centralmoment/creative_job_analysis_2026_Q1

2026'Q1 CPro job listings analysis

Analyze job listings without user model choice.

🌟 Overview

This application enables rapid, repeatable analysis of job posting datasets. It supports:

• —🔍 Natural-language querying of CSV job postings
• —🧠 OpenAI Assistant logic with structured tools
• —🗂️ Hybrid retrieval (semantic + keyword + CSV filtering)
• —📊 Automated Python analysis (Code Interpreter)
• —📝 Follow-up questions within the same context
• —⚡ Fast results with minimal UI complexity

This Space is ideal for market sizing, creative labor segmentation, workflow analysis, and identifying software/tool requirements across job listings.

🚀 Features

Semantic + Structured Querying

Ask questions like:

• —“How many jobs require video editing tools but don’t mention Adobe?”
• —“Which UX roles mention AI or LLM skills?”
• —“What non-Adobe creative tools appear most often?”

Code Interpreter for On-the-Fly Analysis

The assistant can:

• —generate tables
• —compute distributions
• —summarize skills/software
• —run filters and aggregations
• —visualize results (if enabled)

No model selection required

The interface is simplified so users do not choose a model manually. Works with your configured OpenAI Assistant and the Space’s environment variables.

Simple, reliable Streamlit UI

No unnecessary complexity — clean, fast, deployable anywhere.

📁 Dataset

This Space is designed to work with uploaded CSV datasets containing job postings.

A typical dataset includes fields such as:

• —title
• —company
• —description
• —creative_categories
• —software_mentions
• —skills
• —location
• —seniority

The exact schema may vary; the assistant automatically adapts.

🔧 Technology Stack

• —Streamlit — Interactive web UI
• —OpenAI Assistants API — LLM reasoning & tool calls
• —Python — Data handling, plotting, and job parsing
• —File Search / Semantic Search — Embedded retrieval over job postings
• —Pandas + Python tools — Structured analysis

🛠️ Setup Instructions

Local Development

1. 1.Install dependencies:

   pip install -r requirements.txt