StreamlitJobs

I am looking for a tutor who can help me understand, in a comprehensive and step-by-step manner, how to deploy a production-ready dashboard that displays the results of a model. My current stack includes: Google Cloud Platform (GCP) Vertex AI Workbench (where I trained the model) Streamlit (for the dashboard) Git and GitHub (for version control) I already have: A trained model in Workbench The .py files developed A structured and synchronized GitHub repository The intention to deploy everything in GCP However, I am not only looking for help with deployment — I want to fully understand the technical process behind it, including: How to properly structure the project for production. How to connect the trained model to the dashboard. The best architecture choice in ...

...need an interactive dashboard built in Streamlit that lets end-users explore time-series data coming from three different sources—raw CSV uploads, existing relational databases, and live API endpoints. The app should read, clean, and merge these feeds on the fly, then offer clear visual insights through line charts, area charts, and any other plots that make trends, seasonality, and anomalies obvious. Under the hood I expect well-structured, reusable Python code that leans on pandas for manipulation, SQLAlchemy (or similar) for database access, and a lightweight requests layer for the APIs. Caching, session-state handling, and responsive layout controls are important so the interface feels fast even as data volumes grow. Deliverables • Streamlit app fold...

...Sales. Growth Potential: Year-over-year growth in PAT. 3. Reporting & Output Summary Dashboard: A clean visual showing if the company is "Undervalued" or "Overvalued" based on the Intrinsic Value vs. current Spot Price. Risk Flags: Highlight if OCI shows significant losses (like pension liabilities or currency drops) that might be hidden from the main P&L. Technical Preferences Platform: A Streamlit Web App (Python), a specialized Google Sheet with AppScript, or a simple React dashboard. Simplicity: The goal is execution and functionality, not a perfect UI. It must work "out of the box." Deliverable A working link (URL) or a source file that I can run locally to demonstrate the tool for a video presentation....

...student-friendly interface (Web-based local UI or Desktop App) where students can type questions and get instant feedback. * Scalability: The ability to easily add or update the curriculum folders. Technical Preferences (Suggested) * Backend: Python (LangChain or LlamaIndex) * Model Management: Ollama, LocalAI, or GPT4All * Vector Database: ChromaDB or FAISS (must be local/persistent) * Frontend: Streamlit, Gradio, or a lightweight React app Ideal Candidate * Experience with Local Large Language Models (LLMs). * Proven track record building RAG pipelines. * Familiarity with hardware limitations for offline AI. * Experience in the EdTech space is a plus. Tips for your post: * Hardware: Decide what the students will use (e.g., "It must run on a laptop with 8GB RAM&qu...

...(MVP) Project Overview: I am looking for an AI/ML developer to build a functional prototype of a security system designed to detect "Digital Arrest" scams. The system needs to analyze video and audio inputs in real-time (or near real-time) to identify deepfakes, threatening language, and fake law enforcement visuals. Key Features Required (The Scope): I need a desktop-based prototype (Python/Streamlit or similar) that can process a sample video feed or live webcam input and perform the following: * Audio Threat Detection (NLP): * Transcribe audio in real-time (using OpenAI Whisper or Google Speech-to-Text). * Detect specific scam keywords/intents (e.g., "money laundering," "CBI," "narcotics," "arrest," "isolate yoursel...

Project Title: Build a Multi-Modal AI Productivity Suite (Meeting & Document Intelligence) Project Description I am seeking a developer to collaborate on a high-level AI productivity tool. The goal is to create a system that can pr...Retrieval-Augmented Generation system allowing users to upload large PDF/DOCX files and "chat" with the data for specific facts. Module 3: Sentiment & Intent Analysis: A dashboard component that tracks the "mood" of a conversation or document. Integration: A clean, functional API or Streamlit-based frontend to tie these features together. Required Technical Stack: Language: Python AI Frameworks: LangChain or LlamaIndex Transcription: OpenAI Whisper or AssemblyAI Database: Vector Databases (ChromaDB, Pinecone, or FAISS)...

