amercader / ckanext-embeddings Goto Github PK
View Code? Open in Web Editor NEWWIP
License: GNU Affero General Public License v3.0
ckanext-embeddings's People
Contributors
Stargazers
Watchers
ckanext-embeddings's Issues
Embeddings storage
The first approach used was to create a separate command that created the embeddings and stored them in the database using pgvector. But to implement Semantic Search we have to index the embedding in Solr anyway so to simplify we dropped pgvector and the embeddings table entirely and just computed the embedding every time we are indexing a dataset (in the before_dataset_index plugin hook).
This has the benefit of not having to worry about the embeddings being up to date if you for instance update a dataset title, but it's very likely not performant enough, certainly when calling an external API because the hooks are called on each individual dataset, so we can't submit data in bulk.
A probably better option would be to have the embeddings cached in the database, being created beforehand in the after_dataset_create and after_dataset_update hooks. We might not even need pgvector, just store them as arrays of floats or even strings, which is what we actually send to Solr.
An additional CLI command to refresh all (or some) embeddings would still be useful to change models, etc
Better UI for the Semantic search
The standard search UI hasn’t been modified to account for this fact, but it probably should.
Rather than “X results returned” the semantic search is more like “X closest datasets to the query term”, and the ordering is always "Similarity"
Can not install on ckan/ckan-dev images
You get a pip error when trying to install sentence-transformers:
ERROR: Cannot install -r requirements.txt (line 4) because these package versions have conflicting dependencies.
The conflict is caused by:
ERROR: ResolutionImpossible: for help visit https://pip.pypa.io/en/latest/topics/dependency-resolution/#dealing-with-dependency-conflicts
sentence-transformers 2.5.1 depends on torch>=1.11.0
sentence-transformers 2.5.0 depends on torch>=1.11.0
[...]
sentence-transformers 0.1.0 depends on torch>=1.0.1
To fix this you could try to:
1. loosen the range of package versions you've specified
2. remove package versions to allow pip attempt to solve the dependency conflict
https://github.com/amercader/ckanext-embeddings/actions/runs/8325293260/job/22778617554
Replicating it locally:
docker run --rm ckan/ckan-dev:2.10 python --version
Python 3.10.13
Pinning to the latest version:
docker run --rm ckan/ckan-dev:2.10 pip install sentence-transformers==2.5.1
Collecting sentence-transformers==2.5.1
Downloading sentence_transformers-2.5.1-py3-none-any.whl.metadata (11 kB)
Collecting transformers<5.0.0,>=4.32.0 (from sentence-transformers==2.5.1)
Downloading transformers-4.38.2-py3-none-any.whl.metadata (130 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 130.7/130.7 kB 3.5 MB/s eta 0:00:00
Collecting tqdm (from sentence-transformers==2.5.1)
Downloading tqdm-4.66.2-py3-none-any.whl.metadata (57 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 57.6/57.6 kB 4.6 MB/s eta 0:00:00
INFO: pip is looking at multiple versions of sentence-transformers to determine which version is compatible with other requirements. This could take a while.
ERROR: Could not find a version that satisfies the requirement torch>=1.11.0 (from sentence-transformers) (from versions: none)
ERROR: No matching distribution found for torch>=1.11.0
That would hint at pytorch not supporting Python 3.10, but that sounds unlikely? Will keep digging
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.