A phone launch, a breaking story, a Vietnamese phrase — keyword search came up short. Semantic retrieval now covers 92% of AI Search.
Vietnam's number-two search engine and browser, reaching one in three internet users with over 600 million monthly searches, built on language models the team fine-tuned for Vietnamese.
Building AI search into a national-scale engine meant retrieving by meaning, not keyword, across hundreds of millions of items in milliseconds....
Web browser and search engine tailored for the Vietnamese market.
Vector database platform for building and scaling AI applications.
Cốc Cốc's Search relevance is part of this use case:
Related implementations across industries and use cases
Safety reads and high-volume writes fought for the same nodes. Milvus disaggregates them: 10B+ vectors, latency steady under load.
Keyword search failed on complex vehicle queries. Now, an AI pipeline rewrites messy questions to power shopping and service assistants.
Messy ingredient data broke text search, capping matches at 20%. AI semantic search now maps free-form inputs to unlock recipe imports.
Safety reads and high-volume writes fought for the same nodes. Milvus disaggregates them: 10B+ vectors, latency steady under load.
Elasticsearch kept every vector in RAM—cost-prohibitive at scale. One shared Milvus platform now runs 100+ workloads on 10B+ vectors.
Scattered data and basic coding tools bottlenecked engineers. A 9-agent AI workflow shifts them from writing code to directing AI teams.
Sequential AI testing bottlenecked development. Engineers built a concurrent, code-first pipeline to evaluate agent responses in seconds.
Tournaments running simultaneously meant an hour of manual checks each. AI agents now run them in minutes, freeing the team to be proactive.
Large AI training jobs meant fighting for preemptible slots or leaving campus. Marlowe gave any lab guaranteed multi-node access on demand.
A phone launch, a breaking story, a Vietnamese phrase — keyword search came up short. Semantic retrieval now covers 92% of AI Search.
Vietnam's number-two search engine and browser, reaching one in three internet users with over 600 million monthly searches, built on language models the team fine-tuned for Vietnamese.
Building AI search into a national-scale engine meant retrieving by meaning, not keyword, across hundreds of millions of items in milliseconds....
Web browser and search engine tailored for the Vietnamese market.
Vector database platform for building and scaling AI applications.
Cốc Cốc's Search relevance is part of this use case:
Related implementations across industries and use cases
Safety reads and high-volume writes fought for the same nodes. Milvus disaggregates them: 10B+ vectors, latency steady under load.
Keyword search failed on complex vehicle queries. Now, an AI pipeline rewrites messy questions to power shopping and service assistants.
Messy ingredient data broke text search, capping matches at 20%. AI semantic search now maps free-form inputs to unlock recipe imports.
Safety reads and high-volume writes fought for the same nodes. Milvus disaggregates them: 10B+ vectors, latency steady under load.
Elasticsearch kept every vector in RAM—cost-prohibitive at scale. One shared Milvus platform now runs 100+ workloads on 10B+ vectors.
Scattered data and basic coding tools bottlenecked engineers. A 9-agent AI workflow shifts them from writing code to directing AI teams.
Sequential AI testing bottlenecked development. Engineers built a concurrent, code-first pipeline to evaluate agent responses in seconds.
Tournaments running simultaneously meant an hour of manual checks each. AI agents now run them in minutes, freeing the team to be proactive.
Large AI training jobs meant fighting for preemptible slots or leaving campus. Marlowe gave any lab guaranteed multi-node access on demand.