Multi-step prompt sequences for complex AI workflows.
52 tools found
Prepare a Wikipedia article dataset for semantic search: collect, chunk, embed, and store as CSV.
A notebook building an embedding-based nearest-neighbor recommender for news articles, with cached embeddings and t-SNE visualization.
A prompt workflow that predicts numerical review scores (1-5 stars) from text embeddings, achieving 0.53 average error on unseen data for regression tasks.
Jupyter notebook demonstrating how to embed text using OpenAI's text-embedding-3-small model with rate-limit management via exponential backoff.
OpenAI Cookbook notebook that reduces 1536-dim embeddings to 2D with t-SNE and plots them colored by star rating.
Notebook workflow that reduces embedding dimensions from 1536 to 3 using PCA and renders them as 3D scatter plots for visual analysis.
OpenAI Cookbook notebook classifying review sentiment with zero labeled training data by comparing embeddings to label-description embeddings.
OpenAI Agents SDK example orchestrating Portfolio Manager, Macro, Fundamental, and Quantitative agents in parallel to produce an investment research memo.
Jupyter notebook demonstrating how to evaluate LLM answers about GitHub repositories using OpenAI Evals framework with custom datasets and MCP tools.
Collect and section 713 Wikipedia pages on the 2020 Olympics as context data for a confabulation-resistant Q&A model.
OpenAI guide introducing the stateful, multi-tool, multimodal Responses API versus Chat Completions and Assistants.
A notebook that logs embeddings to Weights & Biases and renders them as a 2D projection with PCA, UMAP, or t-SNE.
