/settings.json

@@ -0,0 +1,6 @@
+{
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter"
+    },
+    "python.formatting.provider": "none"
+}

01_homepage.py

@@ -0,0 +1,20 @@
+# Import necessary libraries
+import streamlit as st
+from streamlit_player import st_player
+
+st.set_page_config(
+    page_title="Smart With Sebi",
+    page_icon=":detective:",
+    layout="wide",
+)
+
+with st.columns(3)[1]:
+    st.image("media/smart_with_sebi.jpeg", width=200)
+
+st.markdown("<h2 style='text-align: center; color: black;'>Welcome to Smart with SEBI portal</h1>", unsafe_allow_html=True)
+
+st.markdown("<h3 style='text-align: left; color: black;'><hr> About this project:</h3>", unsafe_allow_html=True)
+
+st.sidebar.success("Select a page above!")
+
+st_player("https://www.youtube.com/watch?v=jNVTSDwTm14")

README.md

@@ -9,18 +9,69 @@
 
 ## README.md must consist of the following information:
 
-#### Team Name -
-#### Problem Statement - 
-#### Team Leader Email -
+#### Team Name - Emperor
+#### Problem Statement - Misleading Claim Detection & Content Curation
+#### Team Leader Email - [email protected]
+#### Project Demo Link: <https://www.youtube.com/watch?v=jNVTSDwTm14>
+#### Project hosted at: <https://sebi-misleading-claim-detection.streamlit.app/>
 
 ## A Brief of the Prototype:
-  This section must include UML Diagrams and prototype description
+  ![use_case](use_case.png)
+
+  Working:
+
+  1. There are two separate portals, one for common user which includes claim detection and educational content generation and other for SEBI personnel for claim detection and features like source reliability rating.
+
+  2. At-first any user inputs TEXT/AUDIO/VIDEO/IMAGE (currently only upload is supported, Web Scraping is reserved for future use-case) then the input is converted to text first.
+
+  3. The text prompt is passed through OpenAI's whisper-1 model with precise prompt to output whether is claim is misleading or not, and based on certain financial points, suppose the input is:
+        "Invest into company A, which is giving good returns."
+        Certain financial keywords: invest, returns are extracted and then based on these key words, videos from YouTube are suggested to the user.
+
+  4. **MOST IMPORTANT FEATURES for SEBI Personnel:** 
+
+      4.1. Based on the input claim, certain rules and regulations are also suggested based upon mapping from the financial concept to the SEBI rules and regulations database.\
+
+      4.2. A source reliability rating database in the form of Google Sheets is connected to the app so that whenever any claim is being judged, it is pushed to tha database (Google Sheet) and a score is marked for each claim type: -1 for MISLEADING and +1 for NOT MISLEADING, based on the cumulative scores a ranking is assigned and displayed.
+
+
 
 ## Tech Stack: 
-   List Down all technologies used to Build the prototype
+   Following technologies were used:\
+      1. Streamlit - for web-development\
+      2. HuggingFace - for sentiment analysis pipeline\
+      3. LangChain - For accessing OpenAI \
+      4. PyTesseract - for Optical Character Recognition\
+      5. pydub - for audio segmentation\
+      6. moviePy - for detaching audio from video\
+      7. GoogleSheets - for backend database
 
 ## Step-by-Step Code Execution Instructions:
-  This Section must contain a set of instructions required to clone and run the prototype so that it can be tested and deeply analyzed
+  1. clone the repository:
+        ```
+        git clone https://github.com/hindesh-akash/Empowering-Investors-Hackathon.git
+        ```
+
+  2. **IMPORTANT**:
+
+        -> Go to '.streamlit/secrets.toml' \
+        -> Enter your OpenAI api key in 'openai_apikey' variable \
+        -> save and exit
+  3. Open a new python terminal
+  4. Run the command:
+      ```
+      pip install -r requirements.txt
+      ```
+      ```
+      streamlit run 01_homepage.py
+      ```
+  5. Explore the app
+
 
 ## What I Learned:
-   Write about the biggest learning you had while developing the prototype
+   I learned about what problems are faced in real world by common people, money is the neccessity of human being, and a person invests his/her money in order to get positive returns so that they can make their living better.
+   And we as contributors can help them achieve the goal.\
+   I faced many challenges while developing the prototype, especially connecting with the database and APIs, but in the end when I see the application of this project in real world, I feel great motivation to develop a fully functional solution.
+
+   Thank you for this opportunity!
+

apikey.py

@@ -0,0 +1,25 @@
+import streamlit as st
+
+apikey = st.secrets['openai_apikey'] #Bobby key
+
+''
+
+'''NOTE:
+This is the API key for the OpenAI API. It is a secret key and should not be shared with anyone.
+The key provided here is my personal key for demonstration purposes only on a trial version of the API.
+Please do not misuse this key.
+
+
+IF THERE IS API KEY PROBLEM, you can enter your own API KEY here.
+Follow the steps:
+
+1. Go to www.openai.com
+2. Sign up for an account
+3. Go to your dashboard
+4. Click on the "Billing" tab
+5. Click on the "API Keys" tab
+6. Click on "Create new API key"
+7. Copy the key and paste it in the apikey variable above
+
+'''
+