...* No duplicate or delayed alerts 6. Interactive Charting * Display Point & Figure charts interactively * UX comparable to TradingView or similar * Must support: * Zoom / pan * Timeframe switching * Live updates 7. Tech Stack (Preferred, Not Mandatory) * Backend: Python (FastAPI / Flask / Django) * WebSockets: KiteTicker * Frontend: * React / Vue / plain JS * OR Python-based UI (Streamlit acceptable only if justified) * Hosting:AWS EC2 (Windows) * Alerts: Telegram Bot API 8. Alert based trades * Based on the alerts(buy/sell), proceed to trigger the trade. * The trade should be overnight all the time. * Should have the view to lock the lots and continue the trades without any stops. * During expiry if the trade is on overnight, exit that on the day or one day b...

Build, connect, and run AI-powered apps instantly using Streamlit and FastAPI — a lightweight accelerator for creating AI apps with minimal setup AI App Builder - Agentic Pipeline Architecture Overview This project uses an agentic (LangGraph-inspired) architecture to generate modular applications from user queries. The core pipeline consists of specialized agents for planning, editing, verifying, and assembling code for frontend, backend, and logic modules. the app looks good but i want some modifications basically i want that when user enters it requirements then it will give Refined Requirements: App Requirements Summary App Overview Core Features Technologies User Interface Data Requirements Assumptions like this which we can edit according to our need or if we are ok with ...

Build, connect, and run AI-powered apps instantly using Streamlit and FastAPI — a lightweight accelerator for creating AI apps with minimal setup AI App Builder - Agentic Pipeline Architecture Overview This project uses an agentic (LangGraph-inspired) architecture to generate modular applications from user queries. The core pipeline consists of specialized agents for planning, editing, verifying, and assembling code for frontend, backend, and logic modules. the app looks good but i want some modifications basically i want that when user enters it requirements then it will give Refined Requirements: App Requirements Summary App Overview Core Features Technologies User Interface Data Requirements Assumptions like this which we can edit according to our need or if we are ok...

Build, connect, and run AI-powered apps instantly using Streamlit and FastAPI — a lightweight accelerator for creating AI apps with minimal setup AI App Builder - Agentic Pipeline Architecture Overview This project uses an agentic (LangGraph-inspired) architecture to generate modular applications from user queries. The core pipeline consists of specialized agents for planning, editing, verifying, and assembling code for frontend, backend, and logic modules. the app looks good but i want some modifications basically i want that when user enters it requirements then it will give Refined Requirements: App Requirements Summary App Overview Core Features Technologies User Interface Data Requirements Assumptions like this which we can edit according to our need or if we are ok...

Project Title: Python ML Developer...details (e.g., specific loops, slants, and imperfections) from the sample image. It should look like real human writing, not a computer font. What You Need to Do: Select & Implement the Best Model: You have the creative freedom to choose the architecture (GANs, Diffusion Models, or Style Transfer). I am looking for the most realistic output. Build a Simple Interface: A basic local web page (Flask/Streamlit) to upload the image and generate text. Output Format: The system should generate high-resolution images (and preferably vector strokes if possible). Requirements: Experience with PyTorch/TensorFlow. Knowledge of Generative AI (GANs, Diffusion, or Transformer-based style transfer). Ability to work with Image Processing (OpenCV) to clean up ...

...Python codebase + README b) Validation report (results, risks, limitations) c) “Plain English” summary for business stakeholders Tech Stack (Preferred) 1. Python 3.10+ 2. PyTorch 3. PINN tooling: DeepXDE or custom PINN in PyTorch 4. pandas, numpy, scikit-learn 5. PDF extraction: pdfplumber + (Camelot/Tabula if needed) Optional: MLflow or W&B for experiment tracking Optional: FastAPI or Streamlit for demo Required Experience (Non-Negotiable) Proven experience with time-series forecasting on messy real-world datasets Hands-on experience with Physics-Informed ML / PINNs (show work, not theory) Strong Python engineering (clean modular code, reproducible experiments) Experience building validation frameworks (train/test split by site, not random rows) ...

