• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Announcement

    Query profiling is generally available in Weaviate v1.38

    Weaviate says setting query_profile in request metadata returns search timings by shard and node alongside the response.

    Connor ShortenCS
    Weaviate AI DatabaseWA
    2 Sources, ,

    TLDR

    Weaviate says query profiling is generally available in v1.38. Setting query_profile in request metadata returns timings from the shards involved in a search. In Weaviate’s example, object hydration takes 36.8ms of a shard’s 48.2ms, compared with 8.4ms for vector search. The company suggests investigating page-cache misses, storage latency, result limits or object size rather than assuming vector search is the bottleneck.

    Combined views

    505

    2 Sources, first seen 2h ago

    Combined views

    505

    2 Sources, first seen 2h ago

    7 likes
    2h ago
    first seen 2h ago
    7 likes
    1 comments
    6 reposts
    1 comments
    6 reposts
    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    Weaviate AI Database@weaviate_ioA slow query is easy to spot. Explaining 𝘸𝘩𝘺 it's slow is the hard part. The latency could come from HNSW traversal, resolving a filter, BM25 scoring, compression rescoring, or fetching objects from disk. Each points to a completely different fix. 𝗤𝘂𝗲𝗿𝘆 𝗽𝗿𝗼𝗳𝗶𝗹𝗶𝗻𝗴 𝗶𝗻 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 makes that breakdown available for each specific search. Set 𝗾𝘂𝗲𝗿𝘆_𝗽𝗿𝗼𝗳𝗶𝗹𝗲 in the request metadata and the profile is returned alongside the response, organized by shard and node. The coordinating node collects timings from every shard involved, so distributed queries no longer require manually piecing together logs from multiple nodes. Consider a shard that takes 48.2ms: • Vector search: 8.4ms • Filter resolution: 2.1ms • Object hydration: 36.8ms HNSW isn't the bottleneck here. Object hydration is. Blindly increasing compute would miss the problem entirely. Page-cache misses, storage latency, a large result limit, or oversized objects are the more useful places to investigate. 𝗤𝘂𝗲𝗿𝘆 𝗽𝗿𝗼𝗳𝗶𝗹𝗶𝗻𝗴 is generally available in Weaviate v1.38. Learn more about it in our blog: https://weaviate.io/blog/query-profiling?utm_source=channels&utm_medium=w_social&utm_campaign=blog_post&utm_content=diagram_post_8054541622h
    Connor Shorten@CShorten30RT @weaviate_io: A slow query is easy to spot. Explaining 𝘸𝘩𝘺 it's slow is the hard part. The latency could come from HNSW traversal, reso…2h

    2 Sources

    Weaviate AI Database@weaviate_ioA slow query is easy to spot. Explaining 𝘸𝘩𝘺 it's slow is the hard part. The latency could come from HNSW traversal, resolving a filter, BM25 scoring, compression rescoring, or fetching objects from disk. Each points to a completely different fix. 𝗤𝘂𝗲𝗿𝘆 𝗽𝗿𝗼𝗳𝗶𝗹𝗶𝗻𝗴 𝗶𝗻 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲 makes that breakdown available for each specific search. Set 𝗾𝘂𝗲𝗿𝘆_𝗽𝗿𝗼𝗳𝗶𝗹𝗲 in the request metadata and the profile is returned alongside the response, organized by shard and node. The coordinating node collects timings from every shard involved, so distributed queries no longer require manually piecing together logs from multiple nodes. Consider a shard that takes 48.2ms: • Vector search: 8.4ms • Filter resolution: 2.1ms • Object hydration: 36.8ms HNSW isn't the bottleneck here. Object hydration is. Blindly increasing compute would miss the problem entirely. Page-cache misses, storage latency, a large result limit, or oversized objects are the more useful places to investigate. 𝗤𝘂𝗲𝗿𝘆 𝗽𝗿𝗼𝗳𝗶𝗹𝗶𝗻𝗴 is generally available in Weaviate v1.38. Learn more about it in our blog: https://weaviate.io/blog/query-profiling?utm_source=channels&utm_medium=w_social&utm_campaign=blog_post&utm_content=diagram_post_8054541622h
    Connor Shorten@CShorten30RT @weaviate_io: A slow query is easy to spot. Explaining 𝘸𝘩𝘺 it's slow is the hard part. The latency could come from HNSW traversal, reso…2h