Comments (3)
MaartenGr
commented on July 17, 2024
Currently, this is only possible by generating the embeddings yourself and then passing them through model.fit_transform(docs, embeddings). Having said that... I am currently working on v0.5 (#46) which allows you to use Flair package in order to easily use huggingface transformer embeddings.
I am aiming to complete this in the coming week 😄
from bertopic.
khairiyah98
commented on July 17, 2024
I see, alright thanks! Looking forward to it
from bertopic.
MaartenGr
commented on July 17, 2024
@khairiyah98 It took a while but v0.5 is finally here! You can now use both custom SentenceTransformers and Flair models which allows you to use all 🤗 transformer models. You can find the changelog here and the tutorial for using custom embedding models here. Hopefully this helps you out a bit. If not, please let me know!
from bertopic.
Related Issues (20)
- I'm trying to use zeroshot topic model,but i encounter an error,Can anyone please help me?TypeError: BERTopic.__init__() got an unexpected keyword argument 'zeroshot_topic_list' HOT 1
- Identical topics: some become outliers, some are assigned to their topic HOT 1
- TerminatedWorkerError:A worker process managed by the executor was unexpectedly terminated. This could be caused by a segmentation fault while calling the function or by an excessive memory usage causing the Operating System to kill the worker. The exit codes of the workers are {EXIT(1)} HOT 3
- TypeError:'NoneType' object is not subscriptable while calling topic_model.hierarchical_topics HOT 5
- Can't update model name when use notebook HOT 4
- Scikit-learn's HDBSCAN Implementation
- Issues with visualizations on loaded models. HOT 1
- (Zero-shot Topic Modeling) TypeError: object of type 'numpy.float64' has no len() HOT 1
- Additional representations did not update with topic reduction HOT 5
- [Guided Topic Modeling] ValueError: setting an array element with a sequence. HOT 6
- Array mismatch when try to fit new data HOT 1
- Does Bertopic support custom keyword extractor? HOT 5
- Why do I lose Names assigned by zero-shot after applying outlier reduction? HOT 1
- get_topic() with KeyBERTInspired? HOT 1
- Mismatch between old OpenAI API in bertopic/backend/_openai and current OpenAI (v1.33.0) HOT 1
- OpenAI Embedding HOT 1
- Potential bug with the PartOfSpeech class due to lower case matching HOT 1
- Chosen represented Topic HOT 5
- merge_topics from a model loaded from safe tensors HOT 1
- Add test coverage around OpenAI(BaseRepresentation) HOT 3
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 bertopic.