...dataset that I will supply at project start. The stack is already chosen: Streamlit for the interactive UI, FastAPI as the service layer, a SQLite store for both raw data and model artefacts, Scikit-learn for data preparation, and a Temporal Fusion Transformer (TFT) as the core model. Visual insights should be delivered through Matplotlib or seaborn charts embedded directly in the Streamlit app. Key points to hit • Cleanly ingest the CSV, write it into SQLite, and expose CRUD endpoints through FastAPI. • Build the full forecasting pipeline—feature engineering, training/validation splits, hyper-parameter tuning, and model persistence. • Serve monthly forecasts via a REST endpoint and display them in Streamlit alongside historical trends...

...the only input in the first release, so your signal-processing and machine-learning choices must squeeze maximum insight from that single source. I’m open to Python (NumPy, SciPy, scikit-learn, TensorFlow) or MATLAB toolchains as long as the final product is easy for me to retrain with new runs. Deliverables • Source code with clear comments and a short setup guide • A lightweight dashboard (Streamlit, Dash, or similar) showing live health indicators, trend plots and a simple traffic-light status • A sample dataset and step-by-step notebook that reproduces your results • Brief report explaining feature extraction, model selection and validation results Acceptance criteria: the model should detect at least 90 % of seeded failure events from the sample s...

...indicators drawn from mock financial, employee-performance, and sales datasets. • Handle ad-hoc follow-up questions, maintaining context across turns. • Deliver answers as a hybrid of text explanations and simple visuals—think inline charts or mini-dashboards generated on request. You are free to pick the stack that gets us there fastest; Python with LangChain/FastAPI and a lightweight front end (Streamlit, React, or similar) would be ideal, but I’m open to alternatives if they shorten development time. The mock data can live in JSON, CSV, or an in-memory database—whatever keeps setup friction low—yet the code should be written cleanly enough that real data sources can slot in later. Deliverables 1. Running MVP: an API or small web app that acc...

...• Exportable outputs: • CSV • PDF Optional: • Simple web dashboard using Streamlit or Flask • Mobile-friendly view ⸻ 7. Cost Optimization The solution must: • Prefer free or low-cost APIs • Use open-source libraries: • Python • Pandas • Scikit-learn • TensorFlow / PyTorch • Use paid APIs (ChatGPT/Gemini) selectively only where necessary ⸻ Deliverables 1. Fully functional ML pipeline 2. Clean and documented source code 3. Trained models 4. Data ingestion scripts 5. Model evaluation report 6. Deployment-ready setup 7. User guide ⸻ Preferred Tech Stack • Python • Pandas / NumPy • Scikit-learn • TensorFlow or PyTorch • HuggingFace Transformers • OpenAI / Gemini AP...

Project Overview: I am looking for a developer to build a simple web-based AI "wrapper." The Workflow: Upload: User uploads a PDF court document. AI Processing: The system reads the PDF (including checked boxes) and sends the text to an LLM (OpenAI or Claude). Display: A simple split-screen view: Left ...Requirements: Speed of Build: I want this up and running quickly. It doesn't need to be lightning-fast (processing time is flexible), but the build should be straightforward. No Database: No logins, no accounts, and no saving data. This is session-based for privacy. Clean UI: Simple, professional, and mobile-friendly. -> I might provide the UI Tooling: You choose the simplest stack (, Streamlit, etc.) that allows me to easily update the AI instructions (p...

Hi, I am looking for a Google Cloud Platform...the PORT=8080 environment variable within the allocated timeout." What I need: Review my current configuration (I can share my screen or provide access). Identify why the container is not binding to the correct port (8080). Fix the issue so the application deploys successfully and is accessible via the public URL. Tech Stack involved: Google AI Studio Google Cloud Run Docker / Python (likely Streamlit or Flask, depending on the AI Studio export). Please apply if: You have experience with Google Cloud Run troubleshooting. You understand how to configure Docker containers to listen on the $PORT environment variable. You can communicate clearly in English (or Spanish). Looking for a quick turnaround as this should be a configuratio...

