Streamlit jobs
...Proxy provider settings. AI Provider settings (API key, model selection). Speed and randomization intervals. Hashtag Strategy: Option to use the first hashtag or the most frequent hashtag as the primary bucket key. Tech Stack Preferences: Language: Python 3.10+ Browser Automation: Playwright (preferred for speed and modern API) or Selenium. GUI Framework: PyQt6 or Streamlit. Storage: SQLite for tracking Account-Hashtag-Proxy relationships. AI Integration: requests or openai library. Deliverables: Database Schema: Design the SQLite schema for tracking Accounts, Proxies, Hashtag Buckets, and Assignment History. Hashtag Extraction Logic: Python function using Playwright/Selenium to scrape hashtags from a YouTube video description. ...
...Requirement - Self Hosted: Must be hosted on my own server/machine or private URL. Must have user-based login/permissions so only I can access. I need to log in, hit "Run Scan", and export to CSV myself without relying on 2: Scale LaterExpand to US, EU, and other countries with a simple config change. Code needs to be Guidance NeededRecommend best stack. Open to: Python + Streamlit/Django for dashboard, Perplexity API, Apify, Playwright, GPT-4/Claude API for signal detection. Must handle anti-scraping, deduplication, and rate :Fully working self-hosted app with user loginClean, commented code + setup documentation2x 1-hour handover calls to teach me how to run, edit filters, add countries, and manage email enrichment2 weeks bug support after deliveryBudget:
...session, narrate what you’re doing and why—showing the essential commands, environment setup, and any common pitfalls. By the end, I should be able to hit an endpoint from a simple front-end snippet and see generated text flowing back. Deliverables • A recorded screen-share (voice-over included) that walks through the full deployment workflow • The interactive demo itself (Colab, Jupyter, or Streamlit are all fine) with clear, inline comments • A concise README outlining prerequisites and how to rerun or adapt the demo for another model - Use of ai tools for this is encouraged If you rely on specific tooling—transformers, Accelerate, Gradio, or HF CLI—make sure the versions used are noted inside the notebook so I can reproduce r...
1. Project Title () Development of an Automated NGO Darpan Data Extraction, Processing, and Management System Using Python, Selenium, BeautifulSoup, SQLite, and Streamlit ________________________________________ 2. Abstract The NGO Darpan portal is India's central repository for registered Non-Governmental Organizations (NGOs), Voluntary Organizations (VOs), Trusts, Societies, and Section 8 Companies. The portal contains publicly available organizational information including registration details, addresses, office bearers, operational sectors, and contact information. The objective of this project is to develop a Python-based automation system capable of systematically collecting publicly available NGO information after authorized user interaction where
...The core is a Python + Streamlit web app that presents a 10-question multiple-choice quiz on Mathematics (all questions pitched at a medium level). When the user finishes, the app should mark the score instantly and display a simple recommendation: “easy”, “medium”, or “hard” depending on how well they performed. This logic can be rule-based—no heavy machine-learning libraries are necessary. To make the hand-in complete, I’ll need: • the Streamlit source code (.py) • a file that stores the quiz questions, options, correct answers, and difficulty tags • a brief one-page report explaining how the system works and how the recommendation threshold is set If you can turn this around today, let me know rig...
...aviation AI safety project (Vayu Rakshak) being presented to defense officials (Indian Air Force). What we need: • 3D Animation / Cinematic B-Roll: Realistic fighter jets, cockpit views, and high-tech digital/cyber dashboards. • Professional Voiceover: Authoritative, clear English voiceover (Indian or neutral accent). • Video Editing: Smoothly merging the animations, voiceover, and our provided Streamlit dashboard screen recordings. • Motion Graphics: On-screen tech text overlays and full subtitles. • Audio Design: Inspiring, low-volume military-style background music. Deliverables: • Final 5-minute video in Full HD or 4K (MP4 format). • Fast turnaround is required as our review is in a few days. Please share your portfolio with technical,...
