Comments (3)
Just write all the data and let Vespa deal with partitioning it for you.
Yes, it may be slightly more efficient to pre-partition when your queries only searches precisely one partition, but this is a special case, and I don't think the potential benefit outweights the additional complexity and interface surface. It's not much faster than filtering on an attribute with fast-search, and once you need to search across multiple partitions, it becomes slower.
from vespa.
Note that I want double partitioning (so each 'partition' will be distibuted).
And while it is a special case for Vespa, it's a normal case for this app to search 1/100 of data.
And the complexity on the app side would be small I think.
And I wouldn't need to keep all data(attributes) in memory, at leas not the old ones. While fast-search it would require even more memory.
I don't understand how fast-search would make things faster though ? You still have to merge bitsets from the other filters. (and partitioning will just make all bitsets smaller)
Needs to be some more explanation in the docs I think (like doc-types are stored separately? fast-search? attributes in-memory all-time or by-request, does each node have 1 inverted-index (or per-core))
Maybe by using different document-types ? Assuming they live in separate inverted-indexes.
from vespa.
Each document type is a separate instance of everything, yes.
Few people have the technical expertise to appreciate more implementation details in the doc, so I'm not sure it is worth it ...
Fast-search adds a B-tree over the attribute. Since (presumably) this attribute will be a strong filter it will be used to skip most of the document space without further work.
If you use partition to put more data on the node than you can search, then there needs to be protection from searching too many of them at the same time because one such query would then kill all the nodes. And, you'd need to have support for unloading a partition when another is needed (or, some more complicated eviction strategy where N can be kept at the same time). But at what time do you unload given that many queries run in parallel. And if you can make that work one query for an old partition will make the response time of all subsequent queries go through the roof ... this is the kind of complexity I mean.
At the very least this would be premature optimization. I suggest you try the straightforward approach first.
from vespa.
Related Issues (20)
- Short form for indexed tensors representing binary data requires "values" HOT 1
- Error when onnx model is fp16 HOT 3
- Generate a sample Vespa JSON payload given a Vespa tensor type
- Vespa CLI option to delete all documents in an application
- What's the difference between Tensor and Vector within other vector databases? HOT 1
- Vespa Deploy fails for application package with model files HOT 3
- Add matched-elements-only support for index fields
- Syntax support for configuring distance-metric within the field
- No 'input' query param when use "vespa query yql=xxx" HOT 4
- Support setting metrics-proxy heap size HOT 3
- All Search Nodes are crashing HOT 4
- Potential Memory Leak Issue in PrometheusModel class HOT 4
- Node coming up with latest deployed application version after being down HOT 5
- Configurable max token length
- Add embedding instruction prompt support for to hf-embedder HOT 1
- NPE while deploying HOT 1
- Cluster Crashes When Distribution Key Is Too High HOT 2
- Error code - ORT_INVALID_PROTOBUF HOT 2
- Vespa content pod created snapshot folder owned by nobody user in a high RAM situation HOT 3
- Add deploy time warning about combining paged attributes with index (hnsw) or fast-search
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from vespa.