...only input in the first release, so your signal-processing and machine-learning choices must squeeze maximum insight from that single source. I’m open to Python (NumPy, SciPy, scikit-learn, TensorFlow) or MATLAB toolchains as long as the final product is easy for me to retrain with new runs. Deliverables • Source code with clear comments and a short setup guide • A lightweight dashboard (Streamlit, Dash, or similar) showing live health indicators, trend plots and a simple traffic-light status • A sample dataset and step-by-step notebook that reproduces your results • Brief report explaining feature extraction, model selection and validation results Acceptance criteria: the model should detect at least 90 % of seeded failure events from the samp...

Project Description I am the manager of a manufacturing plant building "Paideia," an AI maintenance assistant. I need a Python Backend Developer to build a Dockerized RAG (Retrieval-Augmented Generation) System. The Core Goal: I need a system where I can personally upload and manage a library of 100+ te...Backend: Python (FastAPI). Infrastructure: Google Cloud Platform (Cloud Run). Database: Dockerized Vector DB (Chroma/Qdrant) with Persistent Storage. Queue: Async Task Queue (for handling large uploads). Deliverables Dockerized Source Code: Ready to deploy. API Endpoints: For Upload (Bulk), Status Checking, and Deletion. Basic "Admin" UI (Optional but Preferred): A simple HTML/Streamlit page to drag-and-drop files and see a progress bar (e...

...already have a first-cut codebase that an AI generated for a small desktop-web hybrid dashboard. It mixes Streamlit with a PySide/PyQt front end, runs on Python 3, and pulls Poppler and OpenCV in the background for PDF and image handling. What I need now is a developer who can step in, clean the code, and make the whole thing run exactly as intended. Core goal Turn the existing prototype into a smooth interactive dashboard that can visualise data coming from CSV files, live database connections, and a couple of light-weight REST APIs. The layout and widgets are sketched out; several functions compile but don’t yet talk to each other the way they should. Scope of work • Refactor the Streamlit and PySide/PyQt layers so they share state seamlessly (no duplica...

Hello , Prefer Developer from - Vietnam , China , Singapore - Task Detail - I have existing Demo ( Logic ) made in streamlit , You will have to convert exact same logic in Fast API. While convert Fast API you have to follow or convert in to current structure of API (which i am using in existing chatbot ) Execution's time - Currently its taking too much time to load resposne due to multipel hit on API , some of hits might be need to change model. Demo URL is connected with demo data . Fast APi need to connect with live ES. Final Delivery would be API , i will test on Postman. Must follow the structure of demo code. you have to work on GitHub. Budget - 10 ,000 INR for this task. Timeline - 1 - 2 days maximum

Vær venlig at Tilmelde dig eller Log ind for at se detaljer.

...(FFT/Spectral Analysis) and what framework will you use for anomaly detection on the Raspberry Pi? 3. Safety Interface: Since we are not using a PLC, how will you safely control the 0.5kW AC motor using the Pi's GPIO? (Please specify your choice of contactors or high-power relays). 4. Web Dashboard: One of the core requirements is a web-based display. Please specify the stack you would use (e.g., Flask, Streamlit, or Node-RED) to visualize real-time sensor data, health status, and "Defect Detected" alerts. 5. Proof of Competency: Share a brief summary or link to a previous project involving Edge AI or IoT Dashboards. I am looking for a solution that is robust, safe for 220V operation, and provides a clean user interface. Best regards,...

I’m looking to build a small-footprint, AI-driven tool that takes a list of company names from me and returns a ranked, fully-scored spreadsheet of prospects that clearly shows who is most in need of digital marketing help. How I want it to work 1. I drop in a batch of company names (CSV, Google Sheet, or simple text input—whatever is fastest for you to wire up...(CSV or Google Sheet) listing the companies, their individual factor scores, and an overall “needs help” rank. • A quick Loom or written walkthrough showing setup and how to retrain or adjust rules. If you’ve already built lead-scoring or web-scraping automations, let’s talk—I’ll prioritise proven experience with Python scraping libraries, GPT or other LLM APIs, and lightw...

