Skip to content
This repository has been archived by the owner on May 10, 2024. It is now read-only.

WIP: add documentation memory #211

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions docs/advanced/index.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
---
slug: /advanced
title: 🛰 Advanced
hide_title: true
---

# 🔌 Advanced

Advanced topic.
17 changes: 17 additions & 0 deletions docs/advanced/memory.md
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:
Copy link
Contributor

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.

- 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.
23 changes: 23 additions & 0 deletions sidebars.js
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,12 @@ const sidebars = {
label: '🔧 API Docs',
className: 'category-link',
},
{
type: 'link',
href: '/advanced',
label: '🛰 Advanced',
Copy link
Contributor

Choose a reason for hiding this comment

The 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: [
{
Expand All @@ -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',
Expand Down