...WebSockets (via libraries like , Django Channels, or Streamlit-WebSockets): Quiz Master / Admin Control Panel: A private interface for the host/judges to manage the question bank, trigger countdown timers, control game states, and manually override or approve scores. Live Audience Display: A visually striking, clutter-free view designed to be projected onto an auditorium screen. It must feature live question updates, an animated countdown clock, and a real-time updating 4-House Leaderboard. House Team Interface: A synchronized local portal or interface where the 4 house teams can view active questions on their own devices simultaneously. Technical Expectations: Backend & Sync: Node.js () or Python (Django Channels / Streamlit WebSockets) or to handle bi-directiona...
...1 broken into smaller fixed-price milestones. Main technology preference: • Python • Streamlit dashboard • Microsoft Graph API / Outlook email • OpenAI API • CSV/Markdown outputs • Simple config files • Local Windows setup Important: • Stage 1 is read-only/safe. • Do not send, delete, archive, forward, or attach emails. • Draft replies are okay, but they must only be shown or saved as Markdown files. • No email action should happen automatically. • I want a simple local dashboard, not a complex SaaS app. • I want clear documentation and handover. • I want fixed-price quotes for each minor milestone. Stage 1A — Project setup and dashboard shell Requirements: • Create Python project. • Create loca...
I have a handful of finished Streamlit apps that I want running in the cloud. My first choice is AWS, so please plan for an AWS-hosted solution; if you see clear advantages in also wiring things to Snowflake later, keep that in mind, but the immediate goal is a clean AWS deployment. I’m not familiar with services like EC2, Lambda, or Elastic Beanstalk, so you’ll need to select and configure the option that best fits small-to-medium Streamlit workloads, automate the build and release steps, and make sure basic scaling and logging are in place. A concise hand-off package—source code, infrastructure files, and a README that walks me through redeploying or extending the setup—will let me maintain everything once the project is complete. May need help to ...
...specific prep bowls and detect the "tilting/pouring" action. * Implement a rolling video buffer logic that extracts exactly 3 seconds of video surrounding the detected action trigger. * Build the Edge-to-Cloud pipeline to upload compressed video fragments efficiently to a secure cloud platform (AWS S3, Google Cloud, or Azure). * Build a clean, lightweight frontend interface (using tools like Retool, Streamlit, or a basic React app) for cloud video playback. ## Required Skills * Deep expertise in Computer Vision and Deep Learning (Python, OpenCV, PyTorch/TensorFlow). * Extensive experience with real-time object detection models (YOLO workflow is highly preferred). * Proven track record building multi-camera RTSP video pipelines and handling edge processing hardware (NV...
...anti-overfitting workflow: rolling train/test splits, parameter stability checks and equity-curve validation. 7. Streamlit Dashboard • One-page overview plus drill-downs for data, strategy metrics, risk and live positions. • Simple authentication so I can share the link with collaborators. Acceptance criteria • End-to-end demo on sample equities universe. • All modules callable from a single orchestrator script (Python 3.11 preferred). • Clean, commented code with README and environment.yml. • Unit tests for core functions; ≥80 % coverage. If you have experience stitching together Alpaca or IB data feeds, writing vectorised backtests and deploying Streamlit apps, let’s talk about timelines and milestones—my ...
I am looking for a developer to build a web scraping project with a simple dashboard. I will provide the target scraping links through chat, and the developer will be responsible for extracting the required data, organizing it properly, and displaying it in a clean dashboard. The project should include a reliable scraping system that ...records, and see key information clearly. The final solution should be easy to run, maintain, and update when new scraping links are added. The developer should also provide basic setup instructions and make sure the scraping process works correctly before final delivery. Required Skills: Python, Selenium, Playwright, Flutter, IOS, Mobile App, web scraping, Dashboard development, Flask, FastAPI, Streamlit, PostgreSQL, MySQL, SQLite, or Google Sheets,...
