shashipal95 / all_in_one_vk_chatbot_with_translator

GeminiAPI_PALM_Chatbot (Audio, Vision, Prompt, Multiple-PDF and addon translator)

ALL IN ONE VK CHATBOT: Audio, Prompt, Multi-PDF, Vision-Based Chatbot that Integrates with Streamlit & Translates (107 Languages)

This Google Gemini chatbot is based on the LLM PALM2 Model!

What & Why Palm2?

• PaLM 2 is our next-generation large language model that builds on Google’s legacy of breakthrough research in machine learning and responsible AI.

• It excels at advanced reasoning tasks, including code and math, classification and question answering, translation and multilingual proficiency, and natural language generation better than our previous state-of-the-art LLMs, including PaLM. It can accomplish these tasks because of the way it was built – bringing together compute-optimal scaling, an improved dataset mixture, and model architecture improvements.

• Palm 2 is grounded in Google’s approach to building and deploying AI responsibly. All versions of PaLM 2 are evaluated rigorously for potential harms and biases, capabilities, and downstream uses in research and in-product applications. PaLM 2 is used in other state-of-the-art models, like Sec-PaLM. We continue to implement the latest versions of PaLM 2 in generative AI tools like the PaLM API and Bard.

OBJECTIVE:

The project's objective is to develop a chatbot with prompt-based responses, multiple pdf-based chatbots, and the ability to quickly summarise the contents of your images.

Phase1

Multiple PDF Based Chatbot Integrating Streamlit

STEPS TO FOLLOW IN THIS PROJECT:

1. Git clone and change directory

$ git clone https://github.com/VK-Ant/Prompt_Vision_Based_Chatbot_integrating_Streamlit.git

$ cd Prompt_Vision_Based_Chatbot_integrating_Streamlit

2. Install the prerequisite library using requirement file

$ pip install -r requirements.txt

3. Add your project folder to the.env folder you created (put your Gemini api key)

'''bash GOOGLE_API_KEY = your Gemini API key '''

4. Finally, run the code

$ streamlit run multi_pdf_chatbot.py

Phase2

Prompt & Vision Based Chatbot Integrating Streamlit

STEPS TO FOLLOW IN THIS PROJECT:

The ultimate(above) three steps are identical.

4. Finally, run the code

$ streamlit run vision_prompt_chatbot.py

Phase3

All in one Chatbot Integrating Streamlit

STEPS TO FOLLOW IN THIS PROJECT:

The ultimate(above) three steps are identical.

4. Finally, run the code

$ streamlit run all_in_one.py

or

streamlit run all_in_one_v1.py

Phase4

All in one Chatbot With Translator

STEPS TO FOLLOW IN THIS PROJECT:

The ultimate(above) three steps are identical.

4. Finally, run the code

$ streamlit run translate_v1.py

Final Phase

Audio-based Chatbot With Translator

if you wish to embed audio within a single chatbot. It's easy

STEPS TO FOLLOW IN THIS PROJECT:

The ultimate(above) three steps are identical.

4. Finally, run the code

$ streamlit run audio_translate.py

PROJECT DESCRIPTION:

1. Install requirement file.

2. .Add your project folder to the.env folder you created (put your gemini api).

3. Run the main file

4. if you choose the vision model then upload the picture else just prompt and get the output

THANK YOU & CREDIT

1. https://ai.google.dev/tutorials/python_quickstart#chat_conversations
2. Streamlit, GoogleGemini library
3. https://github.com/MuhammadMoinFaisal/LargeLanguageModelsProjects

🤗Happy learning🤗