Comments (4)
Update here!
- You can update the index by just adding more items with
add_items
. You might need to check the size of the index first however andresize_index
first. No idea what the logic is around how expensive this is.. cons of making it too large, etc. - You can soft delete using
mark_deleted
andunmark_deleted
. Seems the ideal approach is to tombstone items and then have a background job clean things up. This is what weaviate did for example.
some relevant links
So the next step here is to proof of concept growing the index. As well as proof of concept around deleting items.
from chroma.
Getting close on this... I need to figure out how to use RETURNING
in the context of executemany
in python. It should be possible, but it's not working as I expect... Going to run a test in the CLI next.
from chroma.
Not worth implementing until we swap out duckdb.
from chroma.
Moving to backlog
from chroma.
Related Issues (20)
- [Bug]: Client & Persistent Client are retrieving different documents HOT 4
- [Install issue]: type object 'CreateCollection' has no attribute 'model_validate' during Create Index HOT 3
- [Feature Request]: TTL for entries HOT 1
- [Bug]: Upserting the same data causes the SQLite db to grow by 50-100% HOT 3
- [Bug]: sqlite3.OperationalError: no such column: collections.topic HOT 7
- [Install issue]: Use my own embedding function add data error HOT 3
- No OllamaEmbeddingFunction in latest release of chromadb/npm module HOT 5
- [BLD]: Matrix test for Node 16+
- [Feature Request]: Langchain plugin for Chroma always tries to create the collection even if the collection already exists. HOT 13
- [Feature Request]: Issue with Data Structure in Chroma DB Collections HOT 2
- [Bug]: Missing OllamaEmbeddingFunction when using chromadb==0.5.0 HOT 2
- [Feature Request]: Set ef_search per query HOT 3
- [Feature Request]: Bump black to 24.4.2
- [Bug]: "Cannot submit more than 5,461 embeddings at once. Please submit your embeddings in batches of size 5,461 or less." but on running *.delete* HOT 5
- [Feature Request]: Async.io suport for python HOT 1
- [Feature Request]: Docs to be crawler friendly, and LLM discoverable HOT 2
- [Bug]: "Collection is not created" message despite being returned by list_collections method HOT 6
- [Bug]: client/server mode RuntimeError: coroutine raised StopIteration HOT 6
- [Bug]: Type mismatch for embedding function HOT 6
- [Bug]: where not equals clause not working HOT 2
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 chroma.