Peter Martens's repositories
GPT4-LangChain-Agents-Research-Web-App
Python Streamlit web app utilizing OpenAI (GPT4) and LangChain LLM tools with access to Wikipedia, DuckDuckgo Search, and a ChromaDB with previous research embeddings. Ultimately delivering a research report for a user-specified input, including an introduction, quantitative facts, as well as relevant publications, books, and youtube links.
OpenAI-Stock-Market-Chat-Bot
Python Streamlit web app with an SQLite user login/authentication system. Application allows users to select multiple stocks, metrics, and visualizations. A Langchain pandas agent utilizing GPT-4 and customized stock-market/financial prompts is then initiated allowing the user to intelligently interact with their specified data.
OpenAI-Whisper-Audio-Transcription-And-Summarization-Chatbot
Web app enabling users to either record or upload audio files. Then utilizing OpenAI API (Whisper, GPT4) generates transcriptions, summaries, fact checks, sentiment analysis, and text metrics. Users can also intelligently chat about their transcriptions with a GPT4 chatbot. Data is stored relationally in SQLite and also vectorized in Pinecone.
OpenAI-LangChain-Pandas-DF-Agent-Query-Streamlit-App
Python Streamlit web app allowing users to interact with their data from a CSV or XLSX file, utilizing OpenAI API and LangChain. It imports necessary libraries, handles API key loading, displays a user-friendly interface for file upload and data preview, creates a Pandas DF agent with OpenAI, and executes user queries.
OpenAI-LangChain-Multi-PDF-Chat-Bot
Python Streamlit web app allowing the user to upload multiple files and then utilizing the OpenAI API GPT 3.5 Turbo language models, the user is able to have a conversation about the uploaded documents. The user is also allowed to specify the language model and the temperature of the model. Also presented with a drop down for PDF analytics.
GPT4-Programming-Assistant
Streamlit web app utilizing OpenAI (GPT-4) and LangChain LLM tools. Application includes an SQLite DB for login/authentication and message storage for later retrieval. Users can upload/embed their own PDF documents for chatbot reference. The user can then interact with a GPT-4 chatbot intended for the user's specified input, context, and scenario.
React-Ecommerce-Site
Interactive frontend for an ecommerce website, built using react.js.
Streamlit-OpenCV-Webcam-Display-Web-App
Python script that creates a Streamlit application for displaying the webcam feed and performing facial detection using OpenCV. The application provides a simple interface to view the live video stream and includes a stop button to halt the feed.
OpenAI-Serpapi-Intelligent-Google-Search-Results-Chat-Bot-Streamlit-Web-App
Python Streamlit web app that takes user input and allows users to chat intelligently with google search results utilizing the Serpapi google search API, OpenAI API and LangChain.
OpenAI-Dalle2-Image-Generation-Streamlit-Web-App
Python Streamlit web app utilizing the OpenAI API to communicate with the Dalle2 image generation model, based on user input.
OpenAI-LangChain-Movie-Concept-and-DALLE2-Poster-Generation-Streamlit-Web-App
Python Streamlit web app utilizing LangChain and the OpenAI API GPT 3.5 Turbo language model to generate example movie concepts based on the AI director(Spike Lee, Quentin Tarrentino, Wes Anderson) and user input, and then the DALLE2 image generation model to generate relevent movie poster.
MiDaS-Computer-Vision-Depth-Estimation
This Python code uses the MiDaS model for real-time depth estimation on webcam video. MiDaS predicts the relative depth of objects in a scene, and the output is displayed using matplotlib. Bicubic interpolation is used to upsample the low-resolution depth map produced by the model. Output is then displayed in an interactive Streamlit web app.
OpenAI-LangChain-Email-Summarizer
Python script utilizing the OpenAI API and LangChain to summarize emails. User inputs email and subject, and function returns sender, role, tone, summary, and spam classification.
SceneXplain-LangChain-Image-Captioning-App
Python Steamlit web app that takes in a user-specified image URL and context. Then utilizing OpenAI(GPT4), LangChain and SceneXplain, the app generates a suitable caption for that image and context.
OpenAI-Customizable-Chat-Bot-Streamlit-App
Python Streamlit web app utilizing the OpenAI API GPT 3.5 Turbo language model. The app has a sidebar that allows the user to change and initiate new chate based on user defined settings such as language model, personality, context, and response temperature.
OpenAI-Rick-and-Morty-ChatBot-Jupyter-Notebook
This Python script uses pandas to read a Rick and Morty script CSV. It generates AI responses using OpenAI's Completion API. Morty suggests adventures, cleaning the spaceship, planet choices, music preferences, and bringing Jessica. Rick's witty responses create a humorous and dynamic dialogue.
OpenAI-SQL-Query-Generator-React-Next-Web-App
React Next web app that generates SQL queries using the OpenAI API. It has a TypeScript/Express backend for handling requests and a React frontend for user interaction. Messages are sent to the server, which returns query completions. The frontend displays the conversation history and generated SQL code.
OpenAI-API-Chat-Bot-Streamlit-Web-App
Chatbot using the OpenAI API and Streamlit. Users can enter messages in a web interface, and the chatbot generates responses using the OpenAI language model. The conversation history is stored and displayed in a chat format.
OpenAI-LangChain-Single-PDF-Question-Bot-Streamlit-Web-App
Streamlit web application utilizing Langchain and the OpenAI API, that allows users to upload a PDF file and ask questions about its content. It extracts the text from the PDF, splits it into smaller chunks, creates embeddings for the chunks, and builds a knowledge base.
satGPT
Python streamlit web app implementing a chatbot, "satGPT," using OpenAI's GPT-3.5. It generates satirical responses based on user input, storing conversation history. Users interact through a web interface, receiving witty and humorous replies displayed in chat bubbles. Emphasis is on entertainment through original and funny interactions.
Face-Detection-OpenCV-Streamlit-Web-App
This code uses Streamlit and OpenCV to create a real-time facial recognition web app. It captures video, detects faces using Haar cascade classifier, and highlights them. The app runs until video ends or "Stop" button is pressed. Powered by OpenCV, Streamlit.
NeuroSynth-Cognitive-fMRI-Analysis
In this Cognitive and Computational Neuroscience research project, I utilized neurosynth to further study the connection between multiple cognitive / behavioral patterns (Addiction, Anxiety), utilizing neurosynth I was able to write up the fMRI neueroanotmoical connection to such cogntive processes.
OpenAI-API-ChatGPT-React-Next-Clone
ChatGPT inspired application utilizing React for the frontend and Express for the backend to communicate with the OpenAI API. Users can input messages, receive AI-generated responses, and view previous chat conversations.
OpenAI-Snoop-Dogg-Rap-Bot
Python Streamlit web app utilizing the OpenAI API. The user enters a prompt and then in the style of Snoop Dogg an original album cover (DALLE2) and title + rap (LangChain + Prompt Templating) are then generated.
petermartens98
GitHub ReadMe Profile MD