4,052 tools found
Predict numerical review scores (1-5 stars) from text embeddings using regression, achieving 0.53 average error on unseen data with a train/test split workflow.
OpenAI cookbook notebook that searches reviews by meaning using cosine similarity between a query embedding and pre-computed document embeddings.
OpenAI cookbook example chaining explain, plan, and generate prompts to write pytest unit tests with the Completions API.
OpenAI cookbook notebook deriving per-user and per-product embeddings by averaging review embeddings, then testing them as a recommendation signal.
Notebook with code snippets to embed text using OpenAI's text-embedding-3-small model, with recommended rate-limit handling using exponential backoff.
OpenAI Cookbook notebook reducing 1536-dim embeddings to 2D via t-SNE and plotting them colored by review star rating as a sanity check.
Jupyter notebook workflow that reduces text-embedding-3-small vectors from 1536 to 3 dimensions using PCA and plots them in 3D scatter plots.
OpenAI cookbook notebook classifying review sentiment with zero labeled data, by comparing sample embeddings to embedded class-label descriptions.
OpenAI Agents SDK cookbook demonstrating hub-and-spoke multi-agent orchestration for collaborative investment research with parallel specialists.
OpenAI Cookbook notebook demonstrating fan-out/fan-in multi-agent orchestration, comparing asyncio.gather against the Agents SDK's tool-planning approach.
A notebook showing how to generate embeddings through the Azure OpenAI service, from resource setup to a sample request.
OpenAI Cookbook notebook demonstrating function calling on Azure OpenAI, covering API-key and Active Directory authentication paths specifically.
