Skip to content

Commit

Permalink
📝 Add links
Browse files Browse the repository at this point in the history 
Signed-off-by: vankichi <kyukawa315@gmail.com>
  • Loading branch information
@vankichi
vankichi committed Jan 26, 2024
1 parent 78cbe85 commit 89f03c5
Showing 1 changed file with 15 additions and 11 deletions.
26 changes: 15 additions & 11 deletions docs/performance/tuning-search-performance.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ flowchart TD

The best practice is:

1. Measure Linear Search performance and use it as a baseline for Search API
1. Measure [Linear Search](../../docs/api/search.md#linearsearch-rpc) performance and use it as a baseline for Search API
1. Repeat tuning to improve precision and measure Search API until the conditions are met
1. Repeat tuning to improve latency and measure Search API until the conditions are met

Expand All @@ -40,21 +40,25 @@ When the results are not good by Linear Search API, it may need to rethink the e

There are two viewpoints, client-side and cluster-side, for improving search performance.

<div class="notice">
There is a trade-off between search speed and accuracy, so tuning accuracy at first is recommended.
</div>

### Client side

On the client side, parameters of `Search.Config` will affect the search result.
On the client side, parameters of [`Search.Config`](../../docs/api/search.md#input) will affect the search result.

| | description | how does it affect? | memo |
| :---------- | :------------------------------------------------ | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------ |
| radius | the search radius for NGT | Define the search range when NGT searches the nearest neighbors | -1 is recommended. |
| epsilon | the search coefficient for NGT | Expansion factor of the NGT search range.<BR>Search operation time increases when the epsilon is big. | recommended value range: `0.01 ~ 0.5`<BR>default value: `0.1` |
| timeout(ns) | max time duration until receiving search results. | An error will be returned if the set `num` search results cannot be obtained within the set time.<BR>By setting `min_num`, the search results will be returned if more than `min_num` can be searched within the time. | default value: `3,000,000,000ns` |
| | description | how does it affect? | memo |
| :---------- | :---------------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------ |
| radius | the search radius for NGT<BR>[ref: search_radius](https://github.com/yahoojapan/NGT/tree/main/bin/ngt#search) | Define the search range when NGT searches the nearest neighbors | recommended value: `-1` |
| epsilon | the search coefficient for NGT<BR>[ref: search_range_coefficient](https://github.com/yahoojapan/NGT/tree/main/bin/ngt#search) | Expansion factor of the NGT search range.<BR>Search operation time increases when the epsilon is big. | recommended value range: `0.01 ~ 0.3`<BR>default value: `0.1` |
| timeout(ns) | max time duration until receiving search results. | An error will be returned if the set `num` search results cannot be obtained within the set time.<BR>By setting `min_num`, the search results will be returned if more than `min_num` can be searched within the time. | default value: `3,000,000,000ns` |

### Cluster-side

On the cluster side, these parameters can be set by `values.yaml`, affect the search result.

| | description | how does it affect? | Memo |
| :--------------------------- | :------------------------------------------------------------ | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------ |
| agent.ngt.creation_edge_size | Number of nodes connected to one node | It helps reduce unreachable edges.<BR>The larger it is, the denser the graph structure will be, but the memory usage, search speed, and index construction time will increase accordingly. | default value: `20` |
| agent.ngt.search_edge_size | Number of nodes to search from the origin node when searching | The number of nodes to search will increase.<BR>Accuracy will be higher, but speed will be lower.<BR>Adjust if adjusting the radius and epsilon does not improve the situation. | default value: `10` |
| | description | how does it affect? | Memo |
| :--------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------ |
| agent.ngt.creation_edge_size | Number of nodes connected to one node<BR>[ref: no_of_edges](https://github.com/yahoojapan/NGT/tree/main/bin/ngt#create) | It helps reduce unreachable edges.<BR>The larger it is, the denser the graph structure will be, but the memory usage, search speed, and index construction time will increase accordingly. | default value: `20` |
| agent.ngt.search_edge_size | Number of nodes to search from the origin node when searching<BR>[ref: no_of_edges_at_search_at](https://github.com/yahoojapan/NGT/tree/main/bin/ngt#create) | The number of nodes to search will increase.<BR>Accuracy will be higher, but speed will be lower.<BR>Adjust if adjusting the radius and epsilon does not improve the situation. | default value: `10` |

0 comments on commit 89f03c5

Please sign in to comment.