Daily Digest — 2026-04-01

Datasette-llm 0.1a4 introduces the ability to configure different API keys for various model purposes, enhancing flexibility in model usage. This feature allows for more tailored and secure interactions with language models.

The llm-all-models-async 0.1 release allows LLM plugins to define models in both sync and async forms, improving compatibility with Datasette. This development facilitates the use of async models, which are crucial for API-backed operations.

LLM 0.30 update introduces a plugin hook for registering models and their aliases, enhancing the integration of various models. This update also improves documentation, making it easier for developers to utilize the LLM framework.

Tiger Data has released pg_textsearch, a Postgres extension for BM25 relevance-ranked full-text search, outperforming existing solutions like Parade/Tantivy. This open-source tool enhances Postgres' capabilities in handling AI-centric workloads, showing significant improvements in query throughput. The development reflects rapid advancements in database technology, enabling more ambitious technical objectives.

LLM-echo 0.4 now includes input and output token fields in prompts, providing more detailed response data. This update aids in better understanding and debugging of model interactions.

A supply chain attack on Axios involved malicious npm dependencies, compromising security by stealing credentials. The attack exploited a leaked npm token, and the incident highlights the need for trusted publishing practices. This serves as a warning for developers to be vigilant about package dependencies.