Merge branch 'recodehive:main' into main

Author: Vishisht16

Algorithms and Deep Learning Models/Beyond-GPS-Navi-Bot/README.md

@@ -0,0 +1,36 @@
+# NaviBot-Voice-Assistant
+
+To get started with NaviBot-Voice-Assistant, follow these steps:
+
+1. Navigate to the project directory:
+
+    ```bash
+    cd NaviBot-Voice-Assistant
+    ```
+
+3. Activating venv (optional) 
+
+    ```bash
+    conda create -n venv python=3.10+
+    conda activate venv
+    ```
+
+4. Install dependencies:
+
+    ```python
+    pip install -r requirements.txt
+    ```
+
+5. Configure environment variables
+    ```
+    Rename `.env-sample` to `.env` file
+    Replace the API your Google API Key, 
+    ```
+    Kindly follow refer to this site for getting [your own key](https://ai.google.dev/tutorials/setup)
+    <br/>
+
+6. Run the chatbot:
+
+    ```bash
+    streamlit run app.py
+    ```

Algorithms and Deep Learning Models/Beyond-GPS-Navi-Bot/app.py

@@ -0,0 +1,133 @@
+import streamlit as st
+import pyttsx3
+import speech_recognition as sr
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+import os
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+import google.generativeai as genai
+from langchain_community.vectorstores import FAISS
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+from dotenv import load_dotenv
+
+load_dotenv()
+os.getenv("GOOGLE_API_KEY")
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+# Initialize pyttsx3 for voice output
+engine = pyttsx3.init()
+
+# Function to speak the text
+def speak(text):
+    engine.say(text)
+    engine.runAndWait()
+
+# Function to listen to voice input
+def listen():
+    r = sr.Recognizer()
+    with sr.Microphone() as source:
+        st.write("Listening...")
+        r.adjust_for_ambient_noise(source)
+        audio = r.listen(source)
+    
+    try:
+        user_input = r.recognize_google(audio)
+        st.write(f"You said: {user_input}")
+        return user_input
+    except sr.UnknownValueError:
+        st.write("Sorry, I could not understand what you said.")
+        return None
+    except sr.RequestError as e:
+        st.write(f"Could not request results from Google Speech Recognition service; {e}")
+        return None
+
+
+def get_pdf_text(pdf_docs):
+    text=""
+    for pdf in pdf_docs:
+        pdf_reader= PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text+= page.extract_text()
+    return  text
+
+
+def get_text_chunks(text):
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+
+def get_vector_store(text_chunks):
+    embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
+    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
+    vector_store.save_local("faiss_index")
+
+
+def get_conversational_chain():
+
+    prompt_template = """
+    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
+    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
+    Context:\n {context}?\n
+    Question: \n{question}\n
+
+    Answer:
+    """
+
+    model = ChatGoogleGenerativeAI(model="gemini-pro",
+                             temperature=0.3)
+
+    prompt = PromptTemplate(template = prompt_template, input_variables = ["context", "question"])
+    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+
+    return chain
+
+
+def user_input(user_question):
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+
+    # Load the local FAISS index with dangerous deserialization allowed
+    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+    docs = new_db.similarity_search(user_question)
+
+    chain = get_conversational_chain()
+
+    response = chain(
+        {"input_documents": docs, "question": user_question},
+        return_only_outputs=True
+    )
+
+    speak(response["output_text"])  # Speak the response
+    st.write("Reply: ", response["output_text"])
+
+
+def main():
+    st.set_page_config("Beyond GPS Navigation")
+    st.header("Beyond GPS Navigator for Blind")
+
+    user_question = st.text_input("Ask your query")
+    voice_input_button = st.button("Voice Input")
+
+    if voice_input_button:
+        user_question = listen()  # Listen to voice input
+        if user_question:
+            user_input(user_question)
+
+    if user_question:
+        user_input(user_question)
+
+    with st.sidebar:
+        st.title("Menu:")
+        pdf_docs = st.file_uploader("Upload your route data and Click on the Submit & Process Button", accept_multiple_files=True)
+        if st.button("Submit & Process"):
+            with st.spinner("Processing..."):
+                raw_text = get_pdf_text(pdf_docs)
+                text_chunks = get_text_chunks(raw_text)
+                get_vector_store(text_chunks)
+                st.success("Done")
+
+
+if __name__ == "__main__":
+    main()

