Comments (4)
There are additional models available on Hugging Face's model hub.
There are also additional models provided by the Sentence Transformers team. #17 has an example of how to use one of these.
from txtai.
Thanks for the answer, I will try with a couple of different models from the hub !
Adding to that, do you have an example on how to pass a tokenizer, to don't use the default at:
txtai/src/python/txtai/extractor.py
Line 33 in c85256f
from txtai.
For the tokenizer, you can pass any object that implements the method:
def tokenize(text)
In this method, you can split the text as you see fit. Could be as simple as text.split(). There is also a lower level abstraction called Pipeline, that you may find more useful if you want to skip the tokenization/content filtering process all together.
from txtai.
Thanks a lot 👍
from txtai.
Related Issues (20)
- Add RAG API endpoint
- Rename Extractor pipeline to RAG
- Add RAG deepdive notebook
- json Response Error when trying to use ollama embeddings in txtai HOT 3
- Feature request : Advanced Reasoning and Inference HOT 1
- Feature request : Enhanced Geospatial and Temporal Search HOT 1
- Feature request : LLM Integration for Knowledge Graph Enhancement HOT 3
- Feature request : Advanced Ontology Management HOT 2
- Add RAG example application
- Segmentation fault when calling embeddings.index HOT 8
- Support max_seq_length parameter with model pooling
- Fix issue with setting quantize=False in HFTrainer pipeline
- Improve textractor pipeline
- Support `<pre>` blocks with Textractor
- Translation: AttributeError: 'ModelInfo' object has no attribute 'modelId' HOT 5
- Example code (10_Extract_text_from_documents.ipynb) does not work: No module named 'txtai.pipeline'; 'txtai' is not a package HOT 10
- Update HF LLM to reduce noisy warnings
- Add new functionality to RAG application
- pipeline not detected on MacOS HOT 4
- 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 txtai.