🆕 tracks featured on Beeb 6 within 10 days of release

Playlist · ohrenweide · 2002 items · 174 saves

Chroma Context-1: Training a Self-Editing Search Agent

Retrieval pipelines typically operate in a single pass, which poses a problem when the information required to answer a question is spread across multiple documents or requires intermediate reasoning to locate. In practice, many real-world queries require multi-hop retrieval, in which the output of one search informs the next. Recent work has shown that frontier LLMs perform this multi-hop search effectively through a process known as agentic search, simply defined as a loop of LLM calls with search tools. This mode of search often comes with significant cost and latency due to their use of frontier-scale LLMs. We introduce Chroma Context-1, a 20B parameter agentic search model derived from gpt-oss-20B that achieves retrieval performance comparable to frontier-scale LLMs at a fraction of the cost and up to 10x faster inference speed. Context-1 is designed to be used as a subagent in conjunction with a frontier reasoning model. Given a query, it produces a ranked list of documents that are relevant to satisfying the query. The model is trained to decompose queries into subqueries, iteratively search a corpus, and selectively edit its own context to free capacity for further exploration.

Chroma Q Color Force 3 - La couleur se renForce !

Les ingénieurs R&D de Chroma-Q frappent fort ! Le Color Force-3, barre LED à haut niveau de performances vise des utilisations de type cyclo, théâtre, architectural mais aussi le live !

#321: Working With Metadata in Chroma - Python Friday