...Smart TV application for our company. The project architecture requires using SolidJS for state management (Reactivity) and LightningJS as the canvas-based renderer. ​The application will communicate with a Streamlit backend, so experience in handling data streams, real-time updates, and API integration between the front-end and the backend is essential. ​Requirements: ​Strong experience with SolidJS (signals, fine-grained reactivity). ​Solid experience in Smart TV development using LightningJS framework/renderer. ​Ability to integrate and connect the front-end smoothly with a Streamlit backend (via APIs / WebSockets). ​Proficiency in JavaScript / TypeScript. ​Deep understanding of memory management and performance optimization for TV hardware. ​Experience or willingness t...
...competitors * Newly detected listings * Price changes over time ### 5. Filters Filter by: * Product * Location * Date * Price range ### 6. Export Export results to: * Excel * CSV ### 7. Alerts (Optional) Notifications when: * A new competitor appears * A competitor lowers their price * A competitor lists a new product ## Preferred Technology * Python * Playwright (preferred) or Selenium * Streamlit (or another simple web dashboard) * SQLite or PostgreSQL * OpenAI API (or equivalent AI model) ## Deliverables * Complete source code * Installation guide * Documentation * * Assistance with initial deployment ## Important The system should only collect publicly available information and should comply with applicable platform terms and applicable laws. ## When Applying...
...sentiment breakdowns that decision-makers can act on. Here’s how I picture the workflow: 1. Ingest raw text through a clean, modular pipeline (API or batch upload is fine). 2. Process the corpus with Python and state-of-the-art NLP libraries—spaCy, HuggingFace Transformers, or similar—so the architecture remains future-proof. 3. Generate clear, exportable outputs: interactive dashboards (Streamlit or Dash are welcome), concise PDF/CSV summaries, and machine-readable JSON for downstream use. Acceptance criteria • End-to-end script or app that runs locally and on a small cloud instance. • Well-commented code, README, and sample dataset to demonstrate each analysis step. • At least three analytical modules (e.g., sentiment, key phrase ...
I am looking for an experienced Python developer to build an AI-powered Investment Intelligence Platform for Indian markets. This is NOT an auto-trading platform. The platform should act as a professional investment research assistant and provide recommendations, rankings, portfolio insights, risk assessments, alerts and daily reports. Technology Stack: - Python - FastAPI - PostgreSQL - Streamlit - OpenAI API - Angel One SmartAPI - TradingView Webhooks - Telegram Bot - Docker Modules Required: 1. Long-Term Investing Engine 2. SIP Recommendation Engine 3. Swing Trading Engine 4. Intraday Trading Engine 5. Commodity Analysis Engine 6. IPO Analysis Engine 7. Portfolio Analysis Engine 8. Risk Management Engine 9. AI Discovery Watchlist Engine 10. Recommendation History Engine 11. A...
...important, so the notebook or script has to generate intuitive plots—scatter trends, residual diagnostics, whatever best tells the story of model quality and feature impact. After modelling, package the chosen estimator in a lightweight Streamlit app where a user can key in property details and instantly see a predicted price. Deliverables • Clean, well-commented Python code (Pandas, NumPy, scikit-learn, Matplotlib / Seaborn, Streamlit) • A concise report explaining preprocessing steps, feature choices, model comparison results, and recommendations • The Streamlit interface ready to run locally (with instructions) • Any supplementary documentation needed to reproduce the full workflow end to end If something in the data suggests a...
...will streamline later iterations. Dashboard Wrap the finished model in a Streamlit app that shows: • an overview KPI panel (current churn rate, predicted next-month churn, model ROC-AUC) • customer-level drill-downs with probability scores and top SHAP drivers • adjustable probability threshold plus CSV download of at-risk accounts Everything should live in a Git repo with clean commit history and a Makefile or so my team can reproduce the environment. Deliverables 1. EDA notebook exploring feedback data 2. Feature-engineering module generating frequency-based predictors 3. Model-training notebook with hyper-parameter search 4. Reusable Python package for batch scoring 5. Streamlit dashboard (responsive, deploy-ready) 6. Explainabil...