Algorithms and Deep Learning Models/Beyond-GPS-Navi-Bot/main.py

@@ -0,0 +1,88 @@
+import os
+import streamlit as st
+from dotenv import load_dotenv
+import google.generativeai as gen_ai
+import speech_recognition as sr
+from gtts import gTTS
+from tempfile import TemporaryFile
+
+# Load environment variables
+load_dotenv()
+
+# Configure Streamlit page settings
+st.set_page_config(
+    page_title="Chat with Gemini-Pro!",
+    page_icon=":brain:",  # Favicon emoji
+    layout="centered",  # Page layout option
+)
+
+GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+
+# Set up Google Gemini-Pro AI model
+gen_ai.configure(api_key=GOOGLE_API_KEY)
+model = gen_ai.GenerativeModel('gemini-pro')
+
+# Function to translate roles between Gemini-Pro and Streamlit terminology
+def translate_role_for_streamlit(user_role):
+    if user_role == "model":
+        return "assistant"
+    else:
+        return user_role
+
+# Function to recognize speech input
+def recognize_speech():
+    r = sr.Recognizer()
+    with sr.Microphone() as source:
+        st.write("Speak now...")
+        audio = r.listen(source)
+
+    try:
+        user_prompt = r.recognize_google(audio)
+        st.write("You said:", user_prompt)
+        return user_prompt
+    except sr.UnknownValueError:
+        st.write("Sorry, I could not understand your audio.")
+        return ""
+    except sr.RequestError as e:
+        st.write("Could not request results from Google Speech Recognition service; {0}".format(e))
+        return ""
+
+# Function to output voice
+def speak(text):
+    tts = gTTS(text=text, lang='en')
+    with TemporaryFile(suffix=".wav", delete=False) as f:
+        tts.write_to_fp(f)
+        filename = f.name
+    st.audio(filename, format='audio/wav')
+
+
+# Initialize chat session in Streamlit if not already present
+if "chat_session" not in st.session_state:
+    st.session_state.chat_session = model.start_chat(history=[])
+
+# Display the chatbot's title on the page
+st.title("🤖 Gemini Pro - ChatBot")
+
+# Display the chat history
+for message in st.session_state.chat_session.history:
+    with st.chat_message(translate_role_for_streamlit(message.role)):
+        st.markdown(message.parts[0].text)
+
+# Input field for user's message
+voice_input = st.checkbox("Voice Input")
+if voice_input:
+    user_prompt = recognize_speech()
+else:
+    user_prompt = st.text_input("Ask Gemini-Pro...")
+
+if user_prompt:
+    # Add user's message to chat and display it
+    st.chat_message("user").markdown(user_prompt)
+
+    # Send user's message to Gemini-Pro and get the response
+    gemini_response = st.session_state.chat_session.send_message(user_prompt)
+
+    # Display Gemini-Pro's response
+    with st.chat_message("assistant"):
+        st.markdown(gemini_response.text)
+        speak(gemini_response.text)