Hello Mohamad, I’ll keep the same Streamlit prototype (no “new design” work), but I will refine the UI so it’s easier to use and clearer for research reviewers. The app will be better structured into clean sections with basic on-screen instructions, consistent layout, and appropriately sized plots so the results are easy to read without extra explanation. Scope includes: loading your Excel/CSV dataset with clean/reproducible preprocessing, configurable burnout threshold (not hard-coded), two models (Logistic Regression baseline + XGBoost as the default “best” model) with both results saved for model-justification, full evaluation metrics displayed and exported, SHAP explainability (global + local) with plots saved as images, and a minimal what-i...

I need a Python-based dashboard that turns my existing financial datasets (CSV or Excel) into clear, interactive pie charts. No real-time feeds or export buttons for now—just concise, well-labelled visualisations that help me grasp revenue splits, expense breakdowns, and profit allocation at a glance. Use whichever stack you prefer—Plotly, Dash, Streamlit, or another lightweight data-vis library—so long as the code is clean, documented, and runs in a standard Python 3.11 environment. Deliverables • Source .py files and any assets • A running dashboard that loads the sample data I provide and displays at least three pie charts • A short README with setup steps, library versions, and instructions to launch the app with a single command Accepta...

I have a series of Excel spreadsheets holding detailed financial data and need a Python-based workflow that turns those raw tables into an intuitive, interactive Streamlit dashboard. The job begins with careful data cleaning and preprocessing in Pandas/NumPy, followed by a short exploratory analysis that highlights trends and anomalies. From there, you will craft clear‐cut financial KPIs—cash flow ratios, revenue growth, cost breakdowns, anything that helps leadership gauge performance at a glance. Visuals should be rendered with Matplotlib as the primary library; if a specific insight would benefit from Seaborn or Plotly, feel free to integrate them, but Matplotlib must anchor the final charts for consistency. The dashboard itself should enable filtering by period, drill-dow...

About the Role We're a bootstrapped AI/ML startup (Toronto-based, two-person founding team) looking for a Full-Stack Agent Engineer + DevOps Engineer to take our OpenAI-powered agents and Streamlit dashboards from local development into production-ready cloud infrastructure. You'll own the entire software lifecycle—from writing agent logic and APIs to designing and deploying our AWS architecture. This is a 0-to-1 role: you'll architect our first cloud deployment, establish CI/CD practices, define our codebase standards, and prepare the foundation for future team growth. You'll report directly to the founders and have significant autonomy in technical decision-making. What You'll Build Agent & Backend Development (60%) Build scalable Python servi...

.../ country, etc.), and shows me a preview table where I can type or paste the title and location rules I care about. With one confirmation click, the tool should disconnect any profiles that do not match those rules. I want a summary CSV at the end listing who stayed, who went, and why, so I can keep the audit trail. I am comfortable running Python, so a clean script or lightweight Flask/Streamlit front end would be ideal, but I’m open to other languages if you explain the setup clearly. Please avoid anything that could violate LinkedIn’s terms of service; official API, Selenium, or similar approaches are fine as long as they work reliably. Deliverables: • Fully working code with clear authentication steps • Simple interface to set job-title a...

...full detail that an audit partner could sign off on. Key requirements • Sub-8-second end-to-end response time for typical files (≈50–250 columns). • Clear segregation of inherent, control, and detection risk, with scoring logic exposed in the code. • Web interface or lightweight desktop app where I can paste headers or upload the CSV. • Written in Python; using LangChain, FastAPI, Streamlit, or similar is fine as long as dependencies stay mainstream. • All prompt engineering, taxonomy libraries, and custom code handed over with brief but precise documentation and a README that lets me redeploy on my own GPU/CPU box. Deliverables 1. Running prototype hosted on your sandbox (URL or demo video). 2. Source code and environment fi...