I need a simple Streamlit dashboard built in Python that loads data from a numpy .npz file and displays investment analysis charts. The dashboard should run locally with streamlit run app.py. What I need: 5 pages using Streamlit multi-page routing. Each page shows metrics and 2-3 Plotly charts for a different asset. The charts are: IRR probability distribution (histogram/KDE), DSCR by year (bar chart), and a scenario comparison (horizontal bar chart). One sidebar with a scenario dropdown that updates the charts. Tech stack: Python, Streamlit, Plotly, numpy. No database, no authentication, no deployment needed. Desktop only. Data: I will provide a .npz file with pre-computed numpy arrays (IRR distributions, DSCR arrays, scenario values). I will give you the exact...
...theming, shared components) once, reused across modules - Implement the full suite of modules (structure prediction, ligand prep, docking, simulations, QSAR, database, and more), wired to our existing Python prediction/docking logic - Add interaction states (loading, empty, error, validation), a 3D molecular viewer, and basic deployment Must have: - Strong Python - Hands-on Gradio experience (or Streamlit, with willingness to work in Gradio) - Comfort with custom CSS/theming within Gradio - A sample of a data-dense or technical UI you've built Nice to have: - Any cheminformatics, scientific, or healthcare software exposure - Experience with or molecular visualization How we'll work: - A small paid trial (one screen) first, then milestone-based delivery for the full ...
...historical backtests on minute-level data to validate tweaks before they go live, outputting metrics like win rate, drawdown, and expectancy I value readable, modular code (separate data, logic, execution, and reporting layers) and clear in-line comments so I can extend the system later. Preference for standard libraries plus proven packages such as pandas, numpy, TA-Lib (if helpful), and FastAPI or Streamlit for the monitoring front end—though I’m open to your suggestions. Deliverables will be: 1. Fully commented Python source files and 2. A backtesting notebook or script with sample results 3. Setup instructions to run everything on my local machine or a VPS 4. A brief hand-off session (video or chat) to walk me through deployment and daily use If you&rs...
I have a raw set of patient records a...and normalise numeric or categorical values so every observation is model-ready. • Feature selection & training: experiment with at least Random Forest and Logistic Regression; pick the best model using accuracy, precision and recall. • Evaluation report: include confusion matrices and a short note explaining why the chosen model performs best. • Lightweight dashboard: a simple Flask or Streamlit interface with one free-text field for symptoms and a results pane listing the suggested medicines. • Clean, well-commented code plus a README describing setup, usage and how to extend the model with medical history or allergy data later. Everything should run end-to-end on my local machine with clear install instructi...
- Developed ChurnShield, an end-to-end AI-powered platform for customer churn prediction and retention intelligence, utilizing Python, FastAPI, TensorFlow, and Streamlit. - Created a custom Artificial Neural Network (ANN) featuring three dense layers, batch normalization, dropout regularization, early stopping, and Adam optimization for churn prediction. - Implemented industry-specific machine learning pipelines for telecommunications and banking datasets, incorporating automated preprocessing and feature engineering. - Established intelligent churn risk classification systems that categorize customers into high, medium, and low-risk groups based on probability scoring. - Designed an interactive, cyberpunk-inspired analytics dashboard for real-time KPI monitoring, risk segmentat...
