This repository has been archived by the owner on May 10, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 111
WIP: add documentation memory #211
Open
nicolasgere
wants to merge
1
commit into
main
Choose a base branch
from
nicolas/add-documentation-memory-management
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,9 @@ | ||
--- | ||
slug: /advanced | ||
title: 🛰 Advanced | ||
hide_title: true | ||
--- | ||
|
||
# 🔌 Advanced | ||
|
||
Advanced topic. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,17 @@ | ||
--- | ||
slug: /advanced/memory | ||
title: 💽 Memory management | ||
--- | ||
|
||
## Memory management | ||
There are situations where you might need to limit the memory usage of Chroma. By default, Chroma loads the entire queried collection into its in-memory cache. To address this, we have implemented a mechanism to set a memory limit, which Chroma endeavors to adhere to as closely as possible through various cache eviction strategies. Here are some important points to note: | ||
- Loading a collection into the cache can introduce some latency, as this process consumes resources. | ||
- This approach is based on best effort, considering that real-time monitoring of RAM usage per collection is an estimation. | ||
|
||
##### Available Cache Strategies | ||
- **Default**: Under this policy, there is no eviction process. Chroma loads all queried collections into memory and retains them until the process is restarted. | ||
- **LRU** (Least Recently Used): In this strategy, Chroma evicts the least recently used collection to free up capacity for the newly queried collection. However,if a collection is larger than the set limit, Chroma will still attempt to load it, evicting other collections if necessary. | ||
|
||
|
||
#### Setup | ||
Set the environment variable `CHROMA_SEGMENT_CACHE_POLICY=LRU` to enable the LRU caching strategy. Additionally, define the memory limit by setting `CHROMA_MEMORY_LIMIT_BYTES=1000000000`, which restricts the cache to a maximum of 1GB. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -49,6 +49,12 @@ const sidebars = { | |
label: '🔧 API Docs', | ||
className: 'category-link', | ||
}, | ||
{ | ||
type: 'link', | ||
href: '/advanced', | ||
label: '🛰 Advanced', | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Does it make sense to make the title a little more descriptive? Something like "Advanced Usage"? |
||
className: 'category-link', | ||
}, | ||
], | ||
integrations: [ | ||
{ | ||
|
@@ -72,6 +78,23 @@ const sidebars = { | |
], | ||
}, | ||
], | ||
advanced: [ | ||
{ | ||
type: 'link', | ||
label: '← Home', | ||
href: '/' | ||
}, | ||
'advanced/index', | ||
{ | ||
type: 'category', | ||
label: 'Advanced', | ||
collapsed: false, | ||
className: 'category-header', | ||
items: [ | ||
'advanced/memory', | ||
], | ||
}, | ||
], | ||
embeddings: [ | ||
{ | ||
type: 'link', | ||
|
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we also add a note in the list below that unloading happens reactively as the user queries new collections, old ones are unloaded.