new_app.py

@@ -0,0 +1,26 @@
+import streamlit as st
+
+import gspread
+from oauth2client.service_account import ServiceAccountCredentials
+
+# Authenticate with Google Sheets API
+scope = ["https://spreadsheets.google.com/feeds", "https://www.googleapis.com/auth/drive"]
+credentials = ServiceAccountCredentials.from_json_keyfile_name("credentials.json", scope)
+client = gspread.authorize(credentials)
+
+st.success("connection done")
+
+# Open the Google Sheet by its title
+sheet = client.open("sebi-hackathon-db")
+st.success("Sheet loaded")
+
+worksheet = sheet.get_worksheet(0)  # Assuming you want to work with the first worksheet
+st.success("Worksheet loaded")
+
+# # Define the data for the new row
+new_row_data = ["Value1", "Value2", "Value3","Val4","val5"]
+
+# # Append the new row to the worksheet
+worksheet.append_row(new_row_data)
+
+st.success("Row appended")

pages/02_user.py

@@ -0,0 +1,100 @@
+# --- IMPORT DEPENDENCIES -------------------------------+
+import sys
+import streamlit as st
+
+# setting path
+
+sys.path.append("../prompts")
+sys.path.append("../utils")
+
+from prompts import *
+from utils import *
+from streamlit_option_menu import option_menu
+
+
+# --- TITLE --------------------------------------------+
+with st.columns(3)[1]:
+    st.image("media/smart_with_sebi.jpeg", width=200)
+
+st.markdown("<h2 style='text-align: center; color: black;'> USER PORTAL<hr></h2>", unsafe_allow_html=True)
+
+
+# --- OPTION MENU --------------------------------------+
+selected = option_menu(
+    menu_title=None,
+    options=["TEXT", "AUDIO", "VIDEO", "IMAGE", "QnA"],
+    icons=["card-text", "volume-up", "camera-reels", "image", "question-circle"],
+    menu_icon="cast",
+    orientation="horizontal",
+    styles={
+        "container": {"padding": "0!important", "background-color": "#fafafa"},
+        "icon": {"color": "orange", "font-size": "25px"}, 
+        "nav-link": {"font-size": "20px", "text-align": "left", "margin":"0px", "--hover-color": "#eee"},
+        "nav-link-selected": {"background-color": "indigo"},
+    },
+)
+
+# Main content based on user's selected
+if selected == "TEXT":
+    st.write("**TEXT BASED CLAIM DETECTION:**\n\n")
+    prompt = st.text_area("User Input")
+
+    if st.button("Submit") and prompt:
+        claim_detection_pipeline(prompt)
+        financial_points = financial_point_extractor(prompt)
+        display_video_links(financial_points)
+        # display_articles(financial_points)
+
+
+if selected == "AUDIO":
+    st.write("**AUDIO BASED CLAIM DETECTION:**")
+    audio_file = st.file_uploader("Upload an audio file", type=["ogg", "mp3", "wav"])
+
+    if audio_file:
+        st.audio(audio_file, format="audio/ogg", start_time=0)
+        transcript = transcribe_audio(audio_file)
+        prompt = st.text_area("Transcribed User Input", value=transcript)
+        if st.button("Submit") and prompt:
+            claim_detection_pipeline(prompt)
+            financial_points = financial_point_extractor(prompt)
+            display_video_links(financial_points)
+
+
+if selected == "IMAGE":
+    st.write("**IMAGE BASED CLAIM DETECTION:**")
+    image_file = st.file_uploader("Upload an image file", type=["png", "jpg", "jpeg"])
+
+    if image_file:
+        st.image(
+            image_file, caption="Uploaded Image.", use_column_width=True, width=300
+        )
+        text_from_image = get_text_from_image(image_file)
+        prompt = st.text_area("User input image to text:", value=text_from_image)
+
+        if st.button("Submit") and prompt:
+            claim_detection_pipeline(prompt)
+            financial_points = financial_point_extractor(prompt)
+            display_video_links(financial_points)
+
+if selected == "QnA":
+    st.write("**Question - Answering**")
+    prompt = st.text_area("User Input")
+
+    if st.button("Submit") and prompt:
+        question_and_answer(prompt)
+
+if selected == "VIDEO":
+        st.write("**VIDEO BASED CLAIM DETECTION:**")
+        video_file = st.file_uploader("Upload a video file", type=["mp4", "mov", "avi"])
+
+        if video_file:
+            st.video(video_file, start_time=0)
+            #----------------------------------------
+            transcript = video_to_text(video_file)
+            #----------------------------------------
+            prompt = st.text_area("Transcribed User Input", value=transcript)
+
+            if st.button("Submit") and prompt:
+                claim_detection_pipeline(prompt)
+                financial_points = financial_point_extractor(prompt)
+                display_video_links(financial_points)