I’m building a quick proof-of-concept that shows how generative AI can help teachers, students and administrators. The app will be a clean, three-page Streamlit multipage project, written in Python and powered by the OpenAI GPT API—no database, no login, just an impressive demo I can show to schools. What I need developed • Teacher – Lesson Plan Assistant – Inputs: class, subject, topic, time, plus an option to upload or auto-pull dependable CBSE material – Outputs: objectives, suggested activities (make them interactive), and quiz questions • Parent / Principal – Student Summary Generator – Inputs: marks and attendance – Outputs: two narrative summaries: one parent-friendly, one principal-style •...

...full detail that an audit partner could sign off on. Key requirements • Sub-8-second end-to-end response time for typical files (≈50–250 columns). • Clear segregation of inherent, control, and detection risk, with scoring logic exposed in the code. • Web interface or lightweight desktop app where I can paste headers or upload the CSV. • Written in Python; using LangChain, FastAPI, Streamlit, or similar is fine as long as dependencies stay mainstream. • All prompt engineering, taxonomy libraries, and custom code handed over with brief but precise documentation and a README that lets me redeploy on my own GPU/CPU box. Deliverables 1. Running prototype hosted on your sandbox (URL or demo video). 2. Source code and environment fi...

I’m ready to move a Retrieval-Augmented Generation chatbot from concept to production and need a developer who can own the entire flow—from data retrieval right through to a polished, corporate-grade interface. Here’s what I’m looking for: • Front-end: Build a modern UI in Python (e.g., Streamlit, FastAPI with Jinja, or a comparable Python-based framework). The look should feel clean and professional, matching a corporate design language. If you prefer React, Angular, or Vue, that’s fine as long as it cleanly talks to the back-end and preserves the corporate aesthetic. • RAG pipeline: Implement a robust retrieval layer (vector store or hybrid search), connect it to the LLM of choice, and ensure responses are properly grounded in the source ...

...reports). Tech requirements (any of these is fine): Mapbox GL JS or Leaflet (Mapbox preferred) Real US ZIP code boundaries (you can download the free Census ZCTA GeoJSON and simplify it, or use a hosted tileset) Pure HTML + JavaScript (so I can host it for free on Netlify / Vercel) Or Python Streamlit if you prefer (also fine) Must be 100% offline-capable after the first load (except the map tiles). Deliverables: Complete source code (GitHub repo or zip) 1-click deploy instructions (Netlify/Vercel or Streamlit sharing link) A short 2-minute loom video showing it working...

...microstructure. Hands-on with Kafka/Redis Streams/RabbitMQ, TimescaleDB/Postgres, Docker/Microservices. Experience in ML/Backtesting frameworks (Pandas, NumPy, Scikit-Learn, XGBoost). Experience with REST APIs, WebSockets, streaming data handling. Nice-to-Have Experience with broker APIs (Angel One, Zerodha, AliceBlue etc.) Experience deploying on AWS/GCP UI dashboard skills (React/Vue/Streamlit) for visualization. Outcome A functioning software system that: Streams real-time market + OI data Stores & processes features for model prediction Predicts intraday NIFTY direction using ML models Generates actionable option trading signals automatically Engagement Contract / Freelance...

Developed a system to extract text from invoice documents using OCR (Optical Character Recognition) techniques. Implemented pre-processing steps (noise removal, thresholding, skew correction) to improve text extraction accuracy. Used Tesseract OCR / EasyOCR to automatically read fields like invoice number, date, vendor details, and total amount. Applied fraud-detection rules and m...dashboard/alerts to flag potentially fraudulent invoices for human verification. System improves financial security by reducing manual efforts, preventing billing fraud, and ensuring audit transparency. Evaluated performance using accuracy and false-positive rate; optimized model with real-world invoice datasets. Technology stack may include: Python, OpenCV, Tesseract, Scikit-learn / ML, Flask/Streamli...

This projec...methodological pipeline—including data preprocessing, engineered behavioural features, XGBoost modelling, a novel Hybrid Temporal-Behavioural Transformer (HTBT), and a hybrid SHAP–LIME explainability framework—the study develops a transparent and high-performing student-risk prediction system. The resulting models and interpretability techniques were translated into an interactive, production-ready Streamlit dashboard that enables users to input student indicators, obtain predictions, and visualise multi-layer explanations. The complete system, from academic design to model training, interface development, and public deployment, demonstrates how research-grade analytics can be operationalised for real-world educational decision-making. Paper will be p...