Algorithms and Deep Learning Models/Beyond-GPS-Navi-Bot/map.py

@@ -0,0 +1,99 @@
+import os
+import streamlit as st
+from dotenv import load_dotenv
+import google.generativeai as gen_ai
+import speech_recognition as sr
+from gtts import gTTS
+from tempfile import TemporaryFile
+import webbrowser
+
+# Load environment variables
+load_dotenv()
+
+# Configure Streamlit page settings
+st.set_page_config(
+    page_title="Beyond GPS Navigator!",
+    page_icon=":brain:",  # Favicon emoji
+    layout="centered",  # Page layout option
+)
+
+GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+
+# Set up Google Gemini-Pro AI model
+gen_ai.configure(api_key=GOOGLE_API_KEY)
+model = gen_ai.GenerativeModel('gemini-pro')
+
+# Function to translate roles between Gemini-Pro and Streamlit terminology
+def translate_role_for_streamlit(user_role):
+    if user_role == "model":
+        return "assistant"
+    else:
+        return user_role
+
+# Function to recognize speech input
+def recognize_speech():
+    r = sr.Recognizer()
+    with sr.Microphone() as source:
+        st.write("Speak now...")
+        audio = r.listen(source)
+
+    try:
+        user_prompt = r.recognize_google(audio)
+        st.write("You said:", user_prompt)
+        return user_prompt
+    except sr.UnknownValueError:
+        st.write("Sorry, I could not understand your audio.")
+        return ""
+    except sr.RequestError as e:
+        st.write("Could not request results from Google Speech Recognition service; {0}".format(e))
+        return ""
+
+# Function to output voice
+def speak(text):
+    tts = gTTS(text=text, lang='en')
+    with TemporaryFile(suffix=".wav", delete=False) as f:
+        tts.write_to_fp(f)
+        filename = f.name
+    st.audio(filename, format='audio/wav')
+
+# Get user's current location
+current_location = st.text_input("What is your current location?")
+
+# Ask the user for their destination
+destination = recognize_speech()
+
+# Initialize chat session in Streamlit if not already present
+if "chat_session" not in st.session_state:
+    st.session_state.chat_session = model.start_chat(history=[])
+
+# Display the chatbot's title on the page
+st.title("🤖 Gemini Pro - ChatBot")
+
+# Display the chat history
+for message in st.session_state.chat_session.history:
+    with st.chat_message(translate_role_for_streamlit(message.role)):
+        st.markdown(message.parts[0].text)
+
+# Input field for user's message
+voice_input = st.checkbox("Voice Input")
+if voice_input:
+    user_prompt = recognize_speech()
+else:
+    user_prompt = st.text_input("Ask Gemini-Pro...")
+
+if user_prompt:
+    # Add user's message to chat and display it
+    st.chat_message("user").markdown(user_prompt)
+
+    # Send user's message to Gemini-Pro and get the response
+    gemini_response = st.session_state.chat_session.send_message(user_prompt)
+
+    # Display Gemini-Pro's response
+    with st.chat_message("assistant"):
+        st.markdown(gemini_response.text)
+        speak(gemini_response.text)
+
+    # If the response contains directions, open them in Google Maps
+    if "directions" in gemini_response.text:
+        directions_url = "https://www.google.com/maps/dir/?api=1&origin=" + current_location + "&destination=" + destination
+        webbrowser.open(directions_url)

Algorithms and Deep Learning Models/Beyond-GPS-Navi-Bot/requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+dotenv
+google-generativeai
+speech_recognition
+gtts

Algorithms and Deep Learning Models/Tiger Identification Project/Dataset/README.md

@@ -0,0 +1,7 @@
+## Dataset 
+Dataset link : https://www.kaggle.com/datasets/quadeer15sh/amur-tiger-reidentification?select=Amur+Tigers
+
+### Description 
+The Amur tiger population is concentrated in the Far East, particularly the Russian Far East and Northeast China. The remaining wild population is estimated to be 600 individuals, so conservation is of crucial importance. Re-identification of a species plays an important role in the conservation of wild life. With the help of WWF, a third-party company (MakerCollider) collected more than 8,000 Amur tiger video clips of 92 individuals from ~10 zoos in China. We organize efforts to make bounding-box, keypoint-based pose, and identity annotations for sampled video frames and formuate the ATRW (Amur Tiger Re-identification in the Wild) dataset. Figure 1 illustrates some example bounding box and pose keypoint annotations in our ATRW dataset. Our dataset is the largest wildlife re-ID dataset to date, Table 1 lists a comparison of current wildlife re-ID datasets. The dataset will be divided into training, validation, and testing subsets. The training/validation subsets along with annotations will be released to public, with the annotations for the test subset withheld by the organizers. The dataset paper is released on Arxiv: 1906.05586.
+
+Dataset contains cropped images with manual annotaetd ID and keypoints. Similar to most existing Re-ID tasks, the plain Re-ID task requires to build models on training-set, and evaluating on the test-set. During testing, each image will be taken as query image, while all the remained images in the test-set as "gallery" or "database", the query results should be rank-list of images in "gallery".