Comments (4)
Hi @AntoninLeroy
Sorry for the late response
It seems like you used to use pydantic<2.0.0, stored your objects and then updated to pydantic>=2.0.0
Your database is not corrupted
I guess you just need to switch back to pydantic<2.0.0
Btw, it seems like you are running it in production and using local mode.
We usually recommend to switch to qdrant in docker, or qdrant cloud to run applications in production.
from qdrant-client.
Thanks for your answer. Yes it was the issue because I had to upgrade vllm version. I had to create a new database and re-vectorise my documents.
I agree that I should use docker but I'm not sure how on my specific offline setup ? Is it something possible without being connected to internet ?
from qdrant-client.
If you have docker installed on your server, then it is not complicated, you just need to save qdrant docker image to an archive and deliver it to the server somehow, and then load it
If you don't have docker installed on the server, it might be a little bit more complicated, but should be still doable, there should be instructions on docker website how to install it without internet connection
from qdrant-client.
@joein Thanks will try to do that.
from qdrant-client.
Related Issues (20)
- Check vectors for NaN in local mode HOT 2
- qdrant_client.get_fastembed_vector_params() with upload_collection HOT 4
- Python Application Crashes on Attempting to Retrieve Non-existent Collection via QdrantClient in GRPC Mode HOT 2
- Add note about batching into README.md HOT 1
- grpc.PointStruct.PayloadEntry errror HOT 2
- How to upload collection asynchronous HOT 2
- Feature Request: Add ability to have properties/metadata for a collection
- qdrant_client.QdrantClient never returns HOT 1
- Datetime timezone parsing inconsistency HOT 1
- investigate local mode close HOT 1
- client method to recover from snapshots
- Make httpx client aware of timeouts passed to methods HOT 2
- Socket error using Windows and REST
- UnexpectedResponse: Unexpected Response: 400 (Bad Request) Raw response content: b'{"status":{"error":"Format error in JSON body: data did not match any variant of untagged enum PointInsertOperations"},"time":0.0}' HOT 2
- Datetime inconsistency between Qdrant local and remote HOT 2
- add `key` parameter to `set_payload` HOT 2
- add sparse embed support from fastembed 0.2.3 HOT 1
- high score with empty document string HOT 6
- Upload batch function of rest uploader is always attempting to upsert points max_retries (3) times. HOT 2
- ValueError: could not broadcast input array from shape (768,) into shape (384,) HOT 1
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 qdrant-client.