...cleaning in Python (pandas preferred). 2. Out-of-the-box analytics: RFM scoring, behavioural segmentation, cohort analysis. 3. Predictive models for churn risk, lifetime value and next-best action—scikit-learn, XGBoost or similar are fine. 4. Streamlit UI that lets a user select a segment, view key metrics, read plain-English recommendations, and export a CSV. 5. Everything containerised or at least runnable with a one-shot requirements file. What I need to see before sign-off • Code repo with clear structure and concise README • Working Streamlit app deployable locally • Synthetic datasets and generation scripts • Short demo video or GIF walking through the UI This build will be shown to early clients and advisors, so polish and...

...Gemini, Llama 3.x+, etc. Vector stores: Pinecone, Weaviate, pgvector, Qdrant Observability & evals: LangSmith, Ragas, promptfoo, guardrails Deployment: Vercel, Modal, , Cloudflare Workers, serverless Integrations: Stripe (escrow), Twilio/SMS, Google Calendar, third-party APIs Nice to have: Real-time features (WebRTC) Light frontend ( / Remix / SvelteKit) or rapid prototyping tools (Streamlit/Gradio) Previous work in real estate, marketplace, or field-service platforms How to bid: State clearly: “Applying as Individual” or “Applying as Team” (list team members & primary strengths) Share 2–3 relevant projects (live links, GitHub repos, or short case studies) that demonstrate agentic AI workflows, RAG, or complex tool-calling systems In 2&nd...

...environment so I can reproduce results later. The finished models must power a Streamlit dashboard where a user can paste or upload new patient data, adjust individual input fields, and instantly see the predicted probability of heart disease alongside confidence scores. Clean, intuitive input widgets and concise on-screen feedback are crucial. If you can wrap the app in Ngrok for quick sharing, great—otherwise local hosting is sufficient. Deliverables: • Well-commented Python notebook or .py scripts covering preprocessing, PCA, feature selection, model training, and evaluation • Saved model files plus or • Streamlit application folder ready to run with `streamlit run ` • Brief readme that walks me through setup, retraining,...

...causal dependencies between image and text features. ​Explainability: The system must output: ​Grad-CAM heatmaps for X-ray visual explanation. ​SHAP/LIME scores for text importance. ​Dataset: Train on MIMIC-CXR (primary) and test robustness on PadChest or NIH ChestX-ray14. ​Deliverables ​A. Working Code & Frontend ​Complete Python source code (PyTorch/TensorFlow). ​Basic Frontend (Gradio/Streamlit): A web interface to upload an X-ray image and paste a clinical report to see: ​Predicted Disease Label. ​Confidence Score. ​Visual Heatmap (Grad-CAM) & Text Highlights. ​Instructions/Readme to run the project locally. ​B. Research Paper ​Full paper drafting (Abstract to Conclusion). ​Target: IEEE JBHI or Medical Image Analysis standard. ​Plagiarism: Must be under 10% ...

Vær venlig at Tilmelde dig eller Log ind for at se detaljer.

...Description: Professional visa petition exhibit generator - Streamlit & Google Apps Script versions Recent Commits: 1. Add RAG and Supabase integration completion summary 2. Add Supabase integration plan for exhibit generator 3. Integrate VISA_EXHIBIT_RAG_COMPREHENSIVE_INSTRUCTIONS as authoritative guide 4. Add Streamlit UI completion documentation 5. Build complete Streamlit UI with compression controls 6. Add comprehensive Claude Project knowledge base guide 7. Add compression implementation summary document 8. Add comprehensive API key setup guide 9. Implement Option A: Full 3-tier PDF compression system 10. Add comprehensive Google Drive folder organization guide The codebase is production-ready with: - Complete Streamlit app (streamlit-exhib...