• Built StockAI, a full-stack AI-powered stock market analysis and trading platform using Python, FastAPI, Streamlit, XGBoost, and Machine Learning. • Developed dual-machine learning models for stock price forecasting and BUY/SELL signal generation using 5 years of historical market data. • Engineered 35+ advanced technical indicators including RSI, MACD, Bollinger Bands, ATR, Stochastic Oscillator, Williams %R, OBV, moving averages, volatility metrics, and momentum-based features. • Implemented feature engineering pipelines to transform raw OHLCV market data into predictive trading intelligence. • Built time-series forecasting systems with proper train-test separation, walk-forward validation, and backtesting to eliminate data leakage. • Created c...
...Scikit-learn, etc.). Large Language Models (LLMs): GPT-4, Claude 3.5, or equivalent via API to synthesize data and generate human-readable recommendations. Agentic Framework: CrewAI, LangGraph, or equivalent to orchestrate specialized sub-agents (e.g., an Attendance Agent, an Academic Agent, and a Decision Agent). UI/Dashboard: A simple, secure interface for data entry and report viewing (built via Streamlit, Power BI integration, or a web framework). What we need from your proposal: A fixed-price quotation for developing this system from scratch. Estimated monthly operational costs (SaaS/Cloud Hosting + LLM API token consumption for 1,450 students). Estimated timeline for delivery. Optional alternative: If you advise building this using Low-Code enterprise tools (e.g., M...
...Skills ## Mandatory ### Python Minimum 5+ years experience Strong knowledge of: * AsyncIO * Multiprocessing * Threading * Event-driven systems * Data pipelines * API integration * Logging * Testing ### Trading Systems Experience with: * Equities * Options * Order routing * Position management * Broker APIs * Market data feeds ### GUI Development Experience with one or more: * PyQt6 * Streamlit * React + FastAPI * Dash ### Data Engineering Experience handling: * Real-time feeds * Market data normalization * Websocket streams * Rate limits * Caching ### Software Engineering * Git * CI/CD * Unit testing * Integration testing * Production deployment --- # Highly Preferred Experience with: * Schwab API * TD Ameritrade API * Alpaca * Polygon * FMP * Interactive Brok...
...automated pipeline to fetch customer purchase data (batch or daily sync). Integrate Claude AI (Anthropic API) as the processing engine to build predictive consumer profiles and generate personalized outreach copy. Wire the pipeline to an official WhatsApp Business API gateway (e.g., Twilio, Wati, or Gupshup). Build a clean, secure, and user-friendly web application dashboard (using Retool, Streamlit, or logs) so a non-technical business owner can easily track daily campaign metrics, gateway wallet balances, and opt-outs. Strict Security & Data Protection Protocols: Zero Real PII Access: You will be provided exclusively with anonymized dummy datasets (fake names/numbers) during the active development, configuration, and testing phases. Real database credenti...
...orchestrator that fires all 75 queries in parallel across the six platforms, handles retries and rate limits, tags client domain and competitor mentions in real time, and writes results to a provided Excel template. Streamlit UI for click-to-run operation, with engagement metadata input, live progress monitoring, results preview, plus Google Drive upload and Slack notification integrations on completion. Deliverables Six platform adapter modules with normalized response interface Async orchestrator with error handling and retry logic Excel writer (we provide the template) Streamlit dashboard Google Drive and Slack integrations README, setup guide, and operator documentation Test suite covering 70%+ of code paths All code in a GitHub private repo owned by us What we prov...
Project Description We are looking for a Python developer to build and fix a simple MVP web application that helps users analyze resumes and job descriptions and generate basic interview preparation support. The goal is to create a lightweight, locally runnable Streamlit application that demonstrates basic resume-job matching functionality. This is a small academic MVP project, so simplicity, clarity, and functionality are more important than complex architecture. MVP Features (Must-Have Only) The application must include the following core features: 1. Upload CV Allow users to upload a resume in PDF or DOCX format 2. Paste Job Description Allow users to paste a job description into a text input field. 3. Keyword Matching Extract and compare keywords from CV and job description 4. ...
...downsampling engine using Pandas resample across multiple timeframes • Order routing via Shoonya NorenApi — market/limit orders, partial fill handling, multi-leg option spreads • Hard circuit breakers — max daily drawdown, margin limits, and position guards calibrated to ₹1,00,000 capital • End-of-day structured JSON/Markdown report generator designed for Claude AI analysis • Telegram alerts, dashboard (Streamlit), and global kill switch • Full audit trail (PostgreSQL) meeting SEBI 5-year retention requirements • Paper trading mode for shadow testing before going live REQUIRED SKILLS Python 3.11+ • asyncio / uvloop • Shoonya NorenRestApiPy • picows • QuestDB or InfluxDB • PostgreSQL + TimescaleDB • Redis &b...
Hi, we will develop a simple Python-based Text Analyzer MVP using Streamlit. The application will allow users to input or upload text and provide basic analysis including word count, character count, most frequent words, keyword extraction, and a simple readability score. This is a lightweight MVP focused on functionality, clean code, and easy local execution. No database, authentication, or deployment is included. Deliverables: - Streamlit application source code - file - README with setup instructions - Clean and maintainable codebase
...Learning rate Epochs Batch size Filter size Number of filters Best performance achieved with low learning rate and more epochs Accuracy achieved above 90% Performance metrics used: Accuracy Precision Recall F1-score Confusion matrix Technologies used: Python TensorFlow Keras OpenCV NumPy Pandas Matplotlib Scikit-learn Platform used: Google Colab Anaconda Model deployment using Hugging Face and Streamlit Upload MRI image to predict disease Fast and automated diagnosis system Reduces manual work for doctors Helps in early treatment planning Non-invasive medical diagnosis method Future scope: Add more diseases Improve accuracy Use larger datasets Clinical healthcare implementation...
Develop an automated daily market-reporting system that collects, processes, and presents Stock Exchange data in a professional Arabic dashboard and report format. The system should scrape the required mar... The system must include validation checks, error handling, and logs showing whether scraping, API connection, AI summarization, report generation, and email delivery were completed successfully. The platform should be modular so that scraping, API, AI summarization, dashboard, report generation, and scheduling can be maintained separately. The preferred technology stack may include Python, Streamlit, Selenium or Playwright, BeautifulSoup, pandas, openpyxl, API requests, OpenAI or Anthropic API, HTML/CSS, PDF export tools, SQLite or PostgreSQL, scheduler, and SMTP or Outlook in...
...category, timeframe, drop percentage, and whether chart snapshots are included. _Optional Dashboard A simple Streamlit dashboard is preferred but not required for the first version. If included, it should allow filtering by: * Date range * Ticker * Exchange * Market cap category * Drop percentage * Relative volume * Sector * Industry * Timeframe * Whether the chart snapshot exists _It should also include export buttons for CSV, Excel, JSON, Parquet, and ZIP. Preferred Technology Stack * Python * Pandas or Polars * PostgreSQL * SQLAlchemy * Requests/API clients * YAML or JSON configuration * Environment variables for API keys * Matplotlib / Plotly / mplfinance for chart generation * Streamlit optional * Modular code structure * Clean documentation _Deliverables * Work...
...(workspaces), filtering by department, year, document type, etc. Conversation History & Memory. High Security: All data stays on local server/machine. Preferred Technology Stack: LLM: Ollama (Qwen3, Llama 3.1/3.3, or any strong Vietnamese-supported models). Framework: LangChain or LlamaIndex. Vector Database: ChromaDB, FAISS, or LanceDB. Embedding Model: nomic-embed-text or equivalent. Frontend: Streamlit, Gradio, Open WebUI, or AnythingLLM. Report Export: python-docx, WeasyPrint, ReportLab, Jinja2. Requirements for Freelancer: Proven experience building Local LLM + RAG systems that run fully offline. Strong expertise with Ollama + LangChain/LlamaIndex. Experience in model optimization (quantization, long context, performance tuning). Good prompt engineering skills, espec...
...POST raw email text and receive the predicted class plus a probability score. • A clear evaluation notebook or script that prints accuracy, F1, ROC-AUC and a confusion matrix so I can verify performance. • Repository structured for easy hand-off, including and a concise README explaining setup, training and API usage. I would appreciate—but do not strictly require—a small Streamlit dashboard that lets me paste an email and see the prediction in real time; feel free to propose how you would add that. Acceptance is based on: 1. Re-running on my machine reproduces the best model. 2. Calling /predict with sample emails returns correct spam/ham flags with confidences. 3. (or notebook) matches or exceeds the scores you quote. 4. Project installs
...CSVs, or DOCX files, the system indexes them into a persistent FAISS vector store, and an interactive Streamlit front-end gives me document upload, semantic search, and response generation in one place. Under the hood, the app should use Python with LangChain to orchestrate local models served through Ollama (Qwen2.5, Llama3.2, Phi3 for the first iteration). The interface must surface at least two key numbers for each model on every query—its latency and the text response itself—so I can judge speed against output quality at a glance. No cloud calls, no telemetry: everything runs offline on the host machine for maximum privacy. Deliverables • Clean, well-commented Python codebase (Streamlit UI, LangChain pipelines, FAISS setup, Ollama integration) &b...
...CSVs, or DOCX files, the system indexes them into a persistent FAISS vector store, and an interactive Streamlit front-end gives me document upload, semantic search, and response generation in one place. Under the hood, the app should use Python with LangChain to orchestrate local models served through Ollama (Qwen2.5, Llama3.2, Phi3 for the first iteration). The interface must surface at least two key numbers for each model on every query—its latency and the text response itself—so I can judge speed against output quality at a glance. No cloud calls, no telemetry: everything runs offline on the host machine for maximum privacy. Deliverables • Clean, well-commented Python codebase (Streamlit UI, LangChain pipelines, FAISS setup, Ollama integration) &b...
...for now). – Retrieve the model’s enrichment output and append it to the stored profile. • Outreach Automation – Using Make or n8n, trigger personalised sequences by email and LinkedIn as soon as a profile is marked “ready”. – Track delivery, opens, replies, and LinkedIn connection status in real time. • Lightweight Monitoring Dashboard – A single-page web app (simple Flask or Streamlit is fine) that shows: number of factories scraped, enrichment success rate, outreach status, and error logs. Acceptance criteria 1. Scraper handles captcha or login changes without manual fixes for at least two weeks. 2. API module retries gracefully on rate limits and returns enriched JSON compliant with our schema. 3. Out...
...system provides an interactive Streamlit dashboard where users can select a stock and choose different prediction models to generate a BUY / SELL / HOLD signal along with predicted price values. The dashboard also visualizes historical stock performance with technical indicators and displays predictions in Indian Rupees (₹). Features Interactive Streamlit dashboard Stock data retrieval using Yahoo Finance Visualization of historical stock performance Moving average indicators (MA50 & MA200) Multiple prediction models: Random Forest ARIMA LSTM Hybrid Model (combination of models) BUY / SELL / HOLD signal generation Currency conversion from USD to INR Model selection and stock selection directly from the dashboard Project Architecture User Input (Streamlit...
...CSVs, or DOCX files, the system indexes them into a persistent FAISS vector store, and an interactive Streamlit front-end gives me document upload, semantic search, and response generation in one place. Under the hood, the app should use Python with LangChain to orchestrate local models served through Ollama (Qwen2.5, Llama3.2, Phi3 for the first iteration). The interface must surface at least two key numbers for each model on every query—its latency and the text response itself—so I can judge speed against output quality at a glance. No cloud calls, no telemetry: everything runs offline on the host machine for maximum privacy. Deliverables • Clean, well-commented Python codebase (Streamlit UI, LangChain pipelines, FAISS setup, Ollama integration) &b...
...Here’s the experience I’m after: ultra-low-latency replies through Groq’s API, running LLaMA 3.3 70B behind the scenes. I want conversation history to persist across a visitor’s session, so Streamlit session_state (or an equally clean solution) is the framework of choice, with python-dotenv keeping keys secure. A polished, on-brand interface, a friendly greeting flow, and easy deployment to a cloud host should round it out. Only English support is required for launch, but the prompt design must be modular enough that I can localise later without breaking anything. Deliverables • End-to-end Streamlit app with custom branding and welcome sequence • Groq API integration tuned for sub-second answers • System prompt architectur...
...pipeline—Python, R, or a notebook environment is fine—that ingests these files, handles missing values, and standardizes the fields. From there, build and validate models that can flag anomalies and forecast key indicators (AR, cash flow, or any other variables you think add value). Finally, present everything in an interactive report; I’m open to Power BI, Tableau, or a web app using Plotly Dash/Streamlit, so long as executives can slice and drill without installing extra software. Deliverables • Clean, documented dataset (with reproducible ETL code) • Machine-learning notebooks/scripts with comments explaining methodology and metrics • Fully functional interactive report hosted or packaged for easy deployment • A brief hand-over wa...
...glance. I expect the workflow to be fully automated once a file is dropped into a designated folder (or a table is updated). Behind the scenes you can rely on Python, pandas, scikit-learn, or similar tooling; as long as the final solution is reproducible and easy for me to extend, the choice of libraries is up to you. I’m comfortable running scripts locally, but a lightweight web dashboard (Streamlit, Dash, etc.) that shows key charts and summary sentences would be ideal. Acceptance criteria – the assistant is complete when it: • Ingests new market-trends data without manual preprocessing • Generates a concise written summary plus interactive visualisations (trend lines, YoY comparisons, anomaly flags) • Saves both the summary and the visuals to a...
...recent data periodically 4. Intraday Focus Operates on 1min / 5min / 15min timeframes Signals generated in real time during market hours 5. Output / Dashboard Simple UI showing current signal, confidence score, market regime Alert via Telegram or email when signal triggers Tech Stack Suggestion Python (core) scikit-learn / TensorFlow / PyTorch (ML) CCXT library (crypto exchange connectivity) Streamlit (quick dashboard) PostgreSQL (data storage) Important Notes for Coder No predefined strategy — system must learn from data Must handle both crypto (24/7) and commodity markets (Gold) Risk management module needed: stop-loss, position sizing suggestions Backtesting module essential before going live...
...datasets) that truly represents urban crash scenarios, then fine-tune an architecture such as YOLOv8, Faster R-CNN, or another proven model in PyTorch/TensorFlow. Accuracy and speed matter equally; anything under a few seconds for a one-minute clip on a modern GPU is ideal. Deliverables • Trained model files and all preprocessing scripts • Lightweight desktop or web demo (Python + OpenCV/Streamlit/Flask—your call) mirroring the UI flow above • At least three short demo videos that clearly show LOW, MEDIUM, and HIGH severity outputs • Brief setup guide so I can reproduce results locally or on a cloud VM This is time-sensitive, so please outline how quickly you can: 1. Finalize the dataset, 2. Train and validate the model, 3. Package the ...
...financial data APIs or market data sources. - Previous work on financial analytics dashboards or research tools. - Familiarity with Google Cloud Platform services (Vertex AI, Looker, Dataflow, etc.). Deliverables: - Well-structured BigQuery database with clean data schema. - Integrated Machine Learning models for bond price research features. - Functional search and analysis interface (e.g., Streamlit, Looker, or simple web app). - Documentation and basic user guide. - 1–2 weeks of support after delivery. How to Apply: Please include in your proposal: - Your experience with BigQuery and Machine Learning projects. - Any relevant work with financial or time-series data (even if not bonds). - A short description of how you would approach this project. - Estimated timel...
