Comments (11)
Ok, understood. I will add this functionality today.
Thanks for sharing
from sharptoken.
See my first comment.
from sharptoken.
Hello @thomasdc !
Thanks for raising an issue.
As far as i understand, embeddings algorithms are caclulated on OpenAI side. This algorithm (most likely some neural network) is not publicly available
from sharptoken.
According to the mentioned docs it uses cl100k_base
.
from sharptoken.
@thomasdc could you share please expected behavior?
Would you like to have smth like ?
var encoding = GptEncoding.GetEncodingForEmbeddingModel("text-embedding-3-large");
from sharptoken.
GptEncoding.GetEncodingForModel("text-embedding-ada-002");
was working fine, but throws for text-embedding-3-large
from sharptoken.
https://github.com/dmitry-brazhenko/SharpToken/pulls
from sharptoken.
Thanks for your feddback. I just introduced this change. Should work in the newer version (1.2.15) once it is available in nuget. Probably in 1-2 hours
from sharptoken.
Ok thanks, can you add small
as well?
from sharptoken.
@thomasdc could you share the full name please? I will add it
from sharptoken.
Sorry, I missed it.
#29
it should become available in v.1.2.16
Please let me know if smth does not work
from sharptoken.
Related Issues (15)
- outdated lib Newtonsoft HOT 1
- gpt-3.5-turbo-16k Not Supported HOT 1
- Performance compared to TiktokenSharp, Tokenizer HOT 7
- Implement MODEL_PREFIX_FOR_ENCODING HOT 2
- Add Microsoft.SourceLink.GitHub to publish repo info/commit to nuget.org HOT 1
- GptEncoding thread-safe? HOT 4
- Anthropic (claude) support HOT 5
- cohere support
- o200k_base support HOT 1
- Gbt4o support
- GPT-4o mini encoding HOT 1
- SharpToken.GptEncoding.GetEncoding(o200k_base) takes minutes HOT 1
- Missing model name for 3.5 turbo Azure Deployment model HOT 5
- Incorrect token count with Cyrillic 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 sharptoken.