Overview I need a lightweight Python utility that runs locally on my Windows laptop. The tool should monitor a predefined folder and automatically process football-transfer contracts (PDF or .txt) as soon as they appear. Each file should be sent to the OpenAI API (GPT-4o / GPT-5.1) to extract appearance-related clauses only. After extraction, the to...environment setup • API key placement • folder structure • example questions • example clause prompts Optional (nice to have): • A tiny Tkinter GUI for Q&A • Logging of processed contracts • More polished formatting of DataFrame output ⸻ Tech Stack Requirements • Python 3.10+ • pandas • watchdog (or similar) • PyPDF2 / pdfplumber for PDF extraction • OpenAI Pytho...

...Full Stack Developer (Python/AWS Serverless) Goal: Build a multi-tenant ESG Data Platform using AWS Serverless architecture. Framework: Streamlit (Frontend), AWS Lambda (Backend), DynamoDB/InfluxDB (Database). 1. Project Overview We are building a SaaS platform for companies to upload ESG data (Environmental, Social, Governance) in CSV format. The system must parse these files, store the data, and visualize it. It also requires an AI reporting feature and IoT data ingestion. Architecture Status: The architecture is already designed. You are required to implement the code based on the provided blueprint. 2. Core Features to Build A. Frontend (Streamlit on AWS App Runner) Login Page: Simple authentication (integrate with AWS Cognito). Dashboard: Scope 1 & 2 Chart...

...dashboards. The goal is to understand our store performance, customer behaviour, and key business metrics through clean data analysis. Responsibilities - Analyse e-commerce datasets (orders, customers, sales, products) - Process and clean data using Python (Pandas, NumPy) - Identify trends, patterns, and actionable insights - Build dashboards (Power BI, Tableau, or Python dashboards like Plotly/Streamlit) - Track KPIs such as revenue, AOV, conversion rate, repeat purchase rate, churn, etc. - Provide data reports and visual summaries - Suggest improvements based on data findings Requirements - Strong experience with Python for data analysis - Excellent knowledge of Pandas, NumPy, and basic visualization libraries - Previous experience handling e-commerce data (preferred) - Abi...

...happiness, neutral, disgust Extracts heart rate (BPM) from facial color variations using rPPG Calculates a combined stress level (Low / Medium / High) Displays live output on the screen Optionally triggers alerts or stores stress logs for analysis Technologies Used: Python OpenCV MediaPipe / DeepFace (for facial emotion detection) rPPG algorithms (CHROM / POS) for heart-rate estimation NumPy / SciPy Streamlit or Flask (optional front-end UI) Key Features: Real-time Facial Emotion Recognition Contactless heart-rate estimation Combined stress scoring algorithm High accuracy due to multi-parameter analysis Can be deployed as a web app, mobile app, or desktop application Suitable for corporate wellness, student monitoring, driver stress detection, healthcare applications, and acade...

...prototypes of tools, AI workflows, and app ideas Debugging and fixing existing Python scripts, GUIs, APIs, and automation projects System-level utilities, dashboards, command centers Custom IDEs, editors, launchers, organizers, and productivity tools Media processors (audio tools, visualizers, tagging systems) Tech Stack Python (159+ libraries), PyQt6, PySide6, Tkinter, Flask, FastAPI, Streamlit, Torch, Transformers, FFmpeg, Vosk, Pandas, Asyncio/Threading, System Utilities. Focus on Offline Solutions Most of the tools I build are designed to run fully offline, including: STT/TTS modules AI text processing Media utilities Desktop GUIs Automation workflows Local API servers This ensures privacy, speed, and zero dependency on external services. Important Note I do n...

...clear setup docs and a short demo video. Acceptance criteria 1. Agent collects data for at least three named competitors and produces an initial comparison report. 2. Answers ad-hoc questions accurately within 30 seconds. 3. Codebase and README allow another developer to reproduce the results in one sitting. If you have experience combining web scraping, LLMs, and dashboarding tools like Streamlit, LangChain, or similar, you’ll be able to hit the ground running. Please outline your proposed tech stack, timeline, and any relevant past projects when you reply....