analiza aiqbench
Databricks has introduced an adaptive search model designed to optimize retrieval efficiency for AI agents handling multi-step queries without sacrificing accuracy. By dynamically determining the necessary number of search steps, this architecture addresses latency and computational costs inherent in complex evidence-gathering tasks. This advancement strengthens the foundational infrastructure for enterprise-grade agentic workflows within the Databricks ecosystem.
Databricks adds adaptive search model to speed agent retrieval
Databricks Inc. today expanded its Adaptive Instructed-Retriever search model to speed up response times for requests from artificial intelligence agents that require multiple rounds of retrieval. The company said the model is a retrieval building block for its Genie Code, Genie One and Genie Agents that matches the retrieval quality of several leading third-party and […] The post Databricks adds adaptive search model to speed agent retrieval appeared first on SiliconANGLE.
Databricks Inc. today expanded its Adaptive Instructed-Retriever search model to speed up response times for requests from artificial intelligence agents that require multiple rounds of retrieval. The company said the model is a retrieval building block for its Genie Code, Genie One and Genie Agents that matches the retrieval quality of several leading third-party and open-source models while responding twice as fast as Anthropic PBC’s Claude Sonnet 5, OpenAI Group PBC’s GPT-5.6…
Extras afișat conform termenilor RSS ai publicației · 72 cuvinte · textul integral și figurile sunt pe site-ul publicației
Subiecte conexe
Operationalizing Genie Ontology in Your Data Stack
Databricks · 1 sept. 2026
Adaptive Instructed-Retriever: Frontier-Quality Search at 2x Lower Latency
Databricks · 9 sept. 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026
[AINews] not much happened today
Latent Space · 